diff options
Diffstat (limited to 'tools/testing')
56 files changed, 6208 insertions, 356 deletions
diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl index d08e214ec6e7..be93ab02b490 100755 --- a/tools/testing/ktest/ktest.pl +++ b/tools/testing/ktest/ktest.pl @@ -719,14 +719,14 @@ sub set_value { if ($buildonly && $lvalue =~ /^TEST_TYPE(\[.*\])?$/ && $prvalue ne "build") { # Note if a test is something other than build, then we - # will need other manditory options. + # will need other mandatory options. if ($prvalue ne "install") { # for bisect, we need to check BISECT_TYPE if ($prvalue ne "bisect") { $buildonly = 0; } } else { - # install still limits some manditory options. + # install still limits some mandatory options. $buildonly = 2; } } @@ -735,7 +735,7 @@ sub set_value { if ($prvalue ne "install") { $buildonly = 0; } else { - # install still limits some manditory options. + # install still limits some mandatory options. $buildonly = 2; } } @@ -3989,7 +3989,7 @@ sub make_min_config { } } - # Save off all the current mandidory configs + # Save off all the current mandatory configs open (OUT, ">$temp_config") or die "Can't write to $temp_config"; foreach my $config (keys %keep_configs) { diff --git a/tools/testing/nvdimm/Kbuild b/tools/testing/nvdimm/Kbuild index 582db95127ed..405212be044a 100644 --- a/tools/testing/nvdimm/Kbuild +++ b/tools/testing/nvdimm/Kbuild @@ -14,6 +14,7 @@ ldflags-y += --wrap=devm_memremap_pages ldflags-y += --wrap=insert_resource ldflags-y += --wrap=remove_resource ldflags-y += --wrap=acpi_evaluate_object +ldflags-y += --wrap=acpi_evaluate_dsm DRIVERS := ../../../drivers NVDIMM_SRC := $(DRIVERS)/nvdimm diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c index 3ccef732fce9..64cae1a5deff 100644 --- a/tools/testing/nvdimm/test/iomap.c +++ b/tools/testing/nvdimm/test/iomap.c @@ -26,14 +26,17 @@ static LIST_HEAD(iomap_head); static struct iomap_ops { nfit_test_lookup_fn nfit_test_lookup; + nfit_test_evaluate_dsm_fn evaluate_dsm; struct list_head list; } iomap_ops = { .list = LIST_HEAD_INIT(iomap_ops.list), }; -void nfit_test_setup(nfit_test_lookup_fn lookup) +void nfit_test_setup(nfit_test_lookup_fn lookup, + nfit_test_evaluate_dsm_fn evaluate) { iomap_ops.nfit_test_lookup = lookup; + iomap_ops.evaluate_dsm = evaluate; list_add_rcu(&iomap_ops.list, &iomap_head); } EXPORT_SYMBOL(nfit_test_setup); @@ -367,4 +370,22 @@ acpi_status __wrap_acpi_evaluate_object(acpi_handle handle, acpi_string path, } EXPORT_SYMBOL(__wrap_acpi_evaluate_object); +union acpi_object * __wrap_acpi_evaluate_dsm(acpi_handle handle, const u8 *uuid, + u64 rev, u64 func, union acpi_object *argv4) +{ + union acpi_object *obj = ERR_PTR(-ENXIO); + struct iomap_ops *ops; + + rcu_read_lock(); + ops = list_first_or_null_rcu(&iomap_head, typeof(*ops), list); + if (ops) + obj = ops->evaluate_dsm(handle, uuid, rev, func, argv4); + rcu_read_unlock(); + + if (IS_ERR(obj)) + return acpi_evaluate_dsm(handle, uuid, rev, func, argv4); + return obj; +} +EXPORT_SYMBOL(__wrap_acpi_evaluate_dsm); + MODULE_LICENSE("GPL v2"); diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index c9a6458cb63e..71620fa95953 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -23,6 +23,7 @@ #include <linux/sizes.h> #include <linux/list.h> #include <linux/slab.h> +#include <nd-core.h> #include <nfit.h> #include <nd.h> #include "nfit_test.h" @@ -1506,6 +1507,225 @@ static int nfit_test_blk_do_io(struct nd_blk_region *ndbr, resource_size_t dpa, return 0; } +static unsigned long nfit_ctl_handle; + +union acpi_object *result; + +static union acpi_object *nfit_test_evaluate_dsm(acpi_handle handle, + const u8 *uuid, u64 rev, u64 func, union acpi_object *argv4) +{ + if (handle != &nfit_ctl_handle) + return ERR_PTR(-ENXIO); + + return result; +} + +static int setup_result(void *buf, size_t size) +{ + result = kmalloc(sizeof(union acpi_object) + size, GFP_KERNEL); + if (!result) + return -ENOMEM; + result->package.type = ACPI_TYPE_BUFFER, + result->buffer.pointer = (void *) (result + 1); + result->buffer.length = size; + memcpy(result->buffer.pointer, buf, size); + memset(buf, 0, size); + return 0; +} + +static int nfit_ctl_test(struct device *dev) +{ + int rc, cmd_rc; + struct nvdimm *nvdimm; + struct acpi_device *adev; + struct nfit_mem *nfit_mem; + struct nd_ars_record *record; + struct acpi_nfit_desc *acpi_desc; + const u64 test_val = 0x0123456789abcdefULL; + unsigned long mask, cmd_size, offset; + union { + struct nd_cmd_get_config_size cfg_size; + struct nd_cmd_ars_status ars_stat; + struct nd_cmd_ars_cap ars_cap; + char buf[sizeof(struct nd_cmd_ars_status) + + sizeof(struct nd_ars_record)]; + } cmds; + + adev = devm_kzalloc(dev, sizeof(*adev), GFP_KERNEL); + if (!adev) + return -ENOMEM; + *adev = (struct acpi_device) { + .handle = &nfit_ctl_handle, + .dev = { + .init_name = "test-adev", + }, + }; + + acpi_desc = devm_kzalloc(dev, sizeof(*acpi_desc), GFP_KERNEL); + if (!acpi_desc) + return -ENOMEM; + *acpi_desc = (struct acpi_nfit_desc) { + .nd_desc = { + .cmd_mask = 1UL << ND_CMD_ARS_CAP + | 1UL << ND_CMD_ARS_START + | 1UL << ND_CMD_ARS_STATUS + | 1UL << ND_CMD_CLEAR_ERROR, + .module = THIS_MODULE, + .provider_name = "ACPI.NFIT", + .ndctl = acpi_nfit_ctl, + }, + .dev = &adev->dev, + }; + + nfit_mem = devm_kzalloc(dev, sizeof(*nfit_mem), GFP_KERNEL); + if (!nfit_mem) + return -ENOMEM; + + mask = 1UL << ND_CMD_SMART | 1UL << ND_CMD_SMART_THRESHOLD + | 1UL << ND_CMD_DIMM_FLAGS | 1UL << ND_CMD_GET_CONFIG_SIZE + | 1UL << ND_CMD_GET_CONFIG_DATA | 1UL << ND_CMD_SET_CONFIG_DATA + | 1UL << ND_CMD_VENDOR; + *nfit_mem = (struct nfit_mem) { + .adev = adev, + .family = NVDIMM_FAMILY_INTEL, + .dsm_mask = mask, + }; + + nvdimm = devm_kzalloc(dev, sizeof(*nvdimm), GFP_KERNEL); + if (!nvdimm) + return -ENOMEM; + *nvdimm = (struct nvdimm) { + .provider_data = nfit_mem, + .cmd_mask = mask, + .dev = { + .init_name = "test-dimm", + }, + }; + + + /* basic checkout of a typical 'get config size' command */ + cmd_size = sizeof(cmds.cfg_size); + cmds.cfg_size = (struct nd_cmd_get_config_size) { + .status = 0, + .config_size = SZ_128K, + .max_xfer = SZ_4K, + }; + rc = setup_result(cmds.buf, cmd_size); + if (rc) + return rc; + rc = acpi_nfit_ctl(&acpi_desc->nd_desc, nvdimm, ND_CMD_GET_CONFIG_SIZE, + cmds.buf, cmd_size, &cmd_rc); + + if (rc < 0 || cmd_rc || cmds.cfg_size.status != 0 + || cmds.cfg_size.config_size != SZ_128K + || cmds.cfg_size.max_xfer != SZ_4K) { + dev_dbg(dev, "%s: failed at: %d rc: %d cmd_rc: %d\n", + __func__, __LINE__, rc, cmd_rc); + return -EIO; + } + + + /* test ars_status with zero output */ + cmd_size = offsetof(struct nd_cmd_ars_status, address); + cmds.ars_stat = (struct nd_cmd_ars_status) { + .out_length = 0, + }; + rc = setup_result(cmds.buf, cmd_size); + if (rc) + return rc; + rc = acpi_nfit_ctl(&acpi_desc->nd_desc, NULL, ND_CMD_ARS_STATUS, + cmds.buf, cmd_size, &cmd_rc); + + if (rc < 0 || cmd_rc) { + dev_dbg(dev, "%s: failed at: %d rc: %d cmd_rc: %d\n", + __func__, __LINE__, rc, cmd_rc); + return -EIO; + } + + + /* test ars_cap with benign extended status */ + cmd_size = sizeof(cmds.ars_cap); + cmds.ars_cap = (struct nd_cmd_ars_cap) { + .status = ND_ARS_PERSISTENT << 16, + }; + offset = offsetof(struct nd_cmd_ars_cap, status); + rc = setup_result(cmds.buf + offset, cmd_size - offset); + if (rc) + return rc; + rc = acpi_nfit_ctl(&acpi_desc->nd_desc, NULL, ND_CMD_ARS_CAP, + cmds.buf, cmd_size, &cmd_rc); + + if (rc < 0 || cmd_rc) { + dev_dbg(dev, "%s: failed at: %d rc: %d cmd_rc: %d\n", + __func__, __LINE__, rc, cmd_rc); + return -EIO; + } + + + /* test ars_status with 'status' trimmed from 'out_length' */ + cmd_size = sizeof(cmds.ars_stat) + sizeof(struct nd_ars_record); + cmds.ars_stat = (struct nd_cmd_ars_status) { + .out_length = cmd_size - 4, + }; + record = &cmds.ars_stat.records[0]; + *record = (struct nd_ars_record) { + .length = test_val, + }; + rc = setup_result(cmds.buf, cmd_size); + if (rc) + return rc; + rc = acpi_nfit_ctl(&acpi_desc->nd_desc, NULL, ND_CMD_ARS_STATUS, + cmds.buf, cmd_size, &cmd_rc); + + if (rc < 0 || cmd_rc || record->length != test_val) { + dev_dbg(dev, "%s: failed at: %d rc: %d cmd_rc: %d\n", + __func__, __LINE__, rc, cmd_rc); + return -EIO; + } + + + /* test ars_status with 'Output (Size)' including 'status' */ + cmd_size = sizeof(cmds.ars_stat) + sizeof(struct nd_ars_record); + cmds.ars_stat = (struct nd_cmd_ars_status) { + .out_length = cmd_size, + }; + record = &cmds.ars_stat.records[0]; + *record = (struct nd_ars_record) { + .length = test_val, + }; + rc = setup_result(cmds.buf, cmd_size); + if (rc) + return rc; + rc = acpi_nfit_ctl(&acpi_desc->nd_desc, NULL, ND_CMD_ARS_STATUS, + cmds.buf, cmd_size, &cmd_rc); + + if (rc < 0 || cmd_rc || record->length != test_val) { + dev_dbg(dev, "%s: failed at: %d rc: %d cmd_rc: %d\n", + __func__, __LINE__, rc, cmd_rc); + return -EIO; + } + + + /* test extended status for get_config_size results in failure */ + cmd_size = sizeof(cmds.cfg_size); + cmds.cfg_size = (struct nd_cmd_get_config_size) { + .status = 1 << 16, + }; + rc = setup_result(cmds.buf, cmd_size); + if (rc) + return rc; + rc = acpi_nfit_ctl(&acpi_desc->nd_desc, nvdimm, ND_CMD_GET_CONFIG_SIZE, + cmds.buf, cmd_size, &cmd_rc); + + if (rc < 0 || cmd_rc >= 0) { + dev_dbg(dev, "%s: failed at: %d rc: %d cmd_rc: %d\n", + __func__, __LINE__, rc, cmd_rc); + return -EIO; + } + + return 0; +} + static int nfit_test_probe(struct platform_device *pdev) { struct nvdimm_bus_descriptor *nd_desc; @@ -1516,6 +1736,12 @@ static int nfit_test_probe(struct platform_device *pdev) union acpi_object *obj; int rc; + if (strcmp(dev_name(&pdev->dev), "nfit_test.0") == 0) { + rc = nfit_ctl_test(&pdev->dev); + if (rc) + return rc; + } + nfit_test = to_nfit_test(&pdev->dev); /* common alloc */ @@ -1639,11 +1865,13 @@ static __init int nfit_test_init(void) { int rc, i; - nfit_test_dimm = class_create(THIS_MODULE, "nfit_test_dimm"); - if (IS_ERR(nfit_test_dimm)) - return PTR_ERR(nfit_test_dimm); + nfit_test_setup(nfit_test_lookup, nfit_test_evaluate_dsm); - nfit_test_setup(nfit_test_lookup); + nfit_test_dimm = class_create(THIS_MODULE, "nfit_test_dimm"); + if (IS_ERR(nfit_test_dimm)) { + rc = PTR_ERR(nfit_test_dimm); + goto err_register; + } for (i = 0; i < NUM_NFITS; i++) { struct nfit_test *nfit_test; diff --git a/tools/testing/nvdimm/test/nfit_test.h b/tools/testing/nvdimm/test/nfit_test.h index c281dd2e5e2d..f54c0032c6ff 100644 --- a/tools/testing/nvdimm/test/nfit_test.h +++ b/tools/testing/nvdimm/test/nfit_test.h @@ -31,11 +31,17 @@ struct nfit_test_resource { void *buf; }; +union acpi_object; +typedef void *acpi_handle; + typedef struct nfit_test_resource *(*nfit_test_lookup_fn)(resource_size_t); +typedef union acpi_object *(*nfit_test_evaluate_dsm_fn)(acpi_handle handle, + const u8 *uuid, u64 rev, u64 func, union acpi_object *argv4); void __iomem *__wrap_ioremap_nocache(resource_size_t offset, unsigned long size); void __wrap_iounmap(volatile void __iomem *addr); -void nfit_test_setup(nfit_test_lookup_fn lookup); +void nfit_test_setup(nfit_test_lookup_fn lookup, + nfit_test_evaluate_dsm_fn evaluate); void nfit_test_teardown(void); struct nfit_test_resource *get_nfit_res(resource_size_t resource); #endif diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile index f2e07f2fd4b4..3635e4d3eca7 100644 --- a/tools/testing/radix-tree/Makefile +++ b/tools/testing/radix-tree/Makefile @@ -1,10 +1,14 @@ -CFLAGS += -I. -g -O2 -Wall -D_LGPL_SOURCE +CFLAGS += -I. -I../../include -g -O2 -Wall -D_LGPL_SOURCE LDFLAGS += -lpthread -lurcu TARGETS = main OFILES = main.o radix-tree.o linux.o test.o tag_check.o find_next_bit.o \ regression1.o regression2.o regression3.o multiorder.o \ - iteration_check.o + iteration_check.o benchmark.o + +ifdef BENCHMARK + CFLAGS += -DBENCHMARK=1 +endif targets: $(TARGETS) @@ -14,7 +18,12 @@ main: $(OFILES) clean: $(RM) -f $(TARGETS) *.o radix-tree.c -$(OFILES): *.h */*.h ../../../include/linux/radix-tree.h ../../include/linux/*.h +find_next_bit.o: ../../lib/find_bit.c + $(CC) $(CFLAGS) -c -o $@ $< + +$(OFILES): *.h */*.h \ + ../../include/linux/*.h \ + ../../../include/linux/radix-tree.h radix-tree.c: ../../../lib/radix-tree.c sed -e 's/^static //' -e 's/__always_inline //' -e 's/inline //' < $< > $@ diff --git a/tools/testing/radix-tree/benchmark.c b/tools/testing/radix-tree/benchmark.c new file mode 100644 index 000000000000..215ca86c7605 --- /dev/null +++ b/tools/testing/radix-tree/benchmark.c @@ -0,0 +1,98 @@ +/* + * benchmark.c: + * Author: Konstantin Khlebnikov <koct9i@gmail.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ +#include <linux/radix-tree.h> +#include <linux/slab.h> +#include <linux/errno.h> +#include <time.h> +#include "test.h" + +#define NSEC_PER_SEC 1000000000L + +static long long benchmark_iter(struct radix_tree_root *root, bool tagged) +{ + volatile unsigned long sink = 0; + struct radix_tree_iter iter; + struct timespec start, finish; + long long nsec; + int l, loops = 1; + void **slot; + +#ifdef BENCHMARK +again: +#endif + clock_gettime(CLOCK_MONOTONIC, &start); + for (l = 0; l < loops; l++) { + if (tagged) { + radix_tree_for_each_tagged(slot, root, &iter, 0, 0) + sink ^= (unsigned long)slot; + } else { + radix_tree_for_each_slot(slot, root, &iter, 0) + sink ^= (unsigned long)slot; + } + } + clock_gettime(CLOCK_MONOTONIC, &finish); + + nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC + + (finish.tv_nsec - start.tv_nsec); + +#ifdef BENCHMARK + if (loops == 1 && nsec * 5 < NSEC_PER_SEC) { + loops = NSEC_PER_SEC / nsec / 4 + 1; + goto again; + } +#endif + + nsec /= loops; + return nsec; +} + +static void benchmark_size(unsigned long size, unsigned long step, int order) +{ + RADIX_TREE(tree, GFP_KERNEL); + long long normal, tagged; + unsigned long index; + + for (index = 0 ; index < size ; index += step) { + item_insert_order(&tree, index, order); + radix_tree_tag_set(&tree, index, 0); + } + + tagged = benchmark_iter(&tree, true); + normal = benchmark_iter(&tree, false); + + printf("Size %ld, step %6ld, order %d tagged %10lld ns, normal %10lld ns\n", + size, step, order, tagged, normal); + + item_kill_tree(&tree); + rcu_barrier(); +} + +void benchmark(void) +{ + unsigned long size[] = {1 << 10, 1 << 20, 0}; + unsigned long step[] = {1, 2, 7, 15, 63, 64, 65, + 128, 256, 512, 12345, 0}; + int c, s; + + printf("starting benchmarks\n"); + printf("RADIX_TREE_MAP_SHIFT = %d\n", RADIX_TREE_MAP_SHIFT); + + for (c = 0; size[c]; c++) + for (s = 0; step[s]; s++) + benchmark_size(size[c], step[s], 0); + + for (c = 0; size[c]; c++) + for (s = 0; step[s]; s++) + benchmark_size(size[c], step[s] << 9, 9); +} diff --git a/tools/testing/radix-tree/find_next_bit.c b/tools/testing/radix-tree/find_next_bit.c deleted file mode 100644 index d1c2178bb2d4..000000000000 --- a/tools/testing/radix-tree/find_next_bit.c +++ /dev/null @@ -1,57 +0,0 @@ -/* find_next_bit.c: fallback find next bit implementation - * - * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include <linux/types.h> -#include <linux/bitops.h> - -#define BITOP_WORD(nr) ((nr) / BITS_PER_LONG) - -/* - * Find the next set bit in a memory region. - */ -unsigned long find_next_bit(const unsigned long *addr, unsigned long size, - unsigned long offset) -{ - const unsigned long *p = addr + BITOP_WORD(offset); - unsigned long result = offset & ~(BITS_PER_LONG-1); - unsigned long tmp; - - if (offset >= size) - return size; - size -= result; - offset %= BITS_PER_LONG; - if (offset) { - tmp = *(p++); - tmp &= (~0UL << offset); - if (size < BITS_PER_LONG) - goto found_first; - if (tmp) - goto found_middle; - size -= BITS_PER_LONG; - result += BITS_PER_LONG; - } - while (size & ~(BITS_PER_LONG-1)) { - if ((tmp = *(p++))) - goto found_middle; - result += BITS_PER_LONG; - size -= BITS_PER_LONG; - } - if (!size) - return result; - tmp = *p; - -found_first: - tmp &= (~0UL >> (BITS_PER_LONG - size)); - if (tmp == 0UL) /* Are any bits set? */ - return result + size; /* Nope. */ -found_middle: - return result + __ffs(tmp); -} diff --git a/tools/testing/radix-tree/iteration_check.c b/tools/testing/radix-tree/iteration_check.c index 9adb8e7415a6..7572b7ed930e 100644 --- a/tools/testing/radix-tree/iteration_check.c +++ b/tools/testing/radix-tree/iteration_check.c @@ -16,35 +16,50 @@ #include <pthread.h> #include "test.h" -#define NUM_THREADS 4 -#define TAG 0 +#define NUM_THREADS 5 +#define MAX_IDX 100 +#define TAG 0 +#define NEW_TAG 1 + static pthread_mutex_t tree_lock = PTHREAD_MUTEX_INITIALIZER; static pthread_t threads[NUM_THREADS]; -RADIX_TREE(tree, GFP_KERNEL); -bool test_complete; +static unsigned int seeds[3]; +static RADIX_TREE(tree, GFP_KERNEL); +static bool test_complete; +static int max_order; /* relentlessly fill the tree with tagged entries */ static void *add_entries_fn(void *arg) { - int pgoff; + rcu_register_thread(); while (!test_complete) { - for (pgoff = 0; pgoff < 100; pgoff++) { + unsigned long pgoff; + int order; + + for (pgoff = 0; pgoff < MAX_IDX; pgoff++) { pthread_mutex_lock(&tree_lock); - if (item_insert(&tree, pgoff) == 0) - item_tag_set(&tree, pgoff, TAG); + for (order = max_order; order >= 0; order--) { + if (item_insert_order(&tree, pgoff, order) + == 0) { + item_tag_set(&tree, pgoff, TAG); + break; + } + } pthread_mutex_unlock(&tree_lock); } } + rcu_unregister_thread(); + return NULL; } /* * Iterate over the tagged entries, doing a radix_tree_iter_retry() as we find * things that have been removed and randomly resetting our iteration to the - * next chunk with radix_tree_iter_next(). Both radix_tree_iter_retry() and - * radix_tree_iter_next() cause radix_tree_next_slot() to be called with a + * next chunk with radix_tree_iter_resume(). Both radix_tree_iter_retry() and + * radix_tree_iter_resume() cause radix_tree_next_slot() to be called with a * NULL 'slot' variable. */ static void *tagged_iteration_fn(void *arg) @@ -52,17 +67,12 @@ static void *tagged_iteration_fn(void *arg) struct radix_tree_iter iter; void **slot; + rcu_register_thread(); + while (!test_complete) { rcu_read_lock(); radix_tree_for_each_tagged(slot, &tree, &iter, 0, TAG) { - void *entry; - int i; - - /* busy wait to let removals happen */ - for (i = 0; i < 1000000; i++) - ; - - entry = radix_tree_deref_slot(slot); + void *entry = radix_tree_deref_slot(slot); if (unlikely(!entry)) continue; @@ -71,20 +81,26 @@ static void *tagged_iteration_fn(void *arg) continue; } - if (rand() % 50 == 0) - slot = radix_tree_iter_next(&iter); + if (rand_r(&seeds[0]) % 50 == 0) { + slot = radix_tree_iter_resume(slot, &iter); + rcu_read_unlock(); + rcu_barrier(); + rcu_read_lock(); + } } rcu_read_unlock(); } + rcu_unregister_thread(); + return NULL; } /* * Iterate over the entries, doing a radix_tree_iter_retry() as we find things * that have been removed and randomly resetting our iteration to the next - * chunk with radix_tree_iter_next(). Both radix_tree_iter_retry() and - * radix_tree_iter_next() cause radix_tree_next_slot() to be called with a + * chunk with radix_tree_iter_resume(). Both radix_tree_iter_retry() and + * radix_tree_iter_resume() cause radix_tree_next_slot() to be called with a * NULL 'slot' variable. */ static void *untagged_iteration_fn(void *arg) @@ -92,17 +108,12 @@ static void *untagged_iteration_fn(void *arg) struct radix_tree_iter iter; void **slot; + rcu_register_thread(); + while (!test_complete) { rcu_read_lock(); radix_tree_for_each_slot(slot, &tree, &iter, 0) { - void *entry; - int i; - - /* busy wait to let removals happen */ - for (i = 0; i < 1000000; i++) - ; - - entry = radix_tree_deref_slot(slot); + void *entry = radix_tree_deref_slot(slot); if (unlikely(!entry)) continue; @@ -111,12 +122,18 @@ static void *untagged_iteration_fn(void *arg) continue; } - if (rand() % 50 == 0) - slot = radix_tree_iter_next(&iter); + if (rand_r(&seeds[1]) % 50 == 0) { + slot = radix_tree_iter_resume(slot, &iter); + rcu_read_unlock(); + rcu_barrier(); + rcu_read_lock(); + } } rcu_read_unlock(); } + rcu_unregister_thread(); + return NULL; } @@ -126,47 +143,71 @@ static void *untagged_iteration_fn(void *arg) */ static void *remove_entries_fn(void *arg) { + rcu_register_thread(); + while (!test_complete) { int pgoff; - pgoff = rand() % 100; + pgoff = rand_r(&seeds[2]) % MAX_IDX; pthread_mutex_lock(&tree_lock); item_delete(&tree, pgoff); pthread_mutex_unlock(&tree_lock); } + rcu_unregister_thread(); + + return NULL; +} + +static void *tag_entries_fn(void *arg) +{ + rcu_register_thread(); + + while (!test_complete) { + tag_tagged_items(&tree, &tree_lock, 0, MAX_IDX, 10, TAG, + NEW_TAG); + } + rcu_unregister_thread(); return NULL; } /* This is a unit test for a bug found by the syzkaller tester */ -void iteration_test(void) +void iteration_test(unsigned order, unsigned test_duration) { int i; - printf("Running iteration tests for 10 seconds\n"); + printf("Running %siteration tests for %d seconds\n", + order > 0 ? "multiorder " : "", test_duration); - srand(time(0)); + max_order = order; test_complete = false; + for (i = 0; i < 3; i++) + seeds[i] = rand(); + if (pthread_create(&threads[0], NULL, tagged_iteration_fn, NULL)) { - perror("pthread_create"); + perror("create tagged iteration thread"); exit(1); } if (pthread_create(&threads[1], NULL, untagged_iteration_fn, NULL)) { - perror("pthread_create"); + perror("create untagged iteration thread"); exit(1); } if (pthread_create(&threads[2], NULL, add_entries_fn, NULL)) { - perror("pthread_create"); + perror("create add entry thread"); exit(1); } if (pthread_create(&threads[3], NULL, remove_entries_fn, NULL)) { - perror("pthread_create"); + perror("create remove entry thread"); + exit(1); + } + if (pthread_create(&threads[4], NULL, tag_entries_fn, NULL)) { + perror("create tag entry thread"); exit(1); } - sleep(10); + sleep(test_duration); test_complete = true; for (i = 0; i < NUM_THREADS; i++) { diff --git a/tools/testing/radix-tree/linux.c b/tools/testing/radix-tree/linux.c index 154823737b20..d31ea7c9abec 100644 --- a/tools/testing/radix-tree/linux.c +++ b/tools/testing/radix-tree/linux.c @@ -1,14 +1,26 @@ #include <stdlib.h> #include <string.h> #include <malloc.h> +#include <pthread.h> #include <unistd.h> #include <assert.h> #include <linux/mempool.h> +#include <linux/poison.h> #include <linux/slab.h> +#include <linux/radix-tree.h> #include <urcu/uatomic.h> int nr_allocated; +int preempt_count; + +struct kmem_cache { + pthread_mutex_t lock; + int size; + int nr_objs; + void *objs; + void (*ctor)(void *); +}; void *mempool_alloc(mempool_t *pool, int gfp_mask) { @@ -33,19 +45,59 @@ mempool_t *mempool_create(int min_nr, mempool_alloc_t *alloc_fn, void *kmem_cache_alloc(struct kmem_cache *cachep, int flags) { - void *ret = malloc(cachep->size); - if (cachep->ctor) - cachep->ctor(ret); + struct radix_tree_node *node; + + if (flags & __GFP_NOWARN) + return NULL; + + pthread_mutex_lock(&cachep->lock); + if (cachep->nr_objs) { + cachep->nr_objs--; + node = cachep->objs; + cachep->objs = node->private_data; + pthread_mutex_unlock(&cachep->lock); + node->private_data = NULL; + } else { + pthread_mutex_unlock(&cachep->lock); + node = malloc(cachep->size); + if (cachep->ctor) + cachep->ctor(node); + } + uatomic_inc(&nr_allocated); - return ret; + return node; } void kmem_cache_free(struct kmem_cache *cachep, void *objp) { assert(objp); uatomic_dec(&nr_allocated); - memset(objp, 0, cachep->size); - free(objp); + pthread_mutex_lock(&cachep->lock); + if (cachep->nr_objs > 10) { + memset(objp, POISON_FREE, cachep->size); + free(objp); + } else { + struct radix_tree_node *node = objp; + cachep->nr_objs++; + node->private_data = cachep->objs; + cachep->objs = node; + } + pthread_mutex_unlock(&cachep->lock); +} + +void *kmalloc(size_t size, gfp_t gfp) +{ + void *ret = malloc(size); + uatomic_inc(&nr_allocated); + return ret; +} + +void kfree(void *p) +{ + if (!p) + return; + uatomic_dec(&nr_allocated); + free(p); } struct kmem_cache * @@ -54,7 +106,10 @@ kmem_cache_create(const char *name, size_t size, size_t offset, { struct kmem_cache *ret = malloc(sizeof(*ret)); + pthread_mutex_init(&ret->lock, NULL); ret->size = size; + ret->nr_objs = 0; + ret->objs = NULL; ret->ctor = ctor; return ret; } diff --git a/tools/testing/radix-tree/linux/bitops.h b/tools/testing/radix-tree/linux/bitops.h index 71d58427ab60..a13e9bc76eec 100644 --- a/tools/testing/radix-tree/linux/bitops.h +++ b/tools/testing/radix-tree/linux/bitops.h @@ -2,9 +2,14 @@ #define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ #include <linux/types.h> +#include <linux/bitops/find.h> +#include <linux/bitops/hweight.h> +#include <linux/kernel.h> -#define BITOP_MASK(nr) (1UL << ((nr) % BITS_PER_LONG)) -#define BITOP_WORD(nr) ((nr) / BITS_PER_LONG) +#define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG)) +#define BIT_WORD(nr) ((nr) / BITS_PER_LONG) +#define BITS_PER_BYTE 8 +#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long)) /** * __set_bit - Set a bit in memory @@ -17,16 +22,16 @@ */ static inline void __set_bit(int nr, volatile unsigned long *addr) { - unsigned long mask = BITOP_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr); + unsigned long mask = BIT_MASK(nr); + unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); *p |= mask; } static inline void __clear_bit(int nr, volatile unsigned long *addr) { - unsigned long mask = BITOP_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr); + unsigned long mask = BIT_MASK(nr); + unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); *p &= ~mask; } @@ -42,8 +47,8 @@ static inline void __clear_bit(int nr, volatile unsigned long *addr) */ static inline void __change_bit(int nr, volatile unsigned long *addr) { - unsigned long mask = BITOP_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr); + unsigned long mask = BIT_MASK(nr); + unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); *p ^= mask; } @@ -59,8 +64,8 @@ static inline void __change_bit(int nr, volatile unsigned long *addr) */ static inline int __test_and_set_bit(int nr, volatile unsigned long *addr) { - unsigned long mask = BITOP_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr); + unsigned long mask = BIT_MASK(nr); + unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); unsigned long old = *p; *p = old | mask; @@ -78,8 +83,8 @@ static inline int __test_and_set_bit(int nr, volatile unsigned long *addr) */ static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr) { - unsigned long mask = BITOP_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr); + unsigned long mask = BIT_MASK(nr); + unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); unsigned long old = *p; *p = old & ~mask; @@ -90,8 +95,8 @@ static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr) static inline int __test_and_change_bit(int nr, volatile unsigned long *addr) { - unsigned long mask = BITOP_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr); + unsigned long mask = BIT_MASK(nr); + unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); unsigned long old = *p; *p = old ^ mask; @@ -105,7 +110,7 @@ static inline int __test_and_change_bit(int nr, */ static inline int test_bit(int nr, const volatile unsigned long *addr) { - return 1UL & (addr[BITOP_WORD(nr)] >> (nr & (BITS_PER_LONG-1))); + return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1))); } /** @@ -147,4 +152,9 @@ unsigned long find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset); +static inline unsigned long hweight_long(unsigned long w) +{ + return sizeof(w) == 4 ? hweight32(w) : hweight64(w); +} + #endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */ diff --git a/tools/testing/radix-tree/linux/bitops/non-atomic.h b/tools/testing/radix-tree/linux/bitops/non-atomic.h index 46a825cf2ae1..6a1bcb9d2c4a 100644 --- a/tools/testing/radix-tree/linux/bitops/non-atomic.h +++ b/tools/testing/radix-tree/linux/bitops/non-atomic.h @@ -3,7 +3,6 @@ #include <asm/types.h> -#define BITOP_MASK(nr) (1UL << ((nr) % BITS_PER_LONG)) #define BITOP_WORD(nr) ((nr) / BITS_PER_LONG) /** @@ -17,7 +16,7 @@ */ static inline void __set_bit(int nr, volatile unsigned long *addr) { - unsigned long mask = BITOP_MASK(nr); + unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr); *p |= mask; @@ -25,7 +24,7 @@ static inline void __set_bit(int nr, volatile unsigned long *addr) static inline void __clear_bit(int nr, volatile unsigned long *addr) { - unsigned long mask = BITOP_MASK(nr); + unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr); *p &= ~mask; @@ -42,7 +41,7 @@ static inline void __clear_bit(int nr, volatile unsigned long *addr) */ static inline void __change_bit(int nr, volatile unsigned long *addr) { - unsigned long mask = BITOP_MASK(nr); + unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr); *p ^= mask; @@ -59,7 +58,7 @@ static inline void __change_bit(int nr, volatile unsigned long *addr) */ static inline int __test_and_set_bit(int nr, volatile unsigned long *addr) { - unsigned long mask = BITOP_MASK(nr); + unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr); unsigned long old = *p; @@ -78,7 +77,7 @@ static inline int __test_and_set_bit(int nr, volatile unsigned long *addr) */ static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr) { - unsigned long mask = BITOP_MASK(nr); + unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr); unsigned long old = *p; @@ -90,7 +89,7 @@ static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr) static inline int __test_and_change_bit(int nr, volatile unsigned long *addr) { - unsigned long mask = BITOP_MASK(nr); + unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr); unsigned long old = *p; diff --git a/tools/testing/radix-tree/linux/bug.h b/tools/testing/radix-tree/linux/bug.h index ccbe444977df..23b8ed52f8c8 100644 --- a/tools/testing/radix-tree/linux/bug.h +++ b/tools/testing/radix-tree/linux/bug.h @@ -1 +1 @@ -#define WARN_ON_ONCE(x) assert(x) +#include "asm/bug.h" diff --git a/tools/testing/radix-tree/linux/cpu.h b/tools/testing/radix-tree/linux/cpu.h index 7cf412103205..a45530d78107 100644 --- a/tools/testing/radix-tree/linux/cpu.h +++ b/tools/testing/radix-tree/linux/cpu.h @@ -1,21 +1 @@ - -#define hotcpu_notifier(a, b) - -#define CPU_ONLINE 0x0002 /* CPU (unsigned)v is up */ -#define CPU_UP_PREPARE 0x0003 /* CPU (unsigned)v coming up */ -#define CPU_UP_CANCELED 0x0004 /* CPU (unsigned)v NOT coming up */ -#define CPU_DOWN_PREPARE 0x0005 /* CPU (unsigned)v going down */ -#define CPU_DOWN_FAILED 0x0006 /* CPU (unsigned)v NOT going down */ -#define CPU_DEAD 0x0007 /* CPU (unsigned)v dead */ -#define CPU_POST_DEAD 0x0009 /* CPU (unsigned)v dead, cpu_hotplug - * lock is dropped */ -#define CPU_BROKEN 0x000C /* CPU (unsigned)v did not die properly, - * perhaps due to preemption. */ -#define CPU_TASKS_FROZEN 0x0010 - -#define CPU_ONLINE_FROZEN (CPU_ONLINE | CPU_TASKS_FROZEN) -#define CPU_UP_PREPARE_FROZEN (CPU_UP_PREPARE | CPU_TASKS_FROZEN) -#define CPU_UP_CANCELED_FROZEN (CPU_UP_CANCELED | CPU_TASKS_FROZEN) -#define CPU_DOWN_PREPARE_FROZEN (CPU_DOWN_PREPARE | CPU_TASKS_FROZEN) -#define CPU_DOWN_FAILED_FROZEN (CPU_DOWN_FAILED | CPU_TASKS_FROZEN) -#define CPU_DEAD_FROZEN (CPU_DEAD | CPU_TASKS_FROZEN) +#define cpuhp_setup_state_nocalls(a, b, c, d) (0) diff --git a/tools/testing/radix-tree/linux/gfp.h b/tools/testing/radix-tree/linux/gfp.h index 5201b915f631..5b09b2ce6c33 100644 --- a/tools/testing/radix-tree/linux/gfp.h +++ b/tools/testing/radix-tree/linux/gfp.h @@ -3,8 +3,24 @@ #define __GFP_BITS_SHIFT 26 #define __GFP_BITS_MASK ((gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) -#define __GFP_WAIT 1 -#define __GFP_ACCOUNT 0 -#define __GFP_NOWARN 0 + +#define __GFP_HIGH 0x20u +#define __GFP_IO 0x40u +#define __GFP_FS 0x80u +#define __GFP_NOWARN 0x200u +#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_ATOMIC (__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM) +#define GFP_KERNEL (__GFP_RECLAIM | __GFP_IO | __GFP_FS) + +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/kernel.h b/tools/testing/radix-tree/linux/kernel.h index be98a47b4e1b..9b43b4975d83 100644 --- a/tools/testing/radix-tree/linux/kernel.h +++ b/tools/testing/radix-tree/linux/kernel.h @@ -8,9 +8,14 @@ #include <limits.h> #include "../../include/linux/compiler.h" +#include "../../include/linux/err.h" #include "../../../include/linux/kconfig.h" +#ifdef BENCHMARK +#define RADIX_TREE_MAP_SHIFT 6 +#else #define RADIX_TREE_MAP_SHIFT 3 +#endif #ifndef NULL #define NULL 0 @@ -43,4 +48,17 @@ static inline int in_interrupt(void) { return 0; } + +/* + * This looks more complex than it should be. But we need to + * get the type for the ~ right in round_down (it needs to be + * as wide as the result!), and we want to evaluate the macro + * arguments just once each. + */ +#define __round_mask(x, y) ((__typeof__(x))((y)-1)) +#define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1) +#define round_down(x, y) ((x) & ~__round_mask(x, y)) + +#define xchg(ptr, x) uatomic_xchg(ptr, x) + #endif /* _KERNEL_H */ diff --git a/tools/testing/radix-tree/linux/notifier.h b/tools/testing/radix-tree/linux/notifier.h deleted file mode 100644 index 70e4797d5a46..000000000000 --- a/tools/testing/radix-tree/linux/notifier.h +++ /dev/null @@ -1,8 +0,0 @@ -#ifndef _NOTIFIER_H -#define _NOTIFIER_H - -struct notifier_block; - -#define NOTIFY_OK 0x0001 /* Suits me */ - -#endif diff --git a/tools/testing/radix-tree/linux/preempt.h b/tools/testing/radix-tree/linux/preempt.h index 6210672e3baa..65c04c226965 100644 --- a/tools/testing/radix-tree/linux/preempt.h +++ b/tools/testing/radix-tree/linux/preempt.h @@ -1,4 +1,4 @@ -/* */ +extern int preempt_count; -#define preempt_disable() do { } while (0) -#define preempt_enable() do { } while (0) +#define preempt_disable() uatomic_inc(&preempt_count) +#define preempt_enable() uatomic_dec(&preempt_count) diff --git a/tools/testing/radix-tree/linux/slab.h b/tools/testing/radix-tree/linux/slab.h index 6d5a34770fd4..e40337f41a38 100644 --- a/tools/testing/radix-tree/linux/slab.h +++ b/tools/testing/radix-tree/linux/slab.h @@ -7,15 +7,8 @@ #define SLAB_PANIC 2 #define SLAB_RECLAIM_ACCOUNT 0x00020000UL /* Objects are reclaimable */ -static inline int gfpflags_allow_blocking(gfp_t mask) -{ - return 1; -} - -struct kmem_cache { - int size; - void (*ctor)(void *); -}; +void *kmalloc(size_t size, gfp_t); +void kfree(void *); void *kmem_cache_alloc(struct kmem_cache *cachep, int flags); void kmem_cache_free(struct kmem_cache *cachep, void *objp); diff --git a/tools/testing/radix-tree/linux/types.h b/tools/testing/radix-tree/linux/types.h index faa0b6ff9ca8..8491d89873bb 100644 --- a/tools/testing/radix-tree/linux/types.h +++ b/tools/testing/radix-tree/linux/types.h @@ -6,8 +6,6 @@ #define __rcu #define __read_mostly -#define BITS_PER_LONG (sizeof(long) * 8) - static inline void INIT_LIST_HEAD(struct list_head *list) { list->next = list; diff --git a/tools/testing/radix-tree/main.c b/tools/testing/radix-tree/main.c index daa9010693e8..f7e9801a6754 100644 --- a/tools/testing/radix-tree/main.c +++ b/tools/testing/radix-tree/main.c @@ -67,7 +67,6 @@ void big_gang_check(bool long_run) for (i = 0; i < (long_run ? 1000 : 3); i++) { __big_gang_check(); - srand(time(0)); printf("%d ", i); fflush(stdout); } @@ -206,8 +205,7 @@ void copy_tag_check(void) } // printf("\ncopying tags...\n"); - cur = start; - tagged = radix_tree_range_tag_if_tagged(&tree, &cur, end, ITEMS, 0, 1); + tagged = tag_tagged_items(&tree, NULL, start, end, ITEMS, 0, 1); // printf("checking copied tags\n"); assert(tagged == count); @@ -215,16 +213,13 @@ void copy_tag_check(void) /* Copy tags in several rounds */ // printf("\ncopying tags...\n"); - cur = start; - do { - tmp = rand() % (count/10+2); - tagged = radix_tree_range_tag_if_tagged(&tree, &cur, end, tmp, 0, 2); - } while (tmp == tagged); + tmp = rand() % (count / 10 + 2); + tagged = tag_tagged_items(&tree, NULL, start, end, tmp, 0, 2); + assert(tagged == count); // printf("%lu %lu %lu\n", tagged, tmp, count); // printf("checking copied tags\n"); check_copied_tags(&tree, start, end, idx, ITEMS, 0, 2); - assert(tagged < tmp); verify_tag_consistency(&tree, 0); verify_tag_consistency(&tree, 1); verify_tag_consistency(&tree, 2); @@ -240,7 +235,7 @@ static void __locate_check(struct radix_tree_root *tree, unsigned long index, item_insert_order(tree, index, order); item = item_lookup(tree, index); - index2 = radix_tree_locate_item(tree, item); + index2 = find_item(tree, item); if (index != index2) { printf("index %ld order %d inserted; found %ld\n", index, order, index2); @@ -274,17 +269,17 @@ static void locate_check(void) index += (1UL << order)) { __locate_check(&tree, index + offset, order); } - if (radix_tree_locate_item(&tree, &tree) != -1) + if (find_item(&tree, &tree) != -1) abort(); item_kill_tree(&tree); } } - if (radix_tree_locate_item(&tree, &tree) != -1) + if (find_item(&tree, &tree) != -1) abort(); __locate_check(&tree, -1, 0); - if (radix_tree_locate_item(&tree, &tree) != -1) + if (find_item(&tree, &tree) != -1) abort(); item_kill_tree(&tree); } @@ -293,50 +288,80 @@ static void single_thread_tests(bool long_run) { int i; - printf("starting single_thread_tests: %d allocated\n", nr_allocated); + printf("starting single_thread_tests: %d allocated, preempt %d\n", + nr_allocated, preempt_count); multiorder_checks(); - printf("after multiorder_check: %d allocated\n", nr_allocated); + rcu_barrier(); + printf("after multiorder_check: %d allocated, preempt %d\n", + nr_allocated, preempt_count); locate_check(); - printf("after locate_check: %d allocated\n", nr_allocated); + rcu_barrier(); + printf("after locate_check: %d allocated, preempt %d\n", + nr_allocated, preempt_count); tag_check(); - printf("after tag_check: %d allocated\n", nr_allocated); + rcu_barrier(); + printf("after tag_check: %d allocated, preempt %d\n", + nr_allocated, preempt_count); gang_check(); - printf("after gang_check: %d allocated\n", nr_allocated); + rcu_barrier(); + printf("after gang_check: %d allocated, preempt %d\n", + nr_allocated, preempt_count); add_and_check(); - printf("after add_and_check: %d allocated\n", nr_allocated); + rcu_barrier(); + printf("after add_and_check: %d allocated, preempt %d\n", + nr_allocated, preempt_count); dynamic_height_check(); - printf("after dynamic_height_check: %d allocated\n", nr_allocated); + rcu_barrier(); + printf("after dynamic_height_check: %d allocated, preempt %d\n", + nr_allocated, preempt_count); big_gang_check(long_run); - printf("after big_gang_check: %d allocated\n", nr_allocated); + rcu_barrier(); + printf("after big_gang_check: %d allocated, preempt %d\n", + nr_allocated, preempt_count); for (i = 0; i < (long_run ? 2000 : 3); i++) { copy_tag_check(); printf("%d ", i); fflush(stdout); } - printf("after copy_tag_check: %d allocated\n", nr_allocated); + rcu_barrier(); + printf("after copy_tag_check: %d allocated, preempt %d\n", + nr_allocated, preempt_count); } int main(int argc, char **argv) { bool long_run = false; int opt; + unsigned int seed = time(NULL); - while ((opt = getopt(argc, argv, "l")) != -1) { + while ((opt = getopt(argc, argv, "ls:")) != -1) { if (opt == 'l') long_run = true; + else if (opt == 's') + seed = strtoul(optarg, NULL, 0); } + printf("random seed %u\n", seed); + srand(seed); + rcu_register_thread(); radix_tree_init(); regression1_test(); regression2_test(); regression3_test(); - iteration_test(); + iteration_test(0, 10); + iteration_test(7, 20); single_thread_tests(long_run); - sleep(1); - printf("after sleep(1): %d allocated\n", nr_allocated); + /* Free any remaining preallocated nodes */ + radix_tree_cpu_dead(0); + + benchmark(); + + rcu_barrier(); + printf("after rcu_barrier: %d allocated, preempt %d\n", + nr_allocated, preempt_count); rcu_unregister_thread(); exit(0); diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c index 05d7bc488971..f79812a5e070 100644 --- a/tools/testing/radix-tree/multiorder.c +++ b/tools/testing/radix-tree/multiorder.c @@ -26,7 +26,6 @@ static void __multiorder_tag_test(int index, int order) { RADIX_TREE(tree, GFP_KERNEL); int base, err, i; - unsigned long first = 0; /* our canonical entry */ base = index & ~((1 << order) - 1); @@ -60,7 +59,7 @@ static void __multiorder_tag_test(int index, int order) assert(!radix_tree_tag_get(&tree, i, 1)); } - assert(radix_tree_range_tag_if_tagged(&tree, &first, ~0UL, 10, 0, 1) == 1); + assert(tag_tagged_items(&tree, NULL, 0, ~0UL, 10, 0, 1) == 1); assert(radix_tree_tag_clear(&tree, index, 0)); for_each_index(i, base, order) { @@ -76,8 +75,27 @@ static void __multiorder_tag_test(int index, int order) item_kill_tree(&tree); } +static void __multiorder_tag_test2(unsigned order, unsigned long index2) +{ + RADIX_TREE(tree, GFP_KERNEL); + unsigned long index = (1 << order); + index2 += index; + + assert(item_insert_order(&tree, 0, order) == 0); + assert(item_insert(&tree, index2) == 0); + + assert(radix_tree_tag_set(&tree, 0, 0)); + assert(radix_tree_tag_set(&tree, index2, 0)); + + assert(tag_tagged_items(&tree, NULL, 0, ~0UL, 10, 0, 1) == 2); + + item_kill_tree(&tree); +} + static void multiorder_tag_tests(void) { + int i, j; + /* test multi-order entry for indices 0-7 with no sibling pointers */ __multiorder_tag_test(0, 3); __multiorder_tag_test(5, 3); @@ -117,6 +135,10 @@ static void multiorder_tag_tests(void) __multiorder_tag_test(300, 8); __multiorder_tag_test(0x12345678UL, 8); + + for (i = 1; i < 10; i++) + for (j = 0; j < (10 << i); j++) + __multiorder_tag_test2(i, j); } static void multiorder_check(unsigned long index, int order) @@ -125,7 +147,7 @@ static void multiorder_check(unsigned long index, int order) unsigned long min = index & ~((1UL << order) - 1); unsigned long max = min + (1UL << order); void **slot; - struct item *item2 = item_create(min); + struct item *item2 = item_create(min, order); RADIX_TREE(tree, GFP_KERNEL); printf("Multiorder index %ld, order %d\n", index, order); @@ -146,7 +168,7 @@ static void multiorder_check(unsigned long index, int order) slot = radix_tree_lookup_slot(&tree, index); free(*slot); - radix_tree_replace_slot(slot, item2); + radix_tree_replace_slot(&tree, slot, item2); for (i = min; i < max; i++) { struct item *item = item_lookup(&tree, i); assert(item != 0); @@ -231,11 +253,14 @@ void multiorder_iteration(void) radix_tree_for_each_slot(slot, &tree, &iter, j) { int height = order[i] / RADIX_TREE_MAP_SHIFT; int shift = height * RADIX_TREE_MAP_SHIFT; - int mask = (1 << order[i]) - 1; + unsigned long mask = (1UL << order[i]) - 1; + struct item *item = *slot; - assert(iter.index >= (index[i] &~ mask)); - assert(iter.index <= (index[i] | mask)); + assert((iter.index | mask) == (index[i] | mask)); assert(iter.shift == shift); + assert(!radix_tree_is_internal_node(item)); + assert((item->index | mask) == (index[i] | mask)); + assert(item->order == order[i]); i++; } } @@ -248,7 +273,6 @@ void multiorder_tagged_iteration(void) RADIX_TREE(tree, GFP_KERNEL); struct radix_tree_iter iter; void **slot; - unsigned long first = 0; int i, j; printf("Multiorder tagged iteration test\n"); @@ -269,7 +293,7 @@ void multiorder_tagged_iteration(void) assert(radix_tree_tag_set(&tree, tag_index[i], 1)); for (j = 0; j < 256; j++) { - int mask, k; + int k; for (i = 0; i < TAG_ENTRIES; i++) { for (k = i; index[k] < tag_index[i]; k++) @@ -279,18 +303,22 @@ void multiorder_tagged_iteration(void) } radix_tree_for_each_tagged(slot, &tree, &iter, j, 1) { + unsigned long mask; + struct item *item = *slot; for (k = i; index[k] < tag_index[i]; k++) ; - mask = (1 << order[k]) - 1; + mask = (1UL << order[k]) - 1; - assert(iter.index >= (tag_index[i] &~ mask)); - assert(iter.index <= (tag_index[i] | mask)); + assert((iter.index | mask) == (tag_index[i] | mask)); + assert(!radix_tree_is_internal_node(item)); + assert((item->index | mask) == (tag_index[i] | mask)); + assert(item->order == order[k]); i++; } } - radix_tree_range_tag_if_tagged(&tree, &first, ~0UL, - MT_NUM_ENTRIES, 1, 2); + assert(tag_tagged_items(&tree, NULL, 0, ~0UL, TAG_ENTRIES, 1, 2) == + TAG_ENTRIES); for (j = 0; j < 256; j++) { int mask, k; @@ -303,19 +331,21 @@ void multiorder_tagged_iteration(void) } radix_tree_for_each_tagged(slot, &tree, &iter, j, 2) { + struct item *item = *slot; for (k = i; index[k] < tag_index[i]; k++) ; mask = (1 << order[k]) - 1; - assert(iter.index >= (tag_index[i] &~ mask)); - assert(iter.index <= (tag_index[i] | mask)); + assert((iter.index | mask) == (tag_index[i] | mask)); + assert(!radix_tree_is_internal_node(item)); + assert((item->index | mask) == (tag_index[i] | mask)); + assert(item->order == order[k]); i++; } } - first = 1; - radix_tree_range_tag_if_tagged(&tree, &first, ~0UL, - MT_NUM_ENTRIES, 1, 0); + assert(tag_tagged_items(&tree, NULL, 1, ~0UL, MT_NUM_ENTRIES * 2, 1, 0) + == TAG_ENTRIES); i = 0; radix_tree_for_each_tagged(slot, &tree, &iter, 0, 0) { assert(iter.index == tag_index[i]); @@ -325,6 +355,261 @@ void multiorder_tagged_iteration(void) item_kill_tree(&tree); } +static void multiorder_join1(unsigned long index, + unsigned order1, unsigned order2) +{ + unsigned long loc; + void *item, *item2 = item_create(index + 1, order1); + RADIX_TREE(tree, GFP_KERNEL); + + item_insert_order(&tree, index, order2); + item = radix_tree_lookup(&tree, index); + radix_tree_join(&tree, index + 1, order1, item2); + loc = find_item(&tree, item); + if (loc == -1) + free(item); + item = radix_tree_lookup(&tree, index + 1); + assert(item == item2); + item_kill_tree(&tree); +} + +static void multiorder_join2(unsigned order1, unsigned order2) +{ + RADIX_TREE(tree, GFP_KERNEL); + struct radix_tree_node *node; + void *item1 = item_create(0, order1); + void *item2; + + item_insert_order(&tree, 0, order2); + radix_tree_insert(&tree, 1 << order2, (void *)0x12UL); + item2 = __radix_tree_lookup(&tree, 1 << order2, &node, NULL); + assert(item2 == (void *)0x12UL); + assert(node->exceptional == 1); + + radix_tree_join(&tree, 0, order1, item1); + item2 = __radix_tree_lookup(&tree, 1 << order2, &node, NULL); + assert(item2 == item1); + assert(node->exceptional == 0); + item_kill_tree(&tree); +} + +/* + * This test revealed an accounting bug for exceptional entries at one point. + * Nodes were being freed back into the pool with an elevated exception count + * by radix_tree_join() and then radix_tree_split() was failing to zero the + * count of exceptional entries. + */ +static void multiorder_join3(unsigned int order) +{ + RADIX_TREE(tree, GFP_KERNEL); + struct radix_tree_node *node; + void **slot; + struct radix_tree_iter iter; + unsigned long i; + + for (i = 0; i < (1 << order); i++) { + radix_tree_insert(&tree, i, (void *)0x12UL); + } + + radix_tree_join(&tree, 0, order, (void *)0x16UL); + rcu_barrier(); + + radix_tree_split(&tree, 0, 0); + + radix_tree_for_each_slot(slot, &tree, &iter, 0) { + radix_tree_iter_replace(&tree, &iter, slot, (void *)0x12UL); + } + + __radix_tree_lookup(&tree, 0, &node, NULL); + assert(node->exceptional == node->count); + + item_kill_tree(&tree); +} + +static void multiorder_join(void) +{ + int i, j, idx; + + for (idx = 0; idx < 1024; idx = idx * 2 + 3) { + for (i = 1; i < 15; i++) { + for (j = 0; j < i; j++) { + multiorder_join1(idx, i, j); + } + } + } + + for (i = 1; i < 15; i++) { + for (j = 0; j < i; j++) { + multiorder_join2(i, j); + } + } + + for (i = 3; i < 10; i++) { + multiorder_join3(i); + } +} + +static void check_mem(unsigned old_order, unsigned new_order, unsigned alloc) +{ + struct radix_tree_preload *rtp = &radix_tree_preloads; + if (rtp->nr != 0) + printf("split(%u %u) remaining %u\n", old_order, new_order, + rtp->nr); + /* + * Can't check for equality here as some nodes may have been + * RCU-freed while we ran. But we should never finish with more + * nodes allocated since they should have all been preloaded. + */ + if (nr_allocated > alloc) + printf("split(%u %u) allocated %u %u\n", old_order, new_order, + alloc, nr_allocated); +} + +static void __multiorder_split(int old_order, int new_order) +{ + RADIX_TREE(tree, GFP_ATOMIC); + void **slot; + struct radix_tree_iter iter; + unsigned alloc; + + radix_tree_preload(GFP_KERNEL); + assert(item_insert_order(&tree, 0, old_order) == 0); + radix_tree_preload_end(); + + /* Wipe out the preloaded cache or it'll confuse check_mem() */ + radix_tree_cpu_dead(0); + + radix_tree_tag_set(&tree, 0, 2); + + radix_tree_split_preload(old_order, new_order, GFP_KERNEL); + alloc = nr_allocated; + radix_tree_split(&tree, 0, new_order); + check_mem(old_order, new_order, alloc); + radix_tree_for_each_slot(slot, &tree, &iter, 0) { + radix_tree_iter_replace(&tree, &iter, slot, + item_create(iter.index, new_order)); + } + radix_tree_preload_end(); + + item_kill_tree(&tree); +} + +static void __multiorder_split2(int old_order, int new_order) +{ + RADIX_TREE(tree, GFP_KERNEL); + void **slot; + struct radix_tree_iter iter; + struct radix_tree_node *node; + void *item; + + __radix_tree_insert(&tree, 0, old_order, (void *)0x12); + + item = __radix_tree_lookup(&tree, 0, &node, NULL); + assert(item == (void *)0x12); + assert(node->exceptional > 0); + + radix_tree_split(&tree, 0, new_order); + radix_tree_for_each_slot(slot, &tree, &iter, 0) { + radix_tree_iter_replace(&tree, &iter, slot, + item_create(iter.index, new_order)); + } + + item = __radix_tree_lookup(&tree, 0, &node, NULL); + assert(item != (void *)0x12); + assert(node->exceptional == 0); + + item_kill_tree(&tree); +} + +static void __multiorder_split3(int old_order, int new_order) +{ + RADIX_TREE(tree, GFP_KERNEL); + void **slot; + struct radix_tree_iter iter; + struct radix_tree_node *node; + void *item; + + __radix_tree_insert(&tree, 0, old_order, (void *)0x12); + + item = __radix_tree_lookup(&tree, 0, &node, NULL); + assert(item == (void *)0x12); + assert(node->exceptional > 0); + + radix_tree_split(&tree, 0, new_order); + radix_tree_for_each_slot(slot, &tree, &iter, 0) { + radix_tree_iter_replace(&tree, &iter, slot, (void *)0x16); + } + + item = __radix_tree_lookup(&tree, 0, &node, NULL); + assert(item == (void *)0x16); + assert(node->exceptional > 0); + + item_kill_tree(&tree); + + __radix_tree_insert(&tree, 0, old_order, (void *)0x12); + + item = __radix_tree_lookup(&tree, 0, &node, NULL); + assert(item == (void *)0x12); + assert(node->exceptional > 0); + + radix_tree_split(&tree, 0, new_order); + radix_tree_for_each_slot(slot, &tree, &iter, 0) { + if (iter.index == (1 << new_order)) + radix_tree_iter_replace(&tree, &iter, slot, + (void *)0x16); + else + radix_tree_iter_replace(&tree, &iter, slot, NULL); + } + + item = __radix_tree_lookup(&tree, 1 << new_order, &node, NULL); + assert(item == (void *)0x16); + assert(node->count == node->exceptional); + do { + node = node->parent; + if (!node) + break; + assert(node->count == 1); + assert(node->exceptional == 0); + } while (1); + + item_kill_tree(&tree); +} + +static void multiorder_split(void) +{ + int i, j; + + for (i = 3; i < 11; i++) + for (j = 0; j < i; j++) { + __multiorder_split(i, j); + __multiorder_split2(i, j); + __multiorder_split3(i, j); + } +} + +static void multiorder_account(void) +{ + RADIX_TREE(tree, GFP_KERNEL); + struct radix_tree_node *node; + void **slot; + + item_insert_order(&tree, 0, 5); + + __radix_tree_insert(&tree, 1 << 5, 5, (void *)0x12); + __radix_tree_lookup(&tree, 0, &node, NULL); + assert(node->count == node->exceptional * 2); + radix_tree_delete(&tree, 1 << 5); + assert(node->exceptional == 0); + + __radix_tree_insert(&tree, 1 << 5, 5, (void *)0x12); + __radix_tree_lookup(&tree, 1 << 5, &node, &slot); + assert(node->count == node->exceptional * 2); + __radix_tree_replace(&tree, node, slot, NULL, NULL, NULL); + assert(node->exceptional == 0); + + item_kill_tree(&tree); +} + void multiorder_checks(void) { int i; @@ -342,4 +627,9 @@ void multiorder_checks(void) multiorder_tag_tests(); multiorder_iteration(); multiorder_tagged_iteration(); + multiorder_join(); + multiorder_split(); + multiorder_account(); + + radix_tree_cpu_dead(0); } diff --git a/tools/testing/radix-tree/rcupdate.c b/tools/testing/radix-tree/rcupdate.c deleted file mode 100644 index 31a2d14225d6..000000000000 --- a/tools/testing/radix-tree/rcupdate.c +++ /dev/null @@ -1,86 +0,0 @@ -#include <linux/rcupdate.h> -#include <pthread.h> -#include <stdio.h> -#include <assert.h> - -static pthread_mutex_t rculock = PTHREAD_MUTEX_INITIALIZER; -static struct rcu_head *rcuhead_global = NULL; -static __thread int nr_rcuhead = 0; -static __thread struct rcu_head *rcuhead = NULL; -static __thread struct rcu_head *rcutail = NULL; - -static pthread_cond_t rcu_worker_cond = PTHREAD_COND_INITIALIZER; - -/* switch to urcu implementation when it is merged. */ -void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *head)) -{ - head->func = func; - head->next = rcuhead; - rcuhead = head; - if (!rcutail) - rcutail = head; - nr_rcuhead++; - if (nr_rcuhead >= 1000) { - int signal = 0; - - pthread_mutex_lock(&rculock); - if (!rcuhead_global) - signal = 1; - rcutail->next = rcuhead_global; - rcuhead_global = head; - pthread_mutex_unlock(&rculock); - - nr_rcuhead = 0; - rcuhead = NULL; - rcutail = NULL; - - if (signal) { - pthread_cond_signal(&rcu_worker_cond); - } - } -} - -static void *rcu_worker(void *arg) -{ - struct rcu_head *r; - - rcupdate_thread_init(); - - while (1) { - pthread_mutex_lock(&rculock); - while (!rcuhead_global) { - pthread_cond_wait(&rcu_worker_cond, &rculock); - } - r = rcuhead_global; - rcuhead_global = NULL; - - pthread_mutex_unlock(&rculock); - - synchronize_rcu(); - - while (r) { - struct rcu_head *tmp = r->next; - r->func(r); - r = tmp; - } - } - - rcupdate_thread_exit(); - - return NULL; -} - -static pthread_t worker_thread; -void rcupdate_init(void) -{ - pthread_create(&worker_thread, NULL, rcu_worker, NULL); -} - -void rcupdate_thread_init(void) -{ - rcu_register_thread(); -} -void rcupdate_thread_exit(void) -{ - rcu_unregister_thread(); -} diff --git a/tools/testing/radix-tree/regression2.c b/tools/testing/radix-tree/regression2.c index 63bf347aaf33..a41325d7a170 100644 --- a/tools/testing/radix-tree/regression2.c +++ b/tools/testing/radix-tree/regression2.c @@ -50,6 +50,7 @@ #include <stdio.h> #include "regression.h" +#include "test.h" #define PAGECACHE_TAG_DIRTY 0 #define PAGECACHE_TAG_WRITEBACK 1 @@ -90,7 +91,7 @@ void regression2_test(void) /* 1. */ start = 0; end = max_slots - 2; - radix_tree_range_tag_if_tagged(&mt_tree, &start, end, 1, + tag_tagged_items(&mt_tree, NULL, start, end, 1, PAGECACHE_TAG_DIRTY, PAGECACHE_TAG_TOWRITE); /* 2. */ diff --git a/tools/testing/radix-tree/regression3.c b/tools/testing/radix-tree/regression3.c index 1f06ed73d0a8..b594841fae85 100644 --- a/tools/testing/radix-tree/regression3.c +++ b/tools/testing/radix-tree/regression3.c @@ -5,7 +5,7 @@ * In following radix_tree_next_slot current chunk size becomes zero. * This isn't checked and it tries to dereference null pointer in slot. * - * Helper radix_tree_iter_next reset slot to NULL and next_index to index + 1, + * Helper radix_tree_iter_resume reset slot to NULL and next_index to index + 1, * for tagger iteraction it also must reset cached tags in iterator to abort * next radix_tree_next_slot and go to slow-path into radix_tree_next_chunk. * @@ -88,7 +88,7 @@ void regression3_test(void) printf("slot %ld %p\n", iter.index, *slot); if (!iter.index) { printf("next at %ld\n", iter.index); - slot = radix_tree_iter_next(&iter); + slot = radix_tree_iter_resume(slot, &iter); } } @@ -96,7 +96,7 @@ void regression3_test(void) printf("contig %ld %p\n", iter.index, *slot); if (!iter.index) { printf("next at %ld\n", iter.index); - slot = radix_tree_iter_next(&iter); + slot = radix_tree_iter_resume(slot, &iter); } } @@ -106,7 +106,7 @@ void regression3_test(void) printf("tagged %ld %p\n", iter.index, *slot); if (!iter.index) { printf("next at %ld\n", iter.index); - slot = radix_tree_iter_next(&iter); + slot = radix_tree_iter_resume(slot, &iter); } } diff --git a/tools/testing/radix-tree/tag_check.c b/tools/testing/radix-tree/tag_check.c index b0ac05741750..fd98c132207a 100644 --- a/tools/testing/radix-tree/tag_check.c +++ b/tools/testing/radix-tree/tag_check.c @@ -23,7 +23,7 @@ __simple_checks(struct radix_tree_root *tree, unsigned long index, int tag) item_tag_set(tree, index, tag); ret = item_tag_get(tree, index, tag); assert(ret != 0); - ret = radix_tree_range_tag_if_tagged(tree, &first, ~0UL, 10, tag, !tag); + ret = tag_tagged_items(tree, NULL, first, ~0UL, 10, tag, !tag); assert(ret == 1); ret = item_tag_get(tree, index, !tag); assert(ret != 0); @@ -51,6 +51,7 @@ void simple_checks(void) verify_tag_consistency(&tree, 1); printf("before item_kill_tree: %d allocated\n", nr_allocated); item_kill_tree(&tree); + rcu_barrier(); printf("after item_kill_tree: %d allocated\n", nr_allocated); } @@ -319,10 +320,13 @@ static void single_check(void) assert(ret == 0); verify_tag_consistency(&tree, 0); verify_tag_consistency(&tree, 1); - ret = radix_tree_range_tag_if_tagged(&tree, &first, 10, 10, 0, 1); + ret = tag_tagged_items(&tree, NULL, first, 10, 10, 0, 1); assert(ret == 1); ret = radix_tree_gang_lookup_tag(&tree, (void **)items, 0, BATCH, 1); assert(ret == 1); + item_tag_clear(&tree, 0, 0); + ret = radix_tree_gang_lookup_tag(&tree, (void **)items, 0, BATCH, 0); + assert(ret == 0); item_kill_tree(&tree); } @@ -331,12 +335,16 @@ void tag_check(void) single_check(); extend_checks(); contract_checks(); + rcu_barrier(); printf("after extend_checks: %d allocated\n", nr_allocated); __leak_check(); leak_check(); + rcu_barrier(); printf("after leak_check: %d allocated\n", nr_allocated); simple_checks(); + rcu_barrier(); printf("after simple_checks: %d allocated\n", nr_allocated); thrash_tags(); + rcu_barrier(); printf("after thrash_tags: %d allocated\n", nr_allocated); } diff --git a/tools/testing/radix-tree/test.c b/tools/testing/radix-tree/test.c index a6e8099eaf4f..e5726e373646 100644 --- a/tools/testing/radix-tree/test.c +++ b/tools/testing/radix-tree/test.c @@ -24,21 +24,29 @@ int item_tag_get(struct radix_tree_root *root, unsigned long index, int tag) return radix_tree_tag_get(root, index, tag); } -int __item_insert(struct radix_tree_root *root, struct item *item, - unsigned order) +int __item_insert(struct radix_tree_root *root, struct item *item) { - return __radix_tree_insert(root, item->index, order, item); + return __radix_tree_insert(root, item->index, item->order, item); } int item_insert(struct radix_tree_root *root, unsigned long index) { - return __item_insert(root, item_create(index), 0); + return __item_insert(root, item_create(index, 0)); } int item_insert_order(struct radix_tree_root *root, unsigned long index, unsigned order) { - return __item_insert(root, item_create(index), order); + return __item_insert(root, item_create(index, order)); +} + +void item_sanity(struct item *item, unsigned long index) +{ + unsigned long mask; + assert(!radix_tree_is_internal_node(item)); + assert(item->order < BITS_PER_LONG); + mask = (1UL << item->order) - 1; + assert((item->index | mask) == (index | mask)); } int item_delete(struct radix_tree_root *root, unsigned long index) @@ -46,18 +54,19 @@ int item_delete(struct radix_tree_root *root, unsigned long index) struct item *item = radix_tree_delete(root, index); if (item) { - assert(item->index == index); + item_sanity(item, index); free(item); return 1; } return 0; } -struct item *item_create(unsigned long index) +struct item *item_create(unsigned long index, unsigned int order) { struct item *ret = malloc(sizeof(*ret)); ret->index = index; + ret->order = order; return ret; } @@ -66,8 +75,8 @@ void item_check_present(struct radix_tree_root *root, unsigned long index) struct item *item; item = radix_tree_lookup(root, index); - assert(item != 0); - assert(item->index == index); + assert(item != NULL); + item_sanity(item, index); } struct item *item_lookup(struct radix_tree_root *root, unsigned long index) @@ -80,7 +89,7 @@ void item_check_absent(struct radix_tree_root *root, unsigned long index) struct item *item; item = radix_tree_lookup(root, index); - assert(item == 0); + assert(item == NULL); } /* @@ -142,6 +151,62 @@ void item_full_scan(struct radix_tree_root *root, unsigned long start, assert(nfound == 0); } +/* Use the same pattern as tag_pages_for_writeback() in mm/page-writeback.c */ +int tag_tagged_items(struct radix_tree_root *root, pthread_mutex_t *lock, + unsigned long start, unsigned long end, unsigned batch, + unsigned iftag, unsigned thentag) +{ + unsigned long tagged = 0; + struct radix_tree_iter iter; + void **slot; + + if (batch == 0) + batch = 1; + + if (lock) + pthread_mutex_lock(lock); + radix_tree_for_each_tagged(slot, root, &iter, start, iftag) { + if (iter.index > end) + break; + radix_tree_iter_tag_set(root, &iter, thentag); + tagged++; + if ((tagged % batch) != 0) + continue; + slot = radix_tree_iter_resume(slot, &iter); + if (lock) { + pthread_mutex_unlock(lock); + rcu_barrier(); + pthread_mutex_lock(lock); + } + } + if (lock) + pthread_mutex_unlock(lock); + + return tagged; +} + +/* Use the same pattern as find_swap_entry() in mm/shmem.c */ +unsigned long find_item(struct radix_tree_root *root, void *item) +{ + struct radix_tree_iter iter; + void **slot; + unsigned long found = -1; + unsigned long checked = 0; + + radix_tree_for_each_slot(slot, root, &iter, 0) { + if (*slot == item) { + found = iter.index; + break; + } + checked++; + if ((checked % 4) != 0) + continue; + slot = radix_tree_iter_resume(slot, &iter); + } + + return found; +} + static int verify_node(struct radix_tree_node *slot, unsigned int tag, int tagged) { @@ -200,9 +265,16 @@ void verify_tag_consistency(struct radix_tree_root *root, unsigned int tag) void item_kill_tree(struct radix_tree_root *root) { + struct radix_tree_iter iter; + void **slot; struct item *items[32]; int nfound; + radix_tree_for_each_slot(slot, root, &iter, 0) { + if (radix_tree_exceptional_entry(*slot)) + radix_tree_delete(root, iter.index); + } + while ((nfound = radix_tree_gang_lookup(root, (void **)items, 0, 32))) { int i; diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h index 217fb2403f09..056a23b56467 100644 --- a/tools/testing/radix-tree/test.h +++ b/tools/testing/radix-tree/test.h @@ -5,11 +5,11 @@ struct item { unsigned long index; + unsigned int order; }; -struct item *item_create(unsigned long index); -int __item_insert(struct radix_tree_root *root, struct item *item, - unsigned order); +struct item *item_create(unsigned long index, unsigned int order); +int __item_insert(struct radix_tree_root *root, struct item *item); int item_insert(struct radix_tree_root *root, unsigned long index); int item_insert_order(struct radix_tree_root *root, unsigned long index, unsigned order); @@ -25,9 +25,15 @@ void item_full_scan(struct radix_tree_root *root, unsigned long start, unsigned long nr, int chunk); void item_kill_tree(struct radix_tree_root *root); +int tag_tagged_items(struct radix_tree_root *, pthread_mutex_t *, + unsigned long start, unsigned long end, unsigned batch, + unsigned iftag, unsigned thentag); +unsigned long find_item(struct radix_tree_root *, void *item); + void tag_check(void); void multiorder_checks(void); -void iteration_test(void); +void iteration_test(unsigned order, unsigned duration); +void benchmark(void); struct item * item_tag_set(struct radix_tree_root *root, unsigned long index, int tag); @@ -40,7 +46,14 @@ void verify_tag_consistency(struct radix_tree_root *root, unsigned int tag); extern int nr_allocated; /* Normally private parts of lib/radix-tree.c */ +struct radix_tree_node *entry_to_node(void *ptr); void radix_tree_dump(struct radix_tree_root *root); int root_tag_get(struct radix_tree_root *root, unsigned int tag); unsigned long node_maxindex(struct radix_tree_node *); unsigned long shift_maxindex(unsigned int shift); +int radix_tree_cpu_dead(unsigned int cpu); +struct radix_tree_preload { + unsigned nr; + struct radix_tree_node *nodes; +}; +extern struct radix_tree_preload radix_tree_preloads; diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 3044d435d18d..71b05891a6a1 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -1,4 +1,5 @@ -TARGETS = breakpoints +TARGETS = bpf +TARGETS += breakpoints TARGETS += capabilities TARGETS += cpu-hotplug TARGETS += efivarfs diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore new file mode 100644 index 000000000000..071431bedde8 --- /dev/null +++ b/tools/testing/selftests/bpf/.gitignore @@ -0,0 +1,3 @@ +test_verifier +test_maps +test_lru_map diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile new file mode 100644 index 000000000000..7a5f24543a5f --- /dev/null +++ b/tools/testing/selftests/bpf/Makefile @@ -0,0 +1,13 @@ +CFLAGS += -Wall -O2 -I../../../../usr/include + +test_objs = test_verifier test_maps test_lru_map + +TEST_PROGS := test_verifier test_maps test_lru_map test_kmod.sh +TEST_FILES := $(test_objs) + +all: $(test_objs) + +include ../lib.mk + +clean: + $(RM) $(test_objs) diff --git a/tools/testing/selftests/bpf/bpf_sys.h b/tools/testing/selftests/bpf/bpf_sys.h new file mode 100644 index 000000000000..6b4565f2a3f2 --- /dev/null +++ b/tools/testing/selftests/bpf/bpf_sys.h @@ -0,0 +1,108 @@ +#ifndef __BPF_SYS__ +#define __BPF_SYS__ + +#include <stdint.h> +#include <stdlib.h> + +#include <sys/syscall.h> + +#include <linux/bpf.h> + +static inline __u64 bpf_ptr_to_u64(const void *ptr) +{ + return (__u64)(unsigned long) ptr; +} + +static inline int bpf(int cmd, union bpf_attr *attr, unsigned int size) +{ +#ifdef __NR_bpf + return syscall(__NR_bpf, cmd, attr, size); +#else + fprintf(stderr, "No bpf syscall, kernel headers too old?\n"); + errno = ENOSYS; + return -1; +#endif +} + +static inline int bpf_map_lookup(int fd, const void *key, void *value) +{ + union bpf_attr attr = {}; + + attr.map_fd = fd; + attr.key = bpf_ptr_to_u64(key); + attr.value = bpf_ptr_to_u64(value); + + return bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr)); +} + +static inline int bpf_map_update(int fd, const void *key, const void *value, + uint64_t flags) +{ + union bpf_attr attr = {}; + + attr.map_fd = fd; + attr.key = bpf_ptr_to_u64(key); + attr.value = bpf_ptr_to_u64(value); + attr.flags = flags; + + return bpf(BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr)); +} + +static inline int bpf_map_delete(int fd, const void *key) +{ + union bpf_attr attr = {}; + + attr.map_fd = fd; + attr.key = bpf_ptr_to_u64(key); + + return bpf(BPF_MAP_DELETE_ELEM, &attr, sizeof(attr)); +} + +static inline int bpf_map_next_key(int fd, const void *key, void *next_key) +{ + union bpf_attr attr = {}; + + attr.map_fd = fd; + attr.key = bpf_ptr_to_u64(key); + attr.next_key = bpf_ptr_to_u64(next_key); + + return bpf(BPF_MAP_GET_NEXT_KEY, &attr, sizeof(attr)); +} + +static inline int bpf_map_create(enum bpf_map_type type, uint32_t size_key, + uint32_t size_value, uint32_t max_elem, + uint32_t flags) +{ + union bpf_attr attr = {}; + + attr.map_type = type; + attr.key_size = size_key; + attr.value_size = size_value; + attr.max_entries = max_elem; + attr.map_flags = flags; + + return bpf(BPF_MAP_CREATE, &attr, sizeof(attr)); +} + +static inline int bpf_prog_load(enum bpf_prog_type type, + const struct bpf_insn *insns, size_t size_insns, + const char *license, char *log, size_t size_log) +{ + union bpf_attr attr = {}; + + attr.prog_type = type; + attr.insns = bpf_ptr_to_u64(insns); + attr.insn_cnt = size_insns / sizeof(struct bpf_insn); + attr.license = bpf_ptr_to_u64(license); + + if (size_log > 0) { + attr.log_buf = bpf_ptr_to_u64(log); + attr.log_size = size_log; + attr.log_level = 1; + log[0] = 0; + } + + return bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); +} + +#endif /* __BPF_SYS__ */ diff --git a/tools/testing/selftests/bpf/bpf_util.h b/tools/testing/selftests/bpf/bpf_util.h new file mode 100644 index 000000000000..84a5d1823f02 --- /dev/null +++ b/tools/testing/selftests/bpf/bpf_util.h @@ -0,0 +1,38 @@ +#ifndef __BPF_UTIL__ +#define __BPF_UTIL__ + +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <errno.h> + +static inline unsigned int bpf_num_possible_cpus(void) +{ + static const char *fcpu = "/sys/devices/system/cpu/possible"; + unsigned int start, end, possible_cpus = 0; + char buff[128]; + FILE *fp; + + fp = fopen(fcpu, "r"); + if (!fp) { + printf("Failed to open %s: '%s'!\n", fcpu, strerror(errno)); + exit(1); + } + + while (fgets(buff, sizeof(buff), fp)) { + if (sscanf(buff, "%u-%u", &start, &end) == 2) { + possible_cpus = start == 0 ? end + 1 : 0; + break; + } + } + + fclose(fp); + if (!possible_cpus) { + printf("Failed to retrieve # possible CPUs!\n"); + exit(1); + } + + return possible_cpus; +} + +#endif /* __BPF_UTIL__ */ diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config new file mode 100644 index 000000000000..52d53ed08769 --- /dev/null +++ b/tools/testing/selftests/bpf/config @@ -0,0 +1,5 @@ +CONFIG_BPF=y +CONFIG_BPF_SYSCALL=y +CONFIG_NET_CLS_BPF=m +CONFIG_BPF_EVENTS=y +CONFIG_TEST_BPF=m diff --git a/tools/testing/selftests/bpf/test_kmod.sh b/tools/testing/selftests/bpf/test_kmod.sh new file mode 100755 index 000000000000..92e627adf354 --- /dev/null +++ b/tools/testing/selftests/bpf/test_kmod.sh @@ -0,0 +1,39 @@ +#!/bin/bash + +SRC_TREE=../../../../ + +test_run() +{ + sysctl -w net.core.bpf_jit_enable=$1 2>&1 > /dev/null + sysctl -w net.core.bpf_jit_harden=$2 2>&1 > /dev/null + + echo "[ JIT enabled:$1 hardened:$2 ]" + dmesg -C + insmod $SRC_TREE/lib/test_bpf.ko 2> /dev/null + if [ $? -ne 0 ]; then + rc=1 + fi + rmmod test_bpf 2> /dev/null + dmesg | grep FAIL +} + +test_save() +{ + JE=`sysctl -n net.core.bpf_jit_enable` + JH=`sysctl -n net.core.bpf_jit_harden` +} + +test_restore() +{ + sysctl -w net.core.bpf_jit_enable=$JE 2>&1 > /dev/null + sysctl -w net.core.bpf_jit_harden=$JH 2>&1 > /dev/null +} + +rc=0 +test_save +test_run 0 0 +test_run 1 0 +test_run 1 1 +test_run 1 2 +test_restore +exit $rc diff --git a/tools/testing/selftests/bpf/test_lru_map.c b/tools/testing/selftests/bpf/test_lru_map.c new file mode 100644 index 000000000000..b13fed534d76 --- /dev/null +++ b/tools/testing/selftests/bpf/test_lru_map.c @@ -0,0 +1,587 @@ +/* + * Copyright (c) 2016 Facebook + * + * 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. + */ +#define _GNU_SOURCE +#include <stdio.h> +#include <unistd.h> +#include <errno.h> +#include <string.h> +#include <assert.h> +#include <sched.h> +#include <stdlib.h> +#include <time.h> + +#include <sys/wait.h> +#include <sys/resource.h> + +#include "bpf_sys.h" +#include "bpf_util.h" + +#define LOCAL_FREE_TARGET (128) +#define PERCPU_FREE_TARGET (16) + +static int nr_cpus; + +static int create_map(int map_type, int map_flags, unsigned int size) +{ + int map_fd; + + map_fd = bpf_map_create(map_type, sizeof(unsigned long long), + sizeof(unsigned long long), size, map_flags); + + if (map_fd == -1) + perror("bpf_map_create"); + + return map_fd; +} + +static int map_subset(int map0, int map1) +{ + unsigned long long next_key = 0; + unsigned long long value0[nr_cpus], value1[nr_cpus]; + int ret; + + while (!bpf_map_next_key(map1, &next_key, &next_key)) { + assert(!bpf_map_lookup(map1, &next_key, value1)); + ret = bpf_map_lookup(map0, &next_key, value0); + if (ret) { + printf("key:%llu not found from map. %s(%d)\n", + next_key, strerror(errno), errno); + return 0; + } + if (value0[0] != value1[0]) { + printf("key:%llu value0:%llu != value1:%llu\n", + next_key, value0[0], value1[0]); + return 0; + } + } + return 1; +} + +static int map_equal(int lru_map, int expected) +{ + return map_subset(lru_map, expected) && map_subset(expected, lru_map); +} + +static int sched_next_online(int pid, int next_to_try) +{ + cpu_set_t cpuset; + + if (next_to_try == nr_cpus) + return -1; + + while (next_to_try < nr_cpus) { + CPU_ZERO(&cpuset); + CPU_SET(next_to_try++, &cpuset); + if (!sched_setaffinity(pid, sizeof(cpuset), &cpuset)) + break; + } + + return next_to_try; +} + +/* Size of the LRU amp is 2 + * Add key=1 (+1 key) + * Add key=2 (+1 key) + * Lookup Key=1 + * Add Key=3 + * => Key=2 will be removed by LRU + * Iterate map. Only found key=1 and key=3 + */ +static void test_lru_sanity0(int map_type, int map_flags) +{ + unsigned long long key, value[nr_cpus]; + int lru_map_fd, expected_map_fd; + + printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type, + map_flags); + + assert(sched_next_online(0, 0) != -1); + + if (map_flags & BPF_F_NO_COMMON_LRU) + lru_map_fd = create_map(map_type, map_flags, 2 * nr_cpus); + else + lru_map_fd = create_map(map_type, map_flags, 2); + assert(lru_map_fd != -1); + + expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0, 2); + assert(expected_map_fd != -1); + + value[0] = 1234; + + /* insert key=1 element */ + + key = 1; + assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST)); + assert(!bpf_map_update(expected_map_fd, &key, value, BPF_NOEXIST)); + + /* BPF_NOEXIST means: add new element if it doesn't exist */ + assert(bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST) == -1 && + /* key=1 already exists */ + errno == EEXIST); + + assert(bpf_map_update(lru_map_fd, &key, value, -1) == -1 && + errno == EINVAL); + + /* insert key=2 element */ + + /* check that key=2 is not found */ + key = 2; + assert(bpf_map_lookup(lru_map_fd, &key, value) == -1 && + errno == ENOENT); + + /* BPF_EXIST means: update existing element */ + assert(bpf_map_update(lru_map_fd, &key, value, BPF_EXIST) == -1 && + /* key=2 is not there */ + errno == ENOENT); + + assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST)); + + /* insert key=3 element */ + + /* check that key=3 is not found */ + key = 3; + assert(bpf_map_lookup(lru_map_fd, &key, value) == -1 && + errno == ENOENT); + + /* check that key=1 can be found and mark the ref bit to + * stop LRU from removing key=1 + */ + key = 1; + assert(!bpf_map_lookup(lru_map_fd, &key, value)); + assert(value[0] == 1234); + + key = 3; + assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST)); + assert(!bpf_map_update(expected_map_fd, &key, value, BPF_NOEXIST)); + + /* key=2 has been removed from the LRU */ + key = 2; + assert(bpf_map_lookup(lru_map_fd, &key, value) == -1); + + assert(map_equal(lru_map_fd, expected_map_fd)); + + close(expected_map_fd); + close(lru_map_fd); + + printf("Pass\n"); +} + +/* Size of the LRU map is 1.5*tgt_free + * Insert 1 to tgt_free (+tgt_free keys) + * Lookup 1 to tgt_free/2 + * Insert 1+tgt_free to 2*tgt_free (+tgt_free keys) + * => 1+tgt_free/2 to LOCALFREE_TARGET will be removed by LRU + */ +static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free) +{ + unsigned long long key, end_key, value[nr_cpus]; + int lru_map_fd, expected_map_fd; + unsigned int batch_size; + unsigned int map_size; + + if (map_flags & BPF_F_NO_COMMON_LRU) + /* Ther percpu lru list (i.e each cpu has its own LRU + * list) does not have a local free list. Hence, + * it will only free old nodes till there is no free + * from the LRU list. Hence, this test does not apply + * to BPF_F_NO_COMMON_LRU + */ + return; + + printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type, + map_flags); + + assert(sched_next_online(0, 0) != -1); + + batch_size = tgt_free / 2; + assert(batch_size * 2 == tgt_free); + + map_size = tgt_free + batch_size; + lru_map_fd = create_map(map_type, map_flags, map_size); + assert(lru_map_fd != -1); + + expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0, map_size); + assert(expected_map_fd != -1); + + value[0] = 1234; + + /* Insert 1 to tgt_free (+tgt_free keys) */ + end_key = 1 + tgt_free; + for (key = 1; key < end_key; key++) + assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST)); + + /* Lookup 1 to tgt_free/2 */ + end_key = 1 + batch_size; + for (key = 1; key < end_key; key++) { + assert(!bpf_map_lookup(lru_map_fd, &key, value)); + assert(!bpf_map_update(expected_map_fd, &key, value, + BPF_NOEXIST)); + } + + /* Insert 1+tgt_free to 2*tgt_free + * => 1+tgt_free/2 to LOCALFREE_TARGET will be + * removed by LRU + */ + key = 1 + tgt_free; + end_key = key + tgt_free; + for (; key < end_key; key++) { + assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST)); + assert(!bpf_map_update(expected_map_fd, &key, value, + BPF_NOEXIST)); + } + + assert(map_equal(lru_map_fd, expected_map_fd)); + + close(expected_map_fd); + close(lru_map_fd); + + printf("Pass\n"); +} + +/* Size of the LRU map 1.5 * tgt_free + * Insert 1 to tgt_free (+tgt_free keys) + * Update 1 to tgt_free/2 + * => The original 1 to tgt_free/2 will be removed due to + * the LRU shrink process + * Re-insert 1 to tgt_free/2 again and do a lookup immeidately + * Insert 1+tgt_free to tgt_free*3/2 + * Insert 1+tgt_free*3/2 to tgt_free*5/2 + * => Key 1+tgt_free to tgt_free*3/2 + * will be removed from LRU because it has never + * been lookup and ref bit is not set + */ +static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free) +{ + unsigned long long key, value[nr_cpus]; + unsigned long long end_key; + int lru_map_fd, expected_map_fd; + unsigned int batch_size; + unsigned int map_size; + + if (map_flags & BPF_F_NO_COMMON_LRU) + /* Ther percpu lru list (i.e each cpu has its own LRU + * list) does not have a local free list. Hence, + * it will only free old nodes till there is no free + * from the LRU list. Hence, this test does not apply + * to BPF_F_NO_COMMON_LRU + */ + return; + + printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type, + map_flags); + + assert(sched_next_online(0, 0) != -1); + + batch_size = tgt_free / 2; + assert(batch_size * 2 == tgt_free); + + map_size = tgt_free + batch_size; + if (map_flags & BPF_F_NO_COMMON_LRU) + lru_map_fd = create_map(map_type, map_flags, + map_size * nr_cpus); + else + lru_map_fd = create_map(map_type, map_flags, map_size); + assert(lru_map_fd != -1); + + expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0, map_size); + assert(expected_map_fd != -1); + + value[0] = 1234; + + /* Insert 1 to tgt_free (+tgt_free keys) */ + end_key = 1 + tgt_free; + for (key = 1; key < end_key; key++) + assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST)); + + /* Any bpf_map_update will require to acquire a new node + * from LRU first. + * + * The local list is running out of free nodes. + * It gets from the global LRU list which tries to + * shrink the inactive list to get tgt_free + * number of free nodes. + * + * Hence, the oldest key 1 to tgt_free/2 + * are removed from the LRU list. + */ + key = 1; + if (map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { + assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST)); + assert(!bpf_map_delete(lru_map_fd, &key)); + } else { + assert(bpf_map_update(lru_map_fd, &key, value, BPF_EXIST)); + } + + /* Re-insert 1 to tgt_free/2 again and do a lookup + * immeidately. + */ + end_key = 1 + batch_size; + value[0] = 4321; + for (key = 1; key < end_key; key++) { + assert(bpf_map_lookup(lru_map_fd, &key, value)); + assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST)); + assert(!bpf_map_lookup(lru_map_fd, &key, value)); + assert(value[0] == 4321); + assert(!bpf_map_update(expected_map_fd, &key, value, + BPF_NOEXIST)); + } + + value[0] = 1234; + + /* Insert 1+tgt_free to tgt_free*3/2 */ + end_key = 1 + tgt_free + batch_size; + for (key = 1 + tgt_free; key < end_key; key++) + /* These newly added but not referenced keys will be + * gone during the next LRU shrink. + */ + assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST)); + + /* Insert 1+tgt_free*3/2 to tgt_free*5/2 */ + end_key = key + tgt_free; + for (; key < end_key; key++) { + assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST)); + assert(!bpf_map_update(expected_map_fd, &key, value, + BPF_NOEXIST)); + } + + assert(map_equal(lru_map_fd, expected_map_fd)); + + close(expected_map_fd); + close(lru_map_fd); + + printf("Pass\n"); +} + +/* Size of the LRU map is 2*tgt_free + * It is to test the active/inactive list rotation + * Insert 1 to 2*tgt_free (+2*tgt_free keys) + * Lookup key 1 to tgt_free*3/2 + * Add 1+2*tgt_free to tgt_free*5/2 (+tgt_free/2 keys) + * => key 1+tgt_free*3/2 to 2*tgt_free are removed from LRU + */ +static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free) +{ + unsigned long long key, end_key, value[nr_cpus]; + int lru_map_fd, expected_map_fd; + unsigned int batch_size; + unsigned int map_size; + + printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type, + map_flags); + + assert(sched_next_online(0, 0) != -1); + + batch_size = tgt_free / 2; + assert(batch_size * 2 == tgt_free); + + map_size = tgt_free * 2; + if (map_flags & BPF_F_NO_COMMON_LRU) + lru_map_fd = create_map(map_type, map_flags, + map_size * nr_cpus); + else + lru_map_fd = create_map(map_type, map_flags, map_size); + assert(lru_map_fd != -1); + + expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0, map_size); + assert(expected_map_fd != -1); + + value[0] = 1234; + + /* Insert 1 to 2*tgt_free (+2*tgt_free keys) */ + end_key = 1 + (2 * tgt_free); + for (key = 1; key < end_key; key++) + assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST)); + + /* Lookup key 1 to tgt_free*3/2 */ + end_key = tgt_free + batch_size; + for (key = 1; key < end_key; key++) { + assert(!bpf_map_lookup(lru_map_fd, &key, value)); + assert(!bpf_map_update(expected_map_fd, &key, value, + BPF_NOEXIST)); + } + + /* Add 1+2*tgt_free to tgt_free*5/2 + * (+tgt_free/2 keys) + */ + key = 2 * tgt_free + 1; + end_key = key + batch_size; + for (; key < end_key; key++) { + assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST)); + assert(!bpf_map_update(expected_map_fd, &key, value, + BPF_NOEXIST)); + } + + assert(map_equal(lru_map_fd, expected_map_fd)); + + close(expected_map_fd); + close(lru_map_fd); + + printf("Pass\n"); +} + +/* Test deletion */ +static void test_lru_sanity4(int map_type, int map_flags, unsigned int tgt_free) +{ + int lru_map_fd, expected_map_fd; + unsigned long long key, value[nr_cpus]; + unsigned long long end_key; + + printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type, + map_flags); + + assert(sched_next_online(0, 0) != -1); + + if (map_flags & BPF_F_NO_COMMON_LRU) + lru_map_fd = create_map(map_type, map_flags, + 3 * tgt_free * nr_cpus); + else + lru_map_fd = create_map(map_type, map_flags, 3 * tgt_free); + assert(lru_map_fd != -1); + + expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0, + 3 * tgt_free); + assert(expected_map_fd != -1); + + value[0] = 1234; + + for (key = 1; key <= 2 * tgt_free; key++) + assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST)); + + key = 1; + assert(bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST)); + + for (key = 1; key <= tgt_free; key++) { + assert(!bpf_map_lookup(lru_map_fd, &key, value)); + assert(!bpf_map_update(expected_map_fd, &key, value, + BPF_NOEXIST)); + } + + for (; key <= 2 * tgt_free; key++) { + assert(!bpf_map_delete(lru_map_fd, &key)); + assert(bpf_map_delete(lru_map_fd, &key)); + } + + end_key = key + 2 * tgt_free; + for (; key < end_key; key++) { + assert(!bpf_map_update(lru_map_fd, &key, value, BPF_NOEXIST)); + assert(!bpf_map_update(expected_map_fd, &key, value, + BPF_NOEXIST)); + } + + assert(map_equal(lru_map_fd, expected_map_fd)); + + close(expected_map_fd); + close(lru_map_fd); + + printf("Pass\n"); +} + +static void do_test_lru_sanity5(unsigned long long last_key, int map_fd) +{ + unsigned long long key, value[nr_cpus]; + + /* Ensure the last key inserted by previous CPU can be found */ + assert(!bpf_map_lookup(map_fd, &last_key, value)); + + value[0] = 1234; + + key = last_key + 1; + assert(!bpf_map_update(map_fd, &key, value, BPF_NOEXIST)); + assert(!bpf_map_lookup(map_fd, &key, value)); + + /* Cannot find the last key because it was removed by LRU */ + assert(bpf_map_lookup(map_fd, &last_key, value)); +} + +/* Test map with only one element */ +static void test_lru_sanity5(int map_type, int map_flags) +{ + unsigned long long key, value[nr_cpus]; + int next_sched_cpu = 0; + int map_fd; + int i; + + if (map_flags & BPF_F_NO_COMMON_LRU) + return; + + printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type, + map_flags); + + map_fd = create_map(map_type, map_flags, 1); + assert(map_fd != -1); + + value[0] = 1234; + key = 0; + assert(!bpf_map_update(map_fd, &key, value, BPF_NOEXIST)); + + for (i = 0; i < nr_cpus; i++) { + pid_t pid; + + pid = fork(); + if (pid == 0) { + next_sched_cpu = sched_next_online(0, next_sched_cpu); + if (next_sched_cpu != -1) + do_test_lru_sanity5(key, map_fd); + exit(0); + } else if (pid == -1) { + printf("couldn't spawn #%d process\n", i); + exit(1); + } else { + int status; + + /* It is mostly redundant and just allow the parent + * process to update next_shced_cpu for the next child + * process + */ + next_sched_cpu = sched_next_online(pid, next_sched_cpu); + + assert(waitpid(pid, &status, 0) == pid); + assert(status == 0); + key++; + } + } + + close(map_fd); + + printf("Pass\n"); +} + +int main(int argc, char **argv) +{ + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + int map_types[] = {BPF_MAP_TYPE_LRU_HASH, + BPF_MAP_TYPE_LRU_PERCPU_HASH}; + int map_flags[] = {0, BPF_F_NO_COMMON_LRU}; + int t, f; + + setbuf(stdout, NULL); + + assert(!setrlimit(RLIMIT_MEMLOCK, &r)); + + nr_cpus = bpf_num_possible_cpus(); + assert(nr_cpus != -1); + printf("nr_cpus:%d\n\n", nr_cpus); + + for (f = 0; f < sizeof(map_flags) / sizeof(*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++) { + 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); + test_lru_sanity3(map_types[t], map_flags[f], tgt_free); + test_lru_sanity4(map_types[t], map_flags[f], tgt_free); + test_lru_sanity5(map_types[t], map_flags[f]); + + printf("\n"); + } + } + + return 0; +} diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c new file mode 100644 index 000000000000..eedfef8d2946 --- /dev/null +++ b/tools/testing/selftests/bpf/test_maps.c @@ -0,0 +1,526 @@ +/* + * Testsuite for eBPF maps + * + * Copyright (c) 2014 PLUMgrid, http://plumgrid.com + * Copyright (c) 2016 Facebook + * + * 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 <stdio.h> +#include <unistd.h> +#include <errno.h> +#include <string.h> +#include <assert.h> +#include <stdlib.h> + +#include <sys/wait.h> +#include <sys/resource.h> + +#include <linux/bpf.h> + +#include "bpf_sys.h" +#include "bpf_util.h" + +static int map_flags; + +static void test_hashmap(int task, void *data) +{ + long long key, next_key, value; + int fd; + + fd = bpf_map_create(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value), + 2, map_flags); + if (fd < 0) { + printf("Failed to create hashmap '%s'!\n", strerror(errno)); + exit(1); + } + + key = 1; + value = 1234; + /* Insert key=1 element. */ + assert(bpf_map_update(fd, &key, &value, BPF_ANY) == 0); + + value = 0; + /* BPF_NOEXIST means add new element if it doesn't exist. */ + assert(bpf_map_update(fd, &key, &value, BPF_NOEXIST) == -1 && + /* key=1 already exists. */ + errno == EEXIST); + + /* -1 is an invalid flag. */ + assert(bpf_map_update(fd, &key, &value, -1) == -1 && errno == EINVAL); + + /* Check that key=1 can be found. */ + assert(bpf_map_lookup(fd, &key, &value) == 0 && value == 1234); + + key = 2; + /* Check that key=2 is not found. */ + assert(bpf_map_lookup(fd, &key, &value) == -1 && errno == ENOENT); + + /* BPF_EXIST means update existing element. */ + assert(bpf_map_update(fd, &key, &value, BPF_EXIST) == -1 && + /* key=2 is not there. */ + errno == ENOENT); + + /* Insert key=2 element. */ + assert(bpf_map_update(fd, &key, &value, BPF_NOEXIST) == 0); + + /* key=1 and key=2 were inserted, check that key=0 cannot be + * inserted due to max_entries limit. + */ + key = 0; + assert(bpf_map_update(fd, &key, &value, BPF_NOEXIST) == -1 && + errno == E2BIG); + + /* Update existing element, though the map is full. */ + key = 1; + assert(bpf_map_update(fd, &key, &value, BPF_EXIST) == 0); + key = 2; + assert(bpf_map_update(fd, &key, &value, BPF_ANY) == 0); + key = 1; + assert(bpf_map_update(fd, &key, &value, BPF_ANY) == 0); + + /* Check that key = 0 doesn't exist. */ + key = 0; + assert(bpf_map_delete(fd, &key) == -1 && errno == ENOENT); + + /* Iterate over two elements. */ + assert(bpf_map_next_key(fd, &key, &next_key) == 0 && + (next_key == 1 || next_key == 2)); + assert(bpf_map_next_key(fd, &next_key, &next_key) == 0 && + (next_key == 1 || next_key == 2)); + assert(bpf_map_next_key(fd, &next_key, &next_key) == -1 && + errno == ENOENT); + + /* Delete both elements. */ + key = 1; + assert(bpf_map_delete(fd, &key) == 0); + key = 2; + assert(bpf_map_delete(fd, &key) == 0); + assert(bpf_map_delete(fd, &key) == -1 && errno == ENOENT); + + key = 0; + /* Check that map is empty. */ + assert(bpf_map_next_key(fd, &key, &next_key) == -1 && + errno == ENOENT); + + close(fd); +} + +static void test_hashmap_percpu(int task, void *data) +{ + unsigned int nr_cpus = bpf_num_possible_cpus(); + long long value[nr_cpus]; + long long key, next_key; + int expected_key_mask = 0; + int fd, i; + + fd = bpf_map_create(BPF_MAP_TYPE_PERCPU_HASH, sizeof(key), + sizeof(value[0]), 2, map_flags); + if (fd < 0) { + printf("Failed to create hashmap '%s'!\n", strerror(errno)); + exit(1); + } + + for (i = 0; i < nr_cpus; i++) + value[i] = i + 100; + + key = 1; + /* Insert key=1 element. */ + assert(!(expected_key_mask & key)); + assert(bpf_map_update(fd, &key, value, BPF_ANY) == 0); + expected_key_mask |= key; + + /* BPF_NOEXIST means add new element if it doesn't exist. */ + assert(bpf_map_update(fd, &key, value, BPF_NOEXIST) == -1 && + /* key=1 already exists. */ + errno == EEXIST); + + /* -1 is an invalid flag. */ + assert(bpf_map_update(fd, &key, value, -1) == -1 && errno == EINVAL); + + /* Check that key=1 can be found. Value could be 0 if the lookup + * was run from a different CPU. + */ + value[0] = 1; + assert(bpf_map_lookup(fd, &key, value) == 0 && value[0] == 100); + + key = 2; + /* Check that key=2 is not found. */ + assert(bpf_map_lookup(fd, &key, value) == -1 && errno == ENOENT); + + /* BPF_EXIST means update existing element. */ + assert(bpf_map_update(fd, &key, value, BPF_EXIST) == -1 && + /* key=2 is not there. */ + errno == ENOENT); + + /* Insert key=2 element. */ + assert(!(expected_key_mask & key)); + assert(bpf_map_update(fd, &key, value, BPF_NOEXIST) == 0); + expected_key_mask |= key; + + /* key=1 and key=2 were inserted, check that key=0 cannot be + * inserted due to max_entries limit. + */ + key = 0; + assert(bpf_map_update(fd, &key, value, BPF_NOEXIST) == -1 && + errno == E2BIG); + + /* Check that key = 0 doesn't exist. */ + assert(bpf_map_delete(fd, &key) == -1 && errno == ENOENT); + + /* Iterate over two elements. */ + while (!bpf_map_next_key(fd, &key, &next_key)) { + assert((expected_key_mask & next_key) == next_key); + expected_key_mask &= ~next_key; + + assert(bpf_map_lookup(fd, &next_key, value) == 0); + + for (i = 0; i < nr_cpus; i++) + assert(value[i] == i + 100); + + key = next_key; + } + assert(errno == ENOENT); + + /* Update with BPF_EXIST. */ + key = 1; + assert(bpf_map_update(fd, &key, value, BPF_EXIST) == 0); + + /* Delete both elements. */ + key = 1; + assert(bpf_map_delete(fd, &key) == 0); + key = 2; + assert(bpf_map_delete(fd, &key) == 0); + assert(bpf_map_delete(fd, &key) == -1 && errno == ENOENT); + + key = 0; + /* Check that map is empty. */ + assert(bpf_map_next_key(fd, &key, &next_key) == -1 && + errno == ENOENT); + + close(fd); +} + +static void test_arraymap(int task, void *data) +{ + int key, next_key, fd; + long long value; + + fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, sizeof(key), sizeof(value), + 2, 0); + if (fd < 0) { + printf("Failed to create arraymap '%s'!\n", strerror(errno)); + exit(1); + } + + key = 1; + value = 1234; + /* Insert key=1 element. */ + assert(bpf_map_update(fd, &key, &value, BPF_ANY) == 0); + + value = 0; + assert(bpf_map_update(fd, &key, &value, BPF_NOEXIST) == -1 && + errno == EEXIST); + + /* Check that key=1 can be found. */ + assert(bpf_map_lookup(fd, &key, &value) == 0 && value == 1234); + + key = 0; + /* Check that key=0 is also found and zero initialized. */ + assert(bpf_map_lookup(fd, &key, &value) == 0 && value == 0); + + /* key=0 and key=1 were inserted, check that key=2 cannot be inserted + * due to max_entries limit. + */ + key = 2; + assert(bpf_map_update(fd, &key, &value, BPF_EXIST) == -1 && + errno == E2BIG); + + /* Check that key = 2 doesn't exist. */ + assert(bpf_map_lookup(fd, &key, &value) == -1 && errno == ENOENT); + + /* Iterate over two elements. */ + assert(bpf_map_next_key(fd, &key, &next_key) == 0 && + next_key == 0); + assert(bpf_map_next_key(fd, &next_key, &next_key) == 0 && + next_key == 1); + assert(bpf_map_next_key(fd, &next_key, &next_key) == -1 && + errno == ENOENT); + + /* Delete shouldn't succeed. */ + key = 1; + assert(bpf_map_delete(fd, &key) == -1 && errno == EINVAL); + + close(fd); +} + +static void test_arraymap_percpu(int task, void *data) +{ + unsigned int nr_cpus = bpf_num_possible_cpus(); + int key, next_key, fd, i; + long values[nr_cpus]; + + fd = bpf_map_create(BPF_MAP_TYPE_PERCPU_ARRAY, sizeof(key), + sizeof(values[0]), 2, 0); + if (fd < 0) { + printf("Failed to create arraymap '%s'!\n", strerror(errno)); + exit(1); + } + + for (i = 0; i < nr_cpus; i++) + values[i] = i + 100; + + key = 1; + /* Insert key=1 element. */ + assert(bpf_map_update(fd, &key, values, BPF_ANY) == 0); + + values[0] = 0; + assert(bpf_map_update(fd, &key, values, BPF_NOEXIST) == -1 && + errno == EEXIST); + + /* Check that key=1 can be found. */ + assert(bpf_map_lookup(fd, &key, values) == 0 && values[0] == 100); + + key = 0; + /* Check that key=0 is also found and zero initialized. */ + assert(bpf_map_lookup(fd, &key, values) == 0 && + values[0] == 0 && values[nr_cpus - 1] == 0); + + /* Check that key=2 cannot be inserted due to max_entries limit. */ + key = 2; + assert(bpf_map_update(fd, &key, values, BPF_EXIST) == -1 && + errno == E2BIG); + + /* Check that key = 2 doesn't exist. */ + assert(bpf_map_lookup(fd, &key, values) == -1 && errno == ENOENT); + + /* Iterate over two elements. */ + assert(bpf_map_next_key(fd, &key, &next_key) == 0 && + next_key == 0); + assert(bpf_map_next_key(fd, &next_key, &next_key) == 0 && + next_key == 1); + assert(bpf_map_next_key(fd, &next_key, &next_key) == -1 && + errno == ENOENT); + + /* Delete shouldn't succeed. */ + key = 1; + assert(bpf_map_delete(fd, &key) == -1 && errno == EINVAL); + + close(fd); +} + +static void test_arraymap_percpu_many_keys(void) +{ + unsigned int nr_cpus = bpf_num_possible_cpus(); + unsigned int nr_keys = 20000; + long values[nr_cpus]; + int key, fd, i; + + fd = bpf_map_create(BPF_MAP_TYPE_PERCPU_ARRAY, sizeof(key), + sizeof(values[0]), nr_keys, 0); + if (fd < 0) { + printf("Failed to create per-cpu arraymap '%s'!\n", + strerror(errno)); + exit(1); + } + + for (i = 0; i < nr_cpus; i++) + values[i] = i + 10; + + for (key = 0; key < nr_keys; key++) + assert(bpf_map_update(fd, &key, values, BPF_ANY) == 0); + + for (key = 0; key < nr_keys; key++) { + for (i = 0; i < nr_cpus; i++) + values[i] = 0; + + assert(bpf_map_lookup(fd, &key, values) == 0); + + for (i = 0; i < nr_cpus; i++) + assert(values[i] == i + 10); + } + + close(fd); +} + +#define MAP_SIZE (32 * 1024) + +static void test_map_large(void) +{ + struct bigkey { + int a; + char b[116]; + long long c; + } key; + int fd, i, value; + + fd = bpf_map_create(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value), + MAP_SIZE, map_flags); + if (fd < 0) { + printf("Failed to create large map '%s'!\n", strerror(errno)); + exit(1); + } + + for (i = 0; i < MAP_SIZE; i++) { + key = (struct bigkey) { .c = i }; + value = i; + + assert(bpf_map_update(fd, &key, &value, BPF_NOEXIST) == 0); + } + + key.c = -1; + assert(bpf_map_update(fd, &key, &value, BPF_NOEXIST) == -1 && + errno == E2BIG); + + /* Iterate through all elements. */ + for (i = 0; i < MAP_SIZE; i++) + assert(bpf_map_next_key(fd, &key, &key) == 0); + assert(bpf_map_next_key(fd, &key, &key) == -1 && errno == ENOENT); + + key.c = 0; + assert(bpf_map_lookup(fd, &key, &value) == 0 && value == 0); + key.a = 1; + assert(bpf_map_lookup(fd, &key, &value) == -1 && errno == ENOENT); + + close(fd); +} + +static void run_parallel(int tasks, void (*fn)(int task, void *data), + void *data) +{ + pid_t pid[tasks]; + int i; + + for (i = 0; i < tasks; i++) { + pid[i] = fork(); + if (pid[i] == 0) { + fn(i, data); + exit(0); + } else if (pid[i] == -1) { + printf("Couldn't spawn #%d process!\n", i); + exit(1); + } + } + + for (i = 0; i < tasks; i++) { + int status; + + assert(waitpid(pid[i], &status, 0) == pid[i]); + assert(status == 0); + } +} + +static void test_map_stress(void) +{ + run_parallel(100, test_hashmap, NULL); + run_parallel(100, test_hashmap_percpu, NULL); + + run_parallel(100, test_arraymap, NULL); + run_parallel(100, test_arraymap_percpu, NULL); +} + +#define TASKS 1024 + +#define DO_UPDATE 1 +#define DO_DELETE 0 + +static void do_work(int fn, void *data) +{ + int do_update = ((int *)data)[1]; + int fd = ((int *)data)[0]; + int i, key, value; + + for (i = fn; i < MAP_SIZE; i += TASKS) { + key = value = i; + + if (do_update) { + assert(bpf_map_update(fd, &key, &value, BPF_NOEXIST) == 0); + assert(bpf_map_update(fd, &key, &value, BPF_EXIST) == 0); + } else { + assert(bpf_map_delete(fd, &key) == 0); + } + } +} + +static void test_map_parallel(void) +{ + int i, fd, key = 0, value = 0; + int data[2]; + + fd = bpf_map_create(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value), + MAP_SIZE, map_flags); + if (fd < 0) { + printf("Failed to create map for parallel test '%s'!\n", + strerror(errno)); + exit(1); + } + + /* Use the same fd in children to add elements to this map: + * child_0 adds key=0, key=1024, key=2048, ... + * child_1 adds key=1, key=1025, key=2049, ... + * child_1023 adds key=1023, ... + */ + data[0] = fd; + data[1] = DO_UPDATE; + run_parallel(TASKS, do_work, data); + + /* Check that key=0 is already there. */ + assert(bpf_map_update(fd, &key, &value, BPF_NOEXIST) == -1 && + errno == EEXIST); + + /* Check that all elements were inserted. */ + key = -1; + for (i = 0; i < MAP_SIZE; i++) + assert(bpf_map_next_key(fd, &key, &key) == 0); + assert(bpf_map_next_key(fd, &key, &key) == -1 && errno == ENOENT); + + /* Another check for all elements */ + for (i = 0; i < MAP_SIZE; i++) { + key = MAP_SIZE - i - 1; + + assert(bpf_map_lookup(fd, &key, &value) == 0 && + value == key); + } + + /* Now let's delete all elemenets in parallel. */ + data[1] = DO_DELETE; + run_parallel(TASKS, do_work, data); + + /* Nothing should be left. */ + key = -1; + assert(bpf_map_next_key(fd, &key, &key) == -1 && errno == ENOENT); +} + +static void run_all_tests(void) +{ + test_hashmap(0, NULL); + test_hashmap_percpu(0, NULL); + + test_arraymap(0, NULL); + test_arraymap_percpu(0, NULL); + + test_arraymap_percpu_many_keys(); + + test_map_large(); + test_map_parallel(); + test_map_stress(); +} + +int main(void) +{ + struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY }; + + setrlimit(RLIMIT_MEMLOCK, &rinf); + + map_flags = 0; + run_all_tests(); + + map_flags = BPF_F_NO_PREALLOC; + run_all_tests(); + + printf("test_maps: OK\n"); + return 0; +} diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c new file mode 100644 index 000000000000..0103bf2e0c0d --- /dev/null +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -0,0 +1,3053 @@ +/* + * Testsuite for eBPF verifier + * + * Copyright (c) 2014 PLUMgrid, http://plumgrid.com + * + * 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 <stdio.h> +#include <unistd.h> +#include <errno.h> +#include <string.h> +#include <stddef.h> +#include <stdbool.h> +#include <sched.h> + +#include <sys/resource.h> + +#include <linux/unistd.h> +#include <linux/filter.h> +#include <linux/bpf_perf_event.h> +#include <linux/bpf.h> + +#include "../../../include/linux/filter.h" + +#include "bpf_sys.h" + +#ifndef ARRAY_SIZE +# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif + +#define MAX_INSNS 512 +#define MAX_FIXUPS 8 + +struct bpf_test { + const char *descr; + struct bpf_insn insns[MAX_INSNS]; + int fixup_map1[MAX_FIXUPS]; + int fixup_map2[MAX_FIXUPS]; + int fixup_prog[MAX_FIXUPS]; + const char *errstr; + const char *errstr_unpriv; + enum { + UNDEF, + ACCEPT, + REJECT + } result, result_unpriv; + enum bpf_prog_type prog_type; +}; + +/* Note we want this to be 64 bit aligned so that the end of our array is + * actually the end of the structure. + */ +#define MAX_ENTRIES 11 + +struct test_val { + unsigned int index; + int foo[MAX_ENTRIES]; +}; + +static struct bpf_test tests[] = { + { + "add+sub+mul", + .insns = { + BPF_MOV64_IMM(BPF_REG_1, 1), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 2), + BPF_MOV64_IMM(BPF_REG_2, 3), + BPF_ALU64_REG(BPF_SUB, BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -1), + BPF_ALU64_IMM(BPF_MUL, BPF_REG_1, 3), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + }, + { + "unreachable", + .insns = { + BPF_EXIT_INSN(), + BPF_EXIT_INSN(), + }, + .errstr = "unreachable", + .result = REJECT, + }, + { + "unreachable2", + .insns = { + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "unreachable", + .result = REJECT, + }, + { + "out of range jump", + .insns = { + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_EXIT_INSN(), + }, + .errstr = "jump out of range", + .result = REJECT, + }, + { + "out of range jump2", + .insns = { + BPF_JMP_IMM(BPF_JA, 0, 0, -2), + BPF_EXIT_INSN(), + }, + .errstr = "jump out of range", + .result = REJECT, + }, + { + "test1 ld_imm64", + .insns = { + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1), + BPF_LD_IMM64(BPF_REG_0, 0), + BPF_LD_IMM64(BPF_REG_0, 0), + BPF_LD_IMM64(BPF_REG_0, 1), + BPF_LD_IMM64(BPF_REG_0, 1), + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_EXIT_INSN(), + }, + .errstr = "invalid BPF_LD_IMM insn", + .errstr_unpriv = "R1 pointer comparison", + .result = REJECT, + }, + { + "test2 ld_imm64", + .insns = { + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1), + BPF_LD_IMM64(BPF_REG_0, 0), + BPF_LD_IMM64(BPF_REG_0, 0), + BPF_LD_IMM64(BPF_REG_0, 1), + BPF_LD_IMM64(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .errstr = "invalid BPF_LD_IMM insn", + .errstr_unpriv = "R1 pointer comparison", + .result = REJECT, + }, + { + "test3 ld_imm64", + .insns = { + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1), + BPF_RAW_INSN(BPF_LD | BPF_IMM | BPF_DW, 0, 0, 0, 0), + BPF_LD_IMM64(BPF_REG_0, 0), + BPF_LD_IMM64(BPF_REG_0, 0), + BPF_LD_IMM64(BPF_REG_0, 1), + BPF_LD_IMM64(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_ld_imm64 insn", + .result = REJECT, + }, + { + "test4 ld_imm64", + .insns = { + BPF_RAW_INSN(BPF_LD | BPF_IMM | BPF_DW, 0, 0, 0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_ld_imm64 insn", + .result = REJECT, + }, + { + "test5 ld_imm64", + .insns = { + BPF_RAW_INSN(BPF_LD | BPF_IMM | BPF_DW, 0, 0, 0, 0), + }, + .errstr = "invalid bpf_ld_imm64 insn", + .result = REJECT, + }, + { + "no bpf_exit", + .insns = { + BPF_ALU64_REG(BPF_MOV, BPF_REG_0, BPF_REG_2), + }, + .errstr = "jump out of range", + .result = REJECT, + }, + { + "loop (back-edge)", + .insns = { + BPF_JMP_IMM(BPF_JA, 0, 0, -1), + BPF_EXIT_INSN(), + }, + .errstr = "back-edge", + .result = REJECT, + }, + { + "loop2 (back-edge)", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_0), + BPF_JMP_IMM(BPF_JA, 0, 0, -4), + BPF_EXIT_INSN(), + }, + .errstr = "back-edge", + .result = REJECT, + }, + { + "conditional loop", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, -3), + BPF_EXIT_INSN(), + }, + .errstr = "back-edge", + .result = REJECT, + }, + { + "read uninitialized register", + .insns = { + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_EXIT_INSN(), + }, + .errstr = "R2 !read_ok", + .result = REJECT, + }, + { + "read invalid register", + .insns = { + BPF_MOV64_REG(BPF_REG_0, -1), + BPF_EXIT_INSN(), + }, + .errstr = "R15 is invalid", + .result = REJECT, + }, + { + "program doesn't init R0 before exit", + .insns = { + BPF_ALU64_REG(BPF_MOV, BPF_REG_2, BPF_REG_1), + BPF_EXIT_INSN(), + }, + .errstr = "R0 !read_ok", + .result = REJECT, + }, + { + "program doesn't init R0 before exit in all branches", + .insns = { + BPF_JMP_IMM(BPF_JGE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 2), + BPF_EXIT_INSN(), + }, + .errstr = "R0 !read_ok", + .errstr_unpriv = "R1 pointer comparison", + .result = REJECT, + }, + { + "stack out of bounds", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, 8, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid stack", + .result = REJECT, + }, + { + "invalid call insn1", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL | BPF_X, 0, 0, 0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "BPF_CALL uses reserved", + .result = REJECT, + }, + { + "invalid call insn2", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 1, 0), + BPF_EXIT_INSN(), + }, + .errstr = "BPF_CALL uses reserved", + .result = REJECT, + }, + { + "invalid function call", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, 1234567), + BPF_EXIT_INSN(), + }, + .errstr = "invalid func unknown#1234567", + .result = REJECT, + }, + { + "uninitialized stack1", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 2 }, + .errstr = "invalid indirect read from stack", + .result = REJECT, + }, + { + "uninitialized stack2", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, -8), + BPF_EXIT_INSN(), + }, + .errstr = "invalid read from stack", + .result = REJECT, + }, + { + "invalid argument register", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_get_cgroup_classid), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_get_cgroup_classid), + BPF_EXIT_INSN(), + }, + .errstr = "R1 !read_ok", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "non-invalid argument register", + .insns = { + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_get_cgroup_classid), + BPF_ALU64_REG(BPF_MOV, BPF_REG_1, BPF_REG_6), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_get_cgroup_classid), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "check valid spill/fill", + .insns = { + /* spill R1(ctx) into stack */ + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8), + /* fill it back into R2 */ + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -8), + /* should be able to access R0 = *(R2 + 8) */ + /* BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, 8), */ + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_EXIT_INSN(), + }, + .errstr_unpriv = "R0 leaks addr", + .result = ACCEPT, + .result_unpriv = REJECT, + }, + { + "check valid spill/fill, skb mark", + .insns = { + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_6, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, + offsetof(struct __sk_buff, mark)), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .result_unpriv = ACCEPT, + }, + { + "check corrupted spill/fill", + .insns = { + /* spill R1(ctx) into stack */ + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8), + /* mess up with R1 pointer on stack */ + BPF_ST_MEM(BPF_B, BPF_REG_10, -7, 0x23), + /* fill back into R0 should fail */ + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8), + BPF_EXIT_INSN(), + }, + .errstr_unpriv = "attempt to corrupt spilled", + .errstr = "corrupted spill", + .result = REJECT, + }, + { + "invalid src register in STX", + .insns = { + BPF_STX_MEM(BPF_B, BPF_REG_10, -1, -1), + BPF_EXIT_INSN(), + }, + .errstr = "R15 is invalid", + .result = REJECT, + }, + { + "invalid dst register in STX", + .insns = { + BPF_STX_MEM(BPF_B, 14, BPF_REG_10, -1), + BPF_EXIT_INSN(), + }, + .errstr = "R14 is invalid", + .result = REJECT, + }, + { + "invalid dst register in ST", + .insns = { + BPF_ST_MEM(BPF_B, 14, -1, -1), + BPF_EXIT_INSN(), + }, + .errstr = "R14 is invalid", + .result = REJECT, + }, + { + "invalid src register in LDX", + .insns = { + BPF_LDX_MEM(BPF_B, BPF_REG_0, 12, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R12 is invalid", + .result = REJECT, + }, + { + "invalid dst register in LDX", + .insns = { + BPF_LDX_MEM(BPF_B, 11, BPF_REG_1, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R11 is invalid", + .result = REJECT, + }, + { + "junk insn", + .insns = { + BPF_RAW_INSN(0, 0, 0, 0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid BPF_LD_IMM", + .result = REJECT, + }, + { + "junk insn2", + .insns = { + BPF_RAW_INSN(1, 0, 0, 0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "BPF_LDX uses reserved fields", + .result = REJECT, + }, + { + "junk insn3", + .insns = { + BPF_RAW_INSN(-1, 0, 0, 0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid BPF_ALU opcode f0", + .result = REJECT, + }, + { + "junk insn4", + .insns = { + BPF_RAW_INSN(-1, -1, -1, -1, -1), + BPF_EXIT_INSN(), + }, + .errstr = "invalid BPF_ALU opcode f0", + .result = REJECT, + }, + { + "junk insn5", + .insns = { + BPF_RAW_INSN(0x7f, -1, -1, -1, -1), + BPF_EXIT_INSN(), + }, + .errstr = "BPF_ALU uses reserved fields", + .result = REJECT, + }, + { + "misaligned read from stack", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, -4), + BPF_EXIT_INSN(), + }, + .errstr = "misaligned access", + .result = REJECT, + }, + { + "invalid map_fd for function call", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_ALU64_REG(BPF_MOV, BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_delete_elem), + BPF_EXIT_INSN(), + }, + .errstr = "fd 0 is not pointing to valid bpf_map", + .result = REJECT, + }, + { + "don't check return value before access", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr = "R0 invalid mem access 'map_value_or_null'", + .result = REJECT, + }, + { + "access memory with incorrect alignment", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 4, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr = "misaligned access", + .result = REJECT, + }, + { + "sometimes access memory with incorrect alignment", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0), + BPF_EXIT_INSN(), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr = "R0 invalid mem access", + .errstr_unpriv = "R0 leaks addr", + .result = REJECT, + }, + { + "jump test 1", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1), + BPF_ST_MEM(BPF_DW, BPF_REG_2, -8, 0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 1, 1), + BPF_ST_MEM(BPF_DW, BPF_REG_2, -16, 1), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 2, 1), + BPF_ST_MEM(BPF_DW, BPF_REG_2, -8, 2), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 3, 1), + BPF_ST_MEM(BPF_DW, BPF_REG_2, -16, 3), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 4, 1), + BPF_ST_MEM(BPF_DW, BPF_REG_2, -8, 4), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 5, 1), + BPF_ST_MEM(BPF_DW, BPF_REG_2, -32, 5), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr_unpriv = "R1 pointer comparison", + .result_unpriv = REJECT, + .result = ACCEPT, + }, + { + "jump test 2", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 2), + BPF_ST_MEM(BPF_DW, BPF_REG_2, -8, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, 14), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 1, 2), + BPF_ST_MEM(BPF_DW, BPF_REG_2, -16, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, 11), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 2, 2), + BPF_ST_MEM(BPF_DW, BPF_REG_2, -32, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, 8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 3, 2), + BPF_ST_MEM(BPF_DW, BPF_REG_2, -40, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, 5), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 4, 2), + BPF_ST_MEM(BPF_DW, BPF_REG_2, -48, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, 2), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 5, 1), + BPF_ST_MEM(BPF_DW, BPF_REG_2, -56, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr_unpriv = "R1 pointer comparison", + .result_unpriv = REJECT, + .result = ACCEPT, + }, + { + "jump test 3", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 3), + BPF_ST_MEM(BPF_DW, BPF_REG_2, -8, 0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_JMP_IMM(BPF_JA, 0, 0, 19), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 1, 3), + BPF_ST_MEM(BPF_DW, BPF_REG_2, -16, 0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16), + BPF_JMP_IMM(BPF_JA, 0, 0, 15), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 2, 3), + BPF_ST_MEM(BPF_DW, BPF_REG_2, -32, 0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -32), + BPF_JMP_IMM(BPF_JA, 0, 0, 11), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 3, 3), + BPF_ST_MEM(BPF_DW, BPF_REG_2, -40, 0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -40), + BPF_JMP_IMM(BPF_JA, 0, 0, 7), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 4, 3), + BPF_ST_MEM(BPF_DW, BPF_REG_2, -48, 0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -48), + BPF_JMP_IMM(BPF_JA, 0, 0, 3), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 5, 0), + BPF_ST_MEM(BPF_DW, BPF_REG_2, -56, 0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -56), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_delete_elem), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 24 }, + .errstr_unpriv = "R1 pointer comparison", + .result_unpriv = REJECT, + .result = ACCEPT, + }, + { + "jump test 4", + .insns = { + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 1), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 2), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 3), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 4), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 1), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 2), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 3), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 4), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 1), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 2), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 3), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 4), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 1), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 2), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 3), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 4), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 1), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 2), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 3), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 4), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 1), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 2), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 3), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 4), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 1), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 2), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 3), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 4), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 1), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 2), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 3), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 4), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 1), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 2), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 3), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 4), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, BPF_REG_10, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr_unpriv = "R1 pointer comparison", + .result_unpriv = REJECT, + .result = ACCEPT, + }, + { + "jump test 5", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_2), + BPF_JMP_IMM(BPF_JGE, BPF_REG_1, 0, 2), + BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_3, -8), + BPF_JMP_IMM(BPF_JA, 0, 0, 2), + BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_2, -8), + BPF_JMP_IMM(BPF_JA, 0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JGE, BPF_REG_1, 0, 2), + BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_3, -8), + BPF_JMP_IMM(BPF_JA, 0, 0, 2), + BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_2, -8), + BPF_JMP_IMM(BPF_JA, 0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JGE, BPF_REG_1, 0, 2), + BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_3, -8), + BPF_JMP_IMM(BPF_JA, 0, 0, 2), + BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_2, -8), + BPF_JMP_IMM(BPF_JA, 0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JGE, BPF_REG_1, 0, 2), + BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_3, -8), + BPF_JMP_IMM(BPF_JA, 0, 0, 2), + BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_2, -8), + BPF_JMP_IMM(BPF_JA, 0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JGE, BPF_REG_1, 0, 2), + BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_3, -8), + BPF_JMP_IMM(BPF_JA, 0, 0, 2), + BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_2, -8), + BPF_JMP_IMM(BPF_JA, 0, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr_unpriv = "R1 pointer comparison", + .result_unpriv = REJECT, + .result = ACCEPT, + }, + { + "access skb fields ok", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, len)), + BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 0, 1), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, mark)), + BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 0, 1), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, pkt_type)), + BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 0, 1), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, queue_mapping)), + BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 0, 0), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, protocol)), + BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 0, 0), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, vlan_present)), + BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 0, 0), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, vlan_tci)), + BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + }, + { + "access skb fields bad1", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -4), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + }, + { + "access skb fields bad2", + .insns = { + BPF_JMP_IMM(BPF_JGE, BPF_REG_1, 0, 9), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + 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_0, BPF_REG_1, + offsetof(struct __sk_buff, pkt_type)), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 4 }, + .errstr = "different pointers", + .errstr_unpriv = "R1 pointer comparison", + .result = REJECT, + }, + { + "access skb fields bad3", + .insns = { + BPF_JMP_IMM(BPF_JGE, BPF_REG_1, 0, 2), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, pkt_type)), + BPF_EXIT_INSN(), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_JMP_IMM(BPF_JA, 0, 0, -12), + }, + .fixup_map1 = { 6 }, + .errstr = "different pointers", + .errstr_unpriv = "R1 pointer comparison", + .result = REJECT, + }, + { + "access skb fields bad4", + .insns = { + BPF_JMP_IMM(BPF_JGE, BPF_REG_1, 0, 3), + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_1, + offsetof(struct __sk_buff, len)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_JMP_IMM(BPF_JA, 0, 0, -13), + }, + .fixup_map1 = { 7 }, + .errstr = "different pointers", + .errstr_unpriv = "R1 pointer comparison", + .result = REJECT, + }, + { + "check skb->mark is not writeable by sockets", + .insns = { + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_1, + offsetof(struct __sk_buff, mark)), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .errstr_unpriv = "R1 leaks addr", + .result = REJECT, + }, + { + "check skb->tc_index is not writeable by sockets", + .insns = { + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_1, + offsetof(struct __sk_buff, tc_index)), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .errstr_unpriv = "R1 leaks addr", + .result = REJECT, + }, + { + "check non-u32 access to cb", + .insns = { + BPF_STX_MEM(BPF_H, BPF_REG_1, BPF_REG_1, + offsetof(struct __sk_buff, cb[0])), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .errstr_unpriv = "R1 leaks addr", + .result = REJECT, + }, + { + "check out of range skb->cb access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[0]) + 256), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .errstr_unpriv = "", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SCHED_ACT, + }, + { + "write skb fields from socket prog", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[4])), + BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 0, 1), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, mark)), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, tc_index)), + BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 0, 1), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_1, + offsetof(struct __sk_buff, cb[0])), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_1, + offsetof(struct __sk_buff, cb[2])), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .errstr_unpriv = "R1 leaks addr", + .result_unpriv = REJECT, + }, + { + "write skb fields from tc_cls_act prog", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, cb[0])), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, mark)), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, tc_index)), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, tc_index)), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, cb[3])), + BPF_EXIT_INSN(), + }, + .errstr_unpriv = "", + .result_unpriv = REJECT, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "PTR_TO_STACK store/load", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -10), + BPF_ST_MEM(BPF_DW, BPF_REG_1, 2, 0xfaceb00c), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 2), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + }, + { + "PTR_TO_STACK store/load - bad alignment on off", + .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, 2, 0xfaceb00c), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 2), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "misaligned access off -6 size 8", + }, + { + "PTR_TO_STACK store/load - bad alignment on reg", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -10), + BPF_ST_MEM(BPF_DW, BPF_REG_1, 8, 0xfaceb00c), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 8), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "misaligned access off -2 size 8", + }, + { + "PTR_TO_STACK store/load - out of bounds low", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -80000), + BPF_ST_MEM(BPF_DW, BPF_REG_1, 8, 0xfaceb00c), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 8), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid stack off=-79992 size=8", + }, + { + "PTR_TO_STACK store/load - out of bounds high", + .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, 8, 0xfaceb00c), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 8), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid stack off=0 size=8", + }, + { + "unpriv: return pointer", + .insns = { + BPF_MOV64_REG(BPF_REG_0, BPF_REG_10), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "R0 leaks addr", + }, + { + "unpriv: add const to pointer", + .insns = { + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "R1 pointer arithmetic", + }, + { + "unpriv: add pointer to pointer", + .insns = { + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_10), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "R1 pointer arithmetic", + }, + { + "unpriv: neg pointer", + .insns = { + BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "R1 pointer arithmetic", + }, + { + "unpriv: cmp pointer with const", + .insns = { + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "R1 pointer comparison", + }, + { + "unpriv: cmp pointer with pointer", + .insns = { + BPF_JMP_REG(BPF_JEQ, BPF_REG_1, BPF_REG_10, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "R10 pointer comparison", + }, + { + "unpriv: check that printk is disallowed", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_2, 8), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_1), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_trace_printk), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr_unpriv = "unknown func 6", + .result_unpriv = REJECT, + .result = ACCEPT, + }, + { + "unpriv: pass pointer to helper function", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_2), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_2), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_update_elem), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr_unpriv = "R4 leaks addr", + .result_unpriv = REJECT, + .result = ACCEPT, + }, + { + "unpriv: indirectly pass pointer on stack to helper function", + .insns = { + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_10, -8), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr = "invalid indirect read from stack off -8+0 size 8", + .result = REJECT, + }, + { + "unpriv: mangle pointer on stack 1", + .insns = { + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_10, -8), + BPF_ST_MEM(BPF_W, BPF_REG_10, -8, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr_unpriv = "attempt to corrupt spilled", + .result_unpriv = REJECT, + .result = ACCEPT, + }, + { + "unpriv: mangle pointer on stack 2", + .insns = { + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_10, -8), + BPF_ST_MEM(BPF_B, BPF_REG_10, -1, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr_unpriv = "attempt to corrupt spilled", + .result_unpriv = REJECT, + .result = ACCEPT, + }, + { + "unpriv: read pointer from stack in small chunks", + .insns = { + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_10, -8), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_10, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid size", + .result = REJECT, + }, + { + "unpriv: write pointer into ctx", + .insns = { + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr_unpriv = "R1 leaks addr", + .result_unpriv = REJECT, + .errstr = "invalid bpf_context access", + .result = REJECT, + }, + { + "unpriv: spill/fill of ctx", + .insns = { + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + }, + { + "unpriv: spill/fill of ctx 2", + .insns = { + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_get_hash_recalc), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "unpriv: spill/fill of ctx 3", + .insns = { + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_10, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_get_hash_recalc), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "R1 type=fp expected=ctx", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "unpriv: spill/fill of ctx 4", + .insns = { + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_DW, BPF_REG_10, + BPF_REG_0, -8, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_get_hash_recalc), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "R1 type=inv expected=ctx", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "unpriv: spill/fill of different pointers stx", + .insns = { + BPF_MOV64_IMM(BPF_REG_3, 42), + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 3), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16), + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_2, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1), + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, 0), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3, + offsetof(struct __sk_buff, mark)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "same insn cannot be used with different pointers", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "unpriv: spill/fill of different pointers ldx", + .insns = { + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 3), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, + -(__s32)offsetof(struct bpf_perf_event_data, + sample_period) - 8), + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_2, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1), + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, + offsetof(struct bpf_perf_event_data, + sample_period)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "same insn cannot be used with different pointers", + .prog_type = BPF_PROG_TYPE_PERF_EVENT, + }, + { + "unpriv: write pointer into map elem value", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr_unpriv = "R0 leaks addr", + .result_unpriv = REJECT, + .result = ACCEPT, + }, + { + "unpriv: partial copy of pointer", + .insns = { + BPF_MOV32_REG(BPF_REG_1, BPF_REG_10), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr_unpriv = "R10 partial copy", + .result_unpriv = REJECT, + .result = ACCEPT, + }, + { + "unpriv: pass pointer to tail_call", + .insns = { + BPF_MOV64_REG(BPF_REG_3, BPF_REG_1), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_tail_call), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_prog = { 1 }, + .errstr_unpriv = "R3 leaks addr into helper", + .result_unpriv = REJECT, + .result = ACCEPT, + }, + { + "unpriv: cmp map pointer with zero", + .insns = { + BPF_MOV64_IMM(BPF_REG_1, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 1 }, + .errstr_unpriv = "R1 pointer comparison", + .result_unpriv = REJECT, + .result = ACCEPT, + }, + { + "unpriv: write into frame pointer", + .insns = { + BPF_MOV64_REG(BPF_REG_10, BPF_REG_1), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "frame pointer is read only", + .result = REJECT, + }, + { + "unpriv: spill/fill frame pointer", + .insns = { + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_10, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_10, BPF_REG_6, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "frame pointer is read only", + .result = REJECT, + }, + { + "unpriv: cmp of frame pointer", + .insns = { + BPF_JMP_IMM(BPF_JEQ, BPF_REG_10, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr_unpriv = "R10 pointer comparison", + .result_unpriv = REJECT, + .result = ACCEPT, + }, + { + "unpriv: cmp of stack pointer", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_2, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr_unpriv = "R2 pointer comparison", + .result_unpriv = REJECT, + .result = ACCEPT, + }, + { + "unpriv: obfuscate stack pointer", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr_unpriv = "R2 pointer arithmetic", + .result_unpriv = REJECT, + .result = ACCEPT, + }, + { + "raw_stack: no skb_load_bytes", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_4, 8), + /* Call to skb_load_bytes() omitted. */ + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid read from stack off -8+0 size 8", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "raw_stack: skb_load_bytes, negative len", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_4, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_load_bytes), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid stack type R3", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "raw_stack: skb_load_bytes, negative len 2", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_4, ~0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_load_bytes), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid stack type R3", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "raw_stack: skb_load_bytes, zero len", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_load_bytes), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid stack type R3", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "raw_stack: skb_load_bytes, no init", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_4, 8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_load_bytes), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "raw_stack: skb_load_bytes, init", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_6, 0, 0xcafe), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_4, 8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_load_bytes), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "raw_stack: skb_load_bytes, spilled regs around bounds", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -16), + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 8), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_4, 8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_load_bytes), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_6, 8), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, + offsetof(struct __sk_buff, mark)), + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_2, + offsetof(struct __sk_buff, priority)), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_2), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "raw_stack: skb_load_bytes, spilled regs corruption", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_4, 8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_load_bytes), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, + offsetof(struct __sk_buff, mark)), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "R0 invalid mem access 'inv'", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "raw_stack: skb_load_bytes, spilled regs corruption 2", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -16), + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 8), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_4, 8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_load_bytes), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_6, 8), + BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_6, 0), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, + offsetof(struct __sk_buff, mark)), + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_2, + offsetof(struct __sk_buff, priority)), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_2), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_3, + offsetof(struct __sk_buff, pkt_type)), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_3), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "R3 invalid mem access 'inv'", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "raw_stack: skb_load_bytes, spilled regs + data", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -16), + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 8), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_4, 8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_load_bytes), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_6, 8), + BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_6, 0), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, + offsetof(struct __sk_buff, mark)), + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_2, + offsetof(struct __sk_buff, priority)), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_3), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "raw_stack: skb_load_bytes, invalid access 1", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -513), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_4, 8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_load_bytes), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid stack type R3 off=-513 access_size=8", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "raw_stack: skb_load_bytes, invalid access 2", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -1), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_4, 8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_load_bytes), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid stack type R3 off=-1 access_size=8", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "raw_stack: skb_load_bytes, invalid access 3", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 0xffffffff), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_4, 0xffffffff), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_load_bytes), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid stack type R3 off=-1 access_size=-1", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "raw_stack: skb_load_bytes, invalid access 4", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -1), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_4, 0x7fffffff), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_load_bytes), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid stack type R3 off=-1 access_size=2147483647", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "raw_stack: skb_load_bytes, invalid access 5", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -512), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_4, 0x7fffffff), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_load_bytes), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid stack type R3 off=-512 access_size=2147483647", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "raw_stack: skb_load_bytes, invalid access 6", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -512), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_load_bytes), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid stack type R3 off=-512 access_size=0", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "raw_stack: skb_load_bytes, large access", + .insns = { + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -512), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_4, 512), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_load_bytes), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "direct packet access: test1", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "direct packet access: test2", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_MOV64_REG(BPF_REG_5, BPF_REG_3), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 14), + BPF_JMP_REG(BPF_JGT, BPF_REG_5, BPF_REG_4, 15), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_3, 7), + BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_3, 12), + BPF_ALU64_IMM(BPF_MUL, BPF_REG_4, 14), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_ALU64_REG(BPF_ADD, BPF_REG_3, BPF_REG_4), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_1), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_2, 48), + BPF_ALU64_IMM(BPF_RSH, BPF_REG_2, 48), + BPF_ALU64_REG(BPF_ADD, BPF_REG_3, BPF_REG_2), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_3), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 8), + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_1, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_3, 4), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "direct packet access: test3", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access off=76", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SOCKET_FILTER, + }, + { + "direct packet access: test4 (write)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + BPF_STX_MEM(BPF_B, BPF_REG_2, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "direct packet access: test5 (pkt_end >= reg, good access)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_0, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "direct packet access: test6 (pkt_end >= reg, bad access)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_0, 3), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid access to packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "direct packet access: test7 (pkt_end >= reg, both accesses)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_0, 3), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid access to packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "direct packet access: test8 (double test, variant 1)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_0, 4), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "direct packet access: test9 (double test, variant 2)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_0, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "direct packet access: test10 (write invalid)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_STX_MEM(BPF_B, BPF_REG_2, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "invalid access to packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "helper access to packet: test1, valid packet_ptr range", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 5), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_2), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_update_elem), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 5 }, + .result_unpriv = ACCEPT, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "helper access to packet: test2, unchecked packet_ptr", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 1 }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "helper access to packet: test3, variable add", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 10), + BPF_LDX_MEM(BPF_B, BPF_REG_5, BPF_REG_2, 0), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_4, BPF_REG_5), + BPF_MOV64_REG(BPF_REG_5, BPF_REG_4), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_5, BPF_REG_3, 4), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_4), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 11 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "helper access to packet: test4, packet_ptr with bad range", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4), + BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 7 }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "helper access to packet: test5, packet_ptr with too short range", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 1), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 7), + BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 6 }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_XDP, + }, + { + "helper access to packet: test6, cls valid packet_ptr range", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 5), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_2), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_update_elem), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 5 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "helper access to packet: test7, cls unchecked packet_ptr", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 1 }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "helper access to packet: test8, cls variable add", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 10), + BPF_LDX_MEM(BPF_B, BPF_REG_5, BPF_REG_2, 0), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_4, BPF_REG_5), + BPF_MOV64_REG(BPF_REG_5, BPF_REG_4), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_5, BPF_REG_3, 4), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_4), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 11 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "helper access to packet: test9, cls packet_ptr with bad range", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4), + BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 7 }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "helper access to packet: test10, cls packet_ptr with too short range", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 1), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 7), + BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 6 }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "helper access to packet: test11, cls unsuitable helper 1", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 7), + BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_7, 4), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_4, 42), + BPF_MOV64_IMM(BPF_REG_5, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_store_bytes), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "helper access to the packet", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "helper access to packet: test12, cls unsuitable helper 2", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_7, 3), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_4, 4), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_load_bytes), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "helper access to the packet", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "helper access to packet: test13, cls helper ok", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_7, 6), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_MOV64_IMM(BPF_REG_5, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_csum_diff), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "helper access to packet: test14, cls helper fail sub", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_7, 6), + BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 4), + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_MOV64_IMM(BPF_REG_5, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_csum_diff), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "type=inv expected=fp", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "helper access to packet: test15, cls helper fail range 1", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_7, 6), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_2, 8), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_MOV64_IMM(BPF_REG_5, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_csum_diff), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "helper access to packet: test16, cls helper fail range 2", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_7, 6), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_2, -9), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_MOV64_IMM(BPF_REG_5, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_csum_diff), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "helper access to packet: test17, cls helper fail range 3", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_7, 6), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_2, ~0), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_MOV64_IMM(BPF_REG_5, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_csum_diff), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "helper access to packet: test18, cls helper fail range zero", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_7, 6), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_MOV64_IMM(BPF_REG_5, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_csum_diff), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "helper access to packet: test19, pkt end as input", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_7, 6), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_MOV64_IMM(BPF_REG_5, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_csum_diff), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "R1 type=pkt_end expected=fp", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "helper access to packet: test20, wrong reg", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_7, 6), + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_MOV64_IMM(BPF_REG_5, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_csum_diff), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "valid map access into an array with a constant", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, + offsetof(struct test_val, foo)), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr_unpriv = "R0 leaks addr", + .result_unpriv = REJECT, + .result = ACCEPT, + }, + { + "valid map access into an array with a register", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_IMM(BPF_REG_1, 4), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, + offsetof(struct test_val, foo)), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .result_unpriv = REJECT, + .result = ACCEPT, + }, + { + "valid map access into an array with a variable", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5), + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JGE, BPF_REG_1, MAX_ENTRIES, 3), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, + offsetof(struct test_val, foo)), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .result_unpriv = REJECT, + .result = ACCEPT, + }, + { + "valid map access into an array with a signed variable", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 0xffffffff, 1), + BPF_MOV32_IMM(BPF_REG_1, 0), + BPF_MOV32_IMM(BPF_REG_2, MAX_ENTRIES), + BPF_JMP_REG(BPF_JSGT, BPF_REG_2, BPF_REG_1, 1), + BPF_MOV32_IMM(BPF_REG_1, 0), + BPF_ALU32_IMM(BPF_LSH, BPF_REG_1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, + offsetof(struct test_val, foo)), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .result_unpriv = REJECT, + .result = ACCEPT, + }, + { + "invalid map access into an array with a constant", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_ST_MEM(BPF_DW, BPF_REG_0, (MAX_ENTRIES + 1) << 2, + offsetof(struct test_val, foo)), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr = "invalid access to map value, value_size=48 off=48 size=8", + .result = REJECT, + }, + { + "invalid map access into an array with a register", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_IMM(BPF_REG_1, MAX_ENTRIES + 1), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, + offsetof(struct test_val, foo)), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R0 min value is outside of the array range", + .result_unpriv = REJECT, + .result = REJECT, + }, + { + "invalid map access into an array with a variable", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, + offsetof(struct test_val, foo)), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.", + .result_unpriv = REJECT, + .result = REJECT, + }, + { + "invalid map access into an array with no floor check", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0), + BPF_MOV32_IMM(BPF_REG_2, MAX_ENTRIES), + BPF_JMP_REG(BPF_JSGT, BPF_REG_2, BPF_REG_1, 1), + BPF_MOV32_IMM(BPF_REG_1, 0), + BPF_ALU32_IMM(BPF_LSH, BPF_REG_1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, + offsetof(struct test_val, foo)), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.", + .result_unpriv = REJECT, + .result = REJECT, + }, + { + "invalid map access into an array with a invalid max check", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0), + BPF_MOV32_IMM(BPF_REG_2, MAX_ENTRIES + 1), + BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_1, 1), + BPF_MOV32_IMM(BPF_REG_1, 0), + BPF_ALU32_IMM(BPF_LSH, BPF_REG_1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, + offsetof(struct test_val, foo)), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "invalid access to map value, value_size=48 off=44 size=8", + .result_unpriv = REJECT, + .result = REJECT, + }, + { + "invalid map access into an array with a invalid max check", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 10), + BPF_MOV64_REG(BPF_REG_8, BPF_REG_0), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_8), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, + offsetof(struct test_val, foo)), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3, 11 }, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.", + .result_unpriv = REJECT, + .result = REJECT, + }, + { + "multiple registers share map_lookup_elem result", + .insns = { + BPF_MOV64_IMM(BPF_REG_1, 10), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_ST_MEM(BPF_DW, BPF_REG_4, 0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 4 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS + }, + { + "invalid memory access with multiple map_lookup_elem calls", + .insns = { + BPF_MOV64_IMM(BPF_REG_1, 10), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_MOV64_REG(BPF_REG_8, BPF_REG_1), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_2), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_8), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_7), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_ST_MEM(BPF_DW, BPF_REG_4, 0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 4 }, + .result = REJECT, + .errstr = "R4 !read_ok", + .prog_type = BPF_PROG_TYPE_SCHED_CLS + }, + { + "valid indirect map_lookup_elem access with 2nd lookup in branch", + .insns = { + BPF_MOV64_IMM(BPF_REG_1, 10), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_MOV64_REG(BPF_REG_8, BPF_REG_1), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_2), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_MOV64_IMM(BPF_REG_2, 10), + BPF_JMP_IMM(BPF_JNE, BPF_REG_2, 0, 3), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_8), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_7), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_MOV64_REG(BPF_REG_4, BPF_REG_0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_ST_MEM(BPF_DW, BPF_REG_4, 0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 4 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS + }, + { + "invalid map access from else condition", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JGE, BPF_REG_1, MAX_ENTRIES-1, 1), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 1), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, offsetof(struct test_val, foo)), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr = "R0 unbounded memory access, make sure to bounds check any array access into a map", + .result = REJECT, + .errstr_unpriv = "R0 pointer arithmetic prohibited", + .result_unpriv = REJECT, + }, + { + "constant register |= constant should keep constant type", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -48), + BPF_MOV64_IMM(BPF_REG_2, 34), + BPF_ALU64_IMM(BPF_OR, BPF_REG_2, 13), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "constant register |= constant should not bypass stack boundary checks", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -48), + BPF_MOV64_IMM(BPF_REG_2, 34), + BPF_ALU64_IMM(BPF_OR, BPF_REG_2, 24), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_EXIT_INSN(), + }, + .errstr = "invalid stack type R1 off=-48 access_size=58", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "constant register |= constant register should keep constant type", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -48), + BPF_MOV64_IMM(BPF_REG_2, 34), + BPF_MOV64_IMM(BPF_REG_4, 13), + BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_4), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "constant register |= constant register should not bypass stack boundary checks", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -48), + BPF_MOV64_IMM(BPF_REG_2, 34), + BPF_MOV64_IMM(BPF_REG_4, 24), + BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_4), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_probe_read), + BPF_EXIT_INSN(), + }, + .errstr = "invalid stack type R1 off=-48 access_size=58", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "invalid direct packet write for LWT_IN", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + BPF_STX_MEM(BPF_B, BPF_REG_2, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "cannot write into packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_LWT_IN, + }, + { + "invalid direct packet write for LWT_OUT", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + BPF_STX_MEM(BPF_B, BPF_REG_2, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "cannot write into packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_LWT_OUT, + }, + { + "direct packet write for LWT_XMIT", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + BPF_STX_MEM(BPF_B, BPF_REG_2, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_LWT_XMIT, + }, + { + "direct packet read for LWT_IN", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_LWT_IN, + }, + { + "direct packet read for LWT_OUT", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_LWT_OUT, + }, + { + "direct packet read for LWT_XMIT", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_LWT_XMIT, + }, + { + "invalid access of tc_classid for LWT_IN", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, tc_classid)), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid bpf_context access", + }, + { + "invalid access of tc_classid for LWT_OUT", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, tc_classid)), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid bpf_context access", + }, + { + "invalid access of tc_classid for LWT_XMIT", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, tc_classid)), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid bpf_context access", + }, +}; + +static int probe_filter_length(const struct bpf_insn *fp) +{ + int len; + + for (len = MAX_INSNS - 1; len > 0; --len) + if (fp[len].code != 0 || fp[len].imm != 0) + break; + return len + 1; +} + +static int create_map(uint32_t size_value, uint32_t max_elem) +{ + int fd; + + fd = bpf_map_create(BPF_MAP_TYPE_HASH, sizeof(long long), + size_value, max_elem, BPF_F_NO_PREALLOC); + if (fd < 0) + printf("Failed to create hash map '%s'!\n", strerror(errno)); + + return fd; +} + +static int create_prog_array(void) +{ + int fd; + + fd = bpf_map_create(BPF_MAP_TYPE_PROG_ARRAY, sizeof(int), + sizeof(int), 4, 0); + if (fd < 0) + printf("Failed to create prog array '%s'!\n", strerror(errno)); + + return fd; +} + +static char bpf_vlog[32768]; + +static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog, + int *fd_f1, int *fd_f2, int *fd_f3) +{ + int *fixup_map1 = test->fixup_map1; + int *fixup_map2 = test->fixup_map2; + int *fixup_prog = test->fixup_prog; + + /* Allocating HTs with 1 elem is fine here, since we only test + * for verifier and not do a runtime lookup, so the only thing + * that really matters is value size in this case. + */ + if (*fixup_map1) { + *fd_f1 = create_map(sizeof(long long), 1); + do { + prog[*fixup_map1].imm = *fd_f1; + fixup_map1++; + } while (*fixup_map1); + } + + if (*fixup_map2) { + *fd_f2 = create_map(sizeof(struct test_val), 1); + do { + prog[*fixup_map2].imm = *fd_f2; + fixup_map2++; + } while (*fixup_map2); + } + + if (*fixup_prog) { + *fd_f3 = create_prog_array(); + do { + prog[*fixup_prog].imm = *fd_f3; + fixup_prog++; + } while (*fixup_prog); + } +} + +static void do_test_single(struct bpf_test *test, bool unpriv, + int *passes, int *errors) +{ + struct bpf_insn *prog = test->insns; + int prog_len = probe_filter_length(prog); + int prog_type = test->prog_type; + int fd_f1 = -1, fd_f2 = -1, fd_f3 = -1; + int fd_prog, expected_ret; + const char *expected_err; + + do_test_fixup(test, prog, &fd_f1, &fd_f2, &fd_f3); + + fd_prog = bpf_prog_load(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER, + prog, prog_len * sizeof(struct bpf_insn), + "GPL", bpf_vlog, sizeof(bpf_vlog)); + + expected_ret = unpriv && test->result_unpriv != UNDEF ? + test->result_unpriv : test->result; + expected_err = unpriv && test->errstr_unpriv ? + test->errstr_unpriv : test->errstr; + if (expected_ret == ACCEPT) { + if (fd_prog < 0) { + printf("FAIL\nFailed to load prog '%s'!\n", + strerror(errno)); + goto fail_log; + } + } else { + if (fd_prog >= 0) { + printf("FAIL\nUnexpected success to load!\n"); + goto fail_log; + } + if (!strstr(bpf_vlog, expected_err)) { + printf("FAIL\nUnexpected error message!\n"); + goto fail_log; + } + } + + (*passes)++; + printf("OK\n"); +close_fds: + close(fd_prog); + close(fd_f1); + close(fd_f2); + close(fd_f3); + sched_yield(); + return; +fail_log: + (*errors)++; + printf("%s", bpf_vlog); + goto close_fds; +} + +static int do_test(bool unpriv, unsigned int from, unsigned int to) +{ + int i, passes = 0, errors = 0; + + for (i = from; i < to; i++) { + struct bpf_test *test = &tests[i]; + + /* Program types that are not supported by non-root we + * skip right away. + */ + if (unpriv && test->prog_type) + continue; + + printf("#%d %s ", i, test->descr); + do_test_single(test, unpriv, &passes, &errors); + } + + printf("Summary: %d PASSED, %d FAILED\n", passes, errors); + return errors ? -errors : 0; +} + +int main(int argc, char **argv) +{ + struct rlimit rinf = { RLIM_INFINITY, RLIM_INFINITY }; + struct rlimit rlim = { 1 << 20, 1 << 20 }; + unsigned int from = 0, to = ARRAY_SIZE(tests); + bool unpriv = geteuid() != 0; + + if (argc == 3) { + unsigned int l = atoi(argv[argc - 2]); + unsigned int u = atoi(argv[argc - 1]); + + if (l < to && u < to) { + from = l; + to = u + 1; + } + } else if (argc == 2) { + unsigned int t = atoi(argv[argc - 1]); + + if (t < to) { + from = t; + to = t + 1; + } + } + + setrlimit(RLIMIT_MEMLOCK, unpriv ? &rlim : &rinf); + return do_test(unpriv, from, to); +} diff --git a/tools/testing/selftests/breakpoints/Makefile b/tools/testing/selftests/breakpoints/Makefile index 74e533fd4bc5..61b79e8df1f4 100644 --- a/tools/testing/selftests/breakpoints/Makefile +++ b/tools/testing/selftests/breakpoints/Makefile @@ -5,6 +5,9 @@ ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/) ifeq ($(ARCH),x86) TEST_PROGS := breakpoint_test endif +ifeq ($(ARCH),aarch64) +TEST_PROGS := breakpoint_test_arm64 +endif TEST_PROGS += step_after_suspend_test @@ -13,4 +16,4 @@ all: $(TEST_PROGS) include ../lib.mk clean: - rm -fr breakpoint_test step_after_suspend_test + rm -fr breakpoint_test breakpoint_test_arm64 step_after_suspend_test diff --git a/tools/testing/selftests/breakpoints/breakpoint_test_arm64.c b/tools/testing/selftests/breakpoints/breakpoint_test_arm64.c new file mode 100644 index 000000000000..3897e996541e --- /dev/null +++ b/tools/testing/selftests/breakpoints/breakpoint_test_arm64.c @@ -0,0 +1,236 @@ +/* + * Copyright (C) 2016 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Original Code by Pavel Labath <labath@google.com> + * + * Code modified by Pratyush Anand <panand@redhat.com> + * for testing different byte select for each access size. + * + */ + +#define _GNU_SOURCE + +#include <sys/types.h> +#include <sys/wait.h> +#include <sys/ptrace.h> +#include <sys/param.h> +#include <sys/uio.h> +#include <stdint.h> +#include <stdbool.h> +#include <stddef.h> +#include <string.h> +#include <stdio.h> +#include <unistd.h> +#include <elf.h> +#include <errno.h> +#include <signal.h> + +#include "../kselftest.h" + +static volatile uint8_t var[96] __attribute__((__aligned__(32))); + +static void child(int size, int wr) +{ + volatile uint8_t *addr = &var[32 + wr]; + + if (ptrace(PTRACE_TRACEME, 0, NULL, NULL) != 0) { + perror("ptrace(PTRACE_TRACEME) failed"); + _exit(1); + } + + if (raise(SIGSTOP) != 0) { + perror("raise(SIGSTOP) failed"); + _exit(1); + } + + if ((uintptr_t) addr % size) { + perror("Wrong address write for the given size\n"); + _exit(1); + } + switch (size) { + case 1: + *addr = 47; + break; + case 2: + *(uint16_t *)addr = 47; + break; + case 4: + *(uint32_t *)addr = 47; + break; + case 8: + *(uint64_t *)addr = 47; + break; + case 16: + __asm__ volatile ("stp x29, x30, %0" : "=m" (addr[0])); + break; + case 32: + __asm__ volatile ("stp q29, q30, %0" : "=m" (addr[0])); + break; + } + + _exit(0); +} + +static bool set_watchpoint(pid_t pid, int size, int wp) +{ + const volatile uint8_t *addr = &var[32 + wp]; + const int offset = (uintptr_t)addr % 8; + const unsigned int byte_mask = ((1 << size) - 1) << offset; + const unsigned int type = 2; /* Write */ + const unsigned int enable = 1; + const unsigned int control = byte_mask << 5 | type << 3 | enable; + struct user_hwdebug_state dreg_state; + struct iovec iov; + + memset(&dreg_state, 0, sizeof(dreg_state)); + dreg_state.dbg_regs[0].addr = (uintptr_t)(addr - offset); + dreg_state.dbg_regs[0].ctrl = control; + iov.iov_base = &dreg_state; + iov.iov_len = offsetof(struct user_hwdebug_state, dbg_regs) + + sizeof(dreg_state.dbg_regs[0]); + if (ptrace(PTRACE_SETREGSET, pid, NT_ARM_HW_WATCH, &iov) == 0) + return true; + + if (errno == EIO) { + printf("ptrace(PTRACE_SETREGSET, NT_ARM_HW_WATCH) " + "not supported on this hardware\n"); + ksft_exit_skip(); + } + perror("ptrace(PTRACE_SETREGSET, NT_ARM_HW_WATCH) failed"); + return false; +} + +static bool run_test(int wr_size, int wp_size, int wr, int wp) +{ + int status; + siginfo_t siginfo; + pid_t pid = fork(); + pid_t wpid; + + if (pid < 0) { + perror("fork() failed"); + return false; + } + if (pid == 0) + child(wr_size, wr); + + wpid = waitpid(pid, &status, __WALL); + if (wpid != pid) { + perror("waitpid() failed"); + return false; + } + if (!WIFSTOPPED(status)) { + printf("child did not stop\n"); + return false; + } + if (WSTOPSIG(status) != SIGSTOP) { + printf("child did not stop with SIGSTOP\n"); + return false; + } + + if (!set_watchpoint(pid, wp_size, wp)) + return false; + + if (ptrace(PTRACE_CONT, pid, NULL, NULL) < 0) { + perror("ptrace(PTRACE_SINGLESTEP) failed"); + return false; + } + + alarm(3); + wpid = waitpid(pid, &status, __WALL); + if (wpid != pid) { + perror("waitpid() failed"); + return false; + } + alarm(0); + if (WIFEXITED(status)) { + printf("child did not single-step\t"); + return false; + } + if (!WIFSTOPPED(status)) { + printf("child did not stop\n"); + return false; + } + if (WSTOPSIG(status) != SIGTRAP) { + printf("child did not stop with SIGTRAP\n"); + return false; + } + if (ptrace(PTRACE_GETSIGINFO, pid, NULL, &siginfo) != 0) { + perror("ptrace(PTRACE_GETSIGINFO)"); + return false; + } + if (siginfo.si_code != TRAP_HWBKPT) { + printf("Unexpected si_code %d\n", siginfo.si_code); + return false; + } + + kill(pid, SIGKILL); + wpid = waitpid(pid, &status, 0); + if (wpid != pid) { + perror("waitpid() failed"); + return false; + } + return true; +} + +static void sigalrm(int sig) +{ +} + +int main(int argc, char **argv) +{ + int opt; + bool succeeded = true; + struct sigaction act; + int wr, wp, size; + bool result; + + act.sa_handler = sigalrm; + sigemptyset(&act.sa_mask); + act.sa_flags = 0; + sigaction(SIGALRM, &act, NULL); + for (size = 1; size <= 32; size = size*2) { + for (wr = 0; wr <= 32; wr = wr + size) { + for (wp = wr - size; wp <= wr + size; wp = wp + size) { + printf("Test size = %d write offset = %d watchpoint offset = %d\t", size, wr, wp); + result = run_test(size, MIN(size, 8), wr, wp); + if ((result && wr == wp) || (!result && wr != wp)) { + printf("[OK]\n"); + ksft_inc_pass_cnt(); + } else { + printf("[FAILED]\n"); + ksft_inc_fail_cnt(); + succeeded = false; + } + } + } + } + + for (size = 1; size <= 32; size = size*2) { + printf("Test size = %d write offset = %d watchpoint offset = -8\t", size, -size); + + if (run_test(size, 8, -size, -8)) { + printf("[OK]\n"); + ksft_inc_pass_cnt(); + } else { + printf("[FAILED]\n"); + ksft_inc_fail_cnt(); + succeeded = false; + } + } + + ksft_print_cnts(); + if (succeeded) + ksft_exit_pass(); + else + ksft_exit_fail(); +} diff --git a/tools/testing/selftests/ftrace/.gitignore b/tools/testing/selftests/ftrace/.gitignore new file mode 100644 index 000000000000..98d8a5a63049 --- /dev/null +++ b/tools/testing/selftests/ftrace/.gitignore @@ -0,0 +1 @@ +logs diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest index 4c6a0bf8ba79..52e3c4df28d6 100755 --- a/tools/testing/selftests/ftrace/ftracetest +++ b/tools/testing/selftests/ftrace/ftracetest @@ -13,7 +13,8 @@ echo "Usage: ftracetest [options] [testcase(s)] [testcase-directory(s)]" echo " Options:" echo " -h|--help Show help message" echo " -k|--keep Keep passed test logs" -echo " -v|--verbose Show all stdout messages in testcases" +echo " -v|--verbose Increase verbosity of test messages" +echo " -vv Alias of -v -v (Show all results in stdout)" echo " -d|--debug Debug mode (trace all shell commands)" exit $1 } @@ -54,8 +55,9 @@ parse_opts() { # opts KEEP_LOG=1 shift 1 ;; - --verbose|-v) - VERBOSE=1 + --verbose|-v|-vv) + VERBOSE=$((VERBOSE + 1)) + [ $1 == '-vv' ] && VERBOSE=$((VERBOSE + 1)) shift 1 ;; --debug|-d) @@ -228,7 +230,7 @@ trap 'SIG_RESULT=$XFAIL' $SIG_XFAIL __run_test() { # testfile # setup PID and PPID, $$ is not updated. - (cd $TRACING_DIR; read PID _ < /proc/self/stat ; set -e; set -x; . $1) + (cd $TRACING_DIR; read PID _ < /proc/self/stat; set -e; set -x; initialize_ftrace; . $1) [ $? -ne 0 ] && kill -s $SIG_FAIL $SIG_PID } @@ -236,10 +238,11 @@ __run_test() { # testfile run_test() { # testfile local testname=`basename $1` local testlog=`mktemp $LOG_DIR/${testname}-log.XXXXXX` + export TMPDIR=`mktemp -d /tmp/ftracetest-dir.XXXXXX` testcase $1 echo "execute: "$1 > $testlog SIG_RESULT=0 - if [ $VERBOSE -ne 0 ]; then + if [ $VERBOSE -ge 2 ]; then __run_test $1 2>> $testlog | tee -a $testlog else __run_test $1 >> $testlog 2>&1 @@ -249,9 +252,10 @@ run_test() { # testfile # Remove test log if the test was done as it was expected. [ $KEEP_LOG -eq 0 ] && rm $testlog else - catlog $testlog + [ $VERBOSE -ge 1 ] && catlog $testlog TOTAL_RESULT=1 fi + rm -rf $TMPDIR } # load in the helper functions diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc new file mode 100644 index 000000000000..9dcd0ca1f49c --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc @@ -0,0 +1,49 @@ +#!/bin/sh +# description: ftrace - function glob filters + +# Make sure that function glob matching filter works. + +if ! grep -q function available_tracers; then + echo "no function tracer configured" + exit_unsupported +fi + +disable_tracing +clear_trace + +# filter by ?, schedule is always good +if ! echo "sch?dule" > set_ftrace_filter; then + # test for powerpc 64 + if ! echo ".sch?dule" > set_ftrace_filter; then + fail "can not enable schedule filter" + fi + cat set_ftrace_filter | grep '^.schedule$' +else + cat set_ftrace_filter | grep '^schedule$' +fi + +ftrace_filter_check() { # glob grep + echo "$1" > set_ftrace_filter + cut -f1 -d" " set_ftrace_filter > $TMPDIR/actual + cut -f1 -d" " available_filter_functions | grep "$2" > $TMPDIR/expected + DIFF=`diff $TMPDIR/actual $TMPDIR/expected` + test -z "$DIFF" +} + +# filter by *, front match +ftrace_filter_check '*schedule' '^.*schedule$' + +# filter by *, middle match +ftrace_filter_check '*schedule*' '^.*schedule.*$' + +# filter by *, end match +ftrace_filter_check 'schedule*' '^schedule.*$' + +# filter by *, both side match +ftrace_filter_check 'sch*ule' '^sch.*ule$' + +# filter by char class. +ftrace_filter_check '[Ss]y[Ss]_*' '^[Ss]y[Ss]_.*$' + +echo > set_ftrace_filter +enable_tracing diff --git a/tools/testing/selftests/ftrace/test.d/functions b/tools/testing/selftests/ftrace/test.d/functions index c37262f6c269..91de1a8e4f19 100644 --- a/tools/testing/selftests/ftrace/test.d/functions +++ b/tools/testing/selftests/ftrace/test.d/functions @@ -23,3 +23,31 @@ reset_trigger() { # reset all current setting triggers done } +reset_events_filter() { # reset all current setting filters + grep -v ^none events/*/*/filter | + while read line; do + echo 0 > `echo $line | cut -f1 -d:` + done +} + +disable_events() { + echo 0 > events/enable +} + +initialize_ftrace() { # Reset ftrace to initial-state +# As the initial state, ftrace will be set to nop tracer, +# no events, no triggers, no filters, no function filters, +# no probes, and tracing on. + disable_tracing + reset_tracer + reset_trigger + reset_events_filter + disable_events + echo > set_event_pid # event tracer is always on + [ -f set_ftrace_filter ] && echo | tee set_ftrace_* + [ -f set_graph_function ] && echo | tee set_graph_* + [ -f stack_trace_filter ] && echo > stack_trace_filter + [ -f kprobe_events ] && echo > kprobe_events + [ -f uprobe_events ] && echo > uprobe_events + enable_tracing +} diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc new file mode 100644 index 000000000000..0a78705b43b2 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_type.tc @@ -0,0 +1,37 @@ +#!/bin/sh +# description: Kprobes event arguments with types + +[ -f kprobe_events ] || exit_unsupported # this is configurable + +grep "x8/16/32/64" README > /dev/null || exit_unsupported # version issue + +echo 0 > events/enable +echo > kprobe_events +enable_tracing + +echo 'p:testprobe _do_fork $stack0:s32 $stack0:u32 $stack0:x32 $stack0:b8@4/32' > kprobe_events +grep testprobe kprobe_events +test -d events/kprobes/testprobe + +echo 1 > events/kprobes/testprobe/enable +( echo "forked") +echo 0 > events/kprobes/testprobe/enable +ARGS=`tail -n 1 trace | sed -e 's/.* arg1=\(.*\) arg2=\(.*\) arg3=\(.*\) arg4=\(.*\)/\1 \2 \3 \4/'` + +check_types() { + X1=`printf "%x" $1 | tail -c 8` + X2=`printf "%x" $2` + X3=`printf "%x" $3` + test $X1 = $X2 + test $X2 = $X3 + test 0x$X3 = $3 + + B4=`printf "%x" $4` + B3=`echo -n $X3 | tail -c 3 | head -c 2` + test $B3 = $B4 +} +check_types $ARGS + +echo "-:testprobe" >> kprobe_events +clear_trace +test -d events/kprobes/testprobe && exit 1 || exit 0 diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc index 0bf5085281f3..400e98b64948 100644 --- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc +++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-mod.tc @@ -56,7 +56,7 @@ echo "Test histogram with syscall modifier" echo 'hist:keys=id.syscall' > events/raw_syscalls/sys_exit/trigger for i in `seq 1 10` ; do ( echo "forked" > /dev/null); done -grep "id: sys_" events/raw_syscalls/sys_exit/hist > /dev/null || \ +grep "id: \(unknown_\|sys_\)" events/raw_syscalls/sys_exit/hist > /dev/null || \ fail "syscall modifier on raw_syscalls/sys_exit did not work" diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-snapshot.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-snapshot.tc index f84b80d551a2..ed94f0c4e0e4 100644 --- a/tools/testing/selftests/ftrace/test.d/trigger/trigger-snapshot.tc +++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-snapshot.tc @@ -23,6 +23,11 @@ if [ ! -f events/sched/sched_process_fork/trigger ]; then exit_unsupported fi +if [ ! -f snapshot ]; then + echo "snapshot is not supported" + exit_unsupported +fi + reset_tracer do_reset diff --git a/tools/testing/selftests/futex/README b/tools/testing/selftests/futex/README index 0558bb9ce0a6..f3926c33ed4c 100644 --- a/tools/testing/selftests/futex/README +++ b/tools/testing/selftests/futex/README @@ -59,4 +59,4 @@ o FIXME: decide on a sane test naming scheme. Currently the tests are named Coding Style ------------ o The Futex Test project adheres to the coding standards set forth by Linux - kernel as defined in the Linux source Documentation/CodingStyle. + kernel as defined in the Linux source Documentation/process/coding-style.rst. diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 0840684deb7d..afe109e5508a 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -3,4 +3,5 @@ psock_fanout psock_tpacket reuseport_bpf reuseport_bpf_cpu +reuseport_bpf_numa reuseport_dualstack diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 0e5340742620..e24e4c82542e 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -1,14 +1,17 @@ # Makefile for net selftests -CFLAGS = -Wall -O2 -g - +CFLAGS = -Wall -Wl,--no-as-needed -O2 -g CFLAGS += -I../../../../usr/include/ -NET_PROGS = socket psock_fanout psock_tpacket reuseport_bpf reuseport_bpf_cpu reuseport_dualstack +NET_PROGS = socket +NET_PROGS += psock_fanout psock_tpacket +NET_PROGS += reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa +NET_PROGS += reuseport_dualstack all: $(NET_PROGS) +reuseport_bpf_numa: LDFLAGS += -lnuma %: %.c - $(CC) $(CFLAGS) -o $@ $^ + $(CC) $(CFLAGS) $(LDFLAGS) -o $@ $^ TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh TEST_FILES := $(NET_PROGS) diff --git a/tools/testing/selftests/net/reuseport_bpf_numa.c b/tools/testing/selftests/net/reuseport_bpf_numa.c new file mode 100644 index 000000000000..6f20bc9ff627 --- /dev/null +++ b/tools/testing/selftests/net/reuseport_bpf_numa.c @@ -0,0 +1,255 @@ +/* + * Test functionality of BPF filters with SO_REUSEPORT. Same test as + * in reuseport_bpf_cpu, only as one socket per NUMA node. + */ + +#define _GNU_SOURCE + +#include <arpa/inet.h> +#include <errno.h> +#include <error.h> +#include <linux/filter.h> +#include <linux/bpf.h> +#include <linux/in.h> +#include <linux/unistd.h> +#include <sched.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/epoll.h> +#include <sys/types.h> +#include <sys/socket.h> +#include <unistd.h> +#include <numa.h> + +static const int PORT = 8888; + +static void build_rcv_group(int *rcv_fd, size_t len, int family, int proto) +{ + struct sockaddr_storage addr; + struct sockaddr_in *addr4; + struct sockaddr_in6 *addr6; + size_t i; + int opt; + + switch (family) { + case AF_INET: + addr4 = (struct sockaddr_in *)&addr; + addr4->sin_family = AF_INET; + addr4->sin_addr.s_addr = htonl(INADDR_ANY); + addr4->sin_port = htons(PORT); + break; + case AF_INET6: + addr6 = (struct sockaddr_in6 *)&addr; + addr6->sin6_family = AF_INET6; + addr6->sin6_addr = in6addr_any; + addr6->sin6_port = htons(PORT); + break; + default: + error(1, 0, "Unsupported family %d", family); + } + + for (i = 0; i < len; ++i) { + rcv_fd[i] = socket(family, proto, 0); + if (rcv_fd[i] < 0) + error(1, errno, "failed to create receive socket"); + + opt = 1; + if (setsockopt(rcv_fd[i], SOL_SOCKET, SO_REUSEPORT, &opt, + sizeof(opt))) + error(1, errno, "failed to set SO_REUSEPORT"); + + if (bind(rcv_fd[i], (struct sockaddr *)&addr, sizeof(addr))) + error(1, errno, "failed to bind receive socket"); + + if (proto == SOCK_STREAM && listen(rcv_fd[i], len * 10)) + error(1, errno, "failed to listen on receive port"); + } +} + +static void attach_bpf(int fd) +{ + static char bpf_log_buf[65536]; + static const char bpf_license[] = ""; + + int bpf_fd; + const struct bpf_insn prog[] = { + /* R0 = bpf_get_numa_node_id() */ + { BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_numa_node_id }, + /* return R0 */ + { BPF_JMP | BPF_EXIT, 0, 0, 0, 0 } + }; + union bpf_attr attr; + + memset(&attr, 0, sizeof(attr)); + attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; + attr.insn_cnt = sizeof(prog) / sizeof(prog[0]); + attr.insns = (unsigned long) &prog; + attr.license = (unsigned long) &bpf_license; + attr.log_buf = (unsigned long) &bpf_log_buf; + attr.log_size = sizeof(bpf_log_buf); + attr.log_level = 1; + + bpf_fd = syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr)); + if (bpf_fd < 0) + error(1, errno, "ebpf error. log:\n%s\n", bpf_log_buf); + + if (setsockopt(fd, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, &bpf_fd, + sizeof(bpf_fd))) + error(1, errno, "failed to set SO_ATTACH_REUSEPORT_EBPF"); + + close(bpf_fd); +} + +static void send_from_node(int node_id, int family, int proto) +{ + struct sockaddr_storage saddr, daddr; + struct sockaddr_in *saddr4, *daddr4; + struct sockaddr_in6 *saddr6, *daddr6; + int fd; + + switch (family) { + case AF_INET: + saddr4 = (struct sockaddr_in *)&saddr; + saddr4->sin_family = AF_INET; + saddr4->sin_addr.s_addr = htonl(INADDR_ANY); + saddr4->sin_port = 0; + + daddr4 = (struct sockaddr_in *)&daddr; + daddr4->sin_family = AF_INET; + daddr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK); + daddr4->sin_port = htons(PORT); + break; + case AF_INET6: + saddr6 = (struct sockaddr_in6 *)&saddr; + saddr6->sin6_family = AF_INET6; + saddr6->sin6_addr = in6addr_any; + saddr6->sin6_port = 0; + + daddr6 = (struct sockaddr_in6 *)&daddr; + daddr6->sin6_family = AF_INET6; + daddr6->sin6_addr = in6addr_loopback; + daddr6->sin6_port = htons(PORT); + break; + default: + error(1, 0, "Unsupported family %d", family); + } + + if (numa_run_on_node(node_id) < 0) + error(1, errno, "failed to pin to node"); + + fd = socket(family, proto, 0); + if (fd < 0) + error(1, errno, "failed to create send socket"); + + if (bind(fd, (struct sockaddr *)&saddr, sizeof(saddr))) + error(1, errno, "failed to bind send socket"); + + if (connect(fd, (struct sockaddr *)&daddr, sizeof(daddr))) + error(1, errno, "failed to connect send socket"); + + if (send(fd, "a", 1, 0) < 0) + error(1, errno, "failed to send message"); + + close(fd); +} + +static +void receive_on_node(int *rcv_fd, int len, int epfd, int node_id, int proto) +{ + struct epoll_event ev; + int i, fd; + char buf[8]; + + i = epoll_wait(epfd, &ev, 1, -1); + if (i < 0) + error(1, errno, "epoll_wait failed"); + + if (proto == SOCK_STREAM) { + fd = accept(ev.data.fd, NULL, NULL); + if (fd < 0) + error(1, errno, "failed to accept"); + i = recv(fd, buf, sizeof(buf), 0); + close(fd); + } else { + i = recv(ev.data.fd, buf, sizeof(buf), 0); + } + + if (i < 0) + error(1, errno, "failed to recv"); + + for (i = 0; i < len; ++i) + if (ev.data.fd == rcv_fd[i]) + break; + if (i == len) + error(1, 0, "failed to find socket"); + fprintf(stderr, "send node %d, receive socket %d\n", node_id, i); + if (node_id != i) + error(1, 0, "node id/receive socket mismatch"); +} + +static void test(int *rcv_fd, int len, int family, int proto) +{ + struct epoll_event ev; + int epfd, node; + + build_rcv_group(rcv_fd, len, family, proto); + attach_bpf(rcv_fd[0]); + + epfd = epoll_create(1); + if (epfd < 0) + error(1, errno, "failed to create epoll"); + for (node = 0; node < len; ++node) { + ev.events = EPOLLIN; + ev.data.fd = rcv_fd[node]; + if (epoll_ctl(epfd, EPOLL_CTL_ADD, rcv_fd[node], &ev)) + error(1, errno, "failed to register sock epoll"); + } + + /* Forward iterate */ + for (node = 0; node < len; ++node) { + send_from_node(node, family, proto); + receive_on_node(rcv_fd, len, epfd, node, proto); + } + + /* Reverse iterate */ + for (node = len - 1; node >= 0; --node) { + send_from_node(node, family, proto); + receive_on_node(rcv_fd, len, epfd, node, proto); + } + + close(epfd); + for (node = 0; node < len; ++node) + close(rcv_fd[node]); +} + +int main(void) +{ + int *rcv_fd, nodes; + + if (numa_available() < 0) + error(1, errno, "no numa api support"); + + nodes = numa_max_node() + 1; + + rcv_fd = calloc(nodes, sizeof(int)); + if (!rcv_fd) + error(1, 0, "failed to allocate array"); + + fprintf(stderr, "---- IPv4 UDP ----\n"); + test(rcv_fd, nodes, AF_INET, SOCK_DGRAM); + + fprintf(stderr, "---- IPv6 UDP ----\n"); + test(rcv_fd, nodes, AF_INET6, SOCK_DGRAM); + + fprintf(stderr, "---- IPv4 TCP ----\n"); + test(rcv_fd, nodes, AF_INET, SOCK_STREAM); + + fprintf(stderr, "---- IPv6 TCP ----\n"); + test(rcv_fd, nodes, AF_INET6, SOCK_STREAM); + + free(rcv_fd); + + fprintf(stderr, "SUCCESS\n"); + return 0; +} diff --git a/tools/testing/selftests/rcutorture/.gitignore b/tools/testing/selftests/rcutorture/.gitignore index 05838f6f2ebe..ccc240275d1c 100644 --- a/tools/testing/selftests/rcutorture/.gitignore +++ b/tools/testing/selftests/rcutorture/.gitignore @@ -1,6 +1,4 @@ initrd -linux-2.6 b[0-9]* -rcu-test-image res *.swp diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh index 0aed965f0062..3b3c1b693ee1 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm.sh @@ -303,6 +303,7 @@ then fi ___EOF___ awk < $T/cfgcpu.pack \ + -v TORTURE_BUILDONLY="$TORTURE_BUILDONLY" \ -v CONFIGDIR="$CONFIGFRAG/" \ -v KVM="$KVM" \ -v ncpus=$cpus \ @@ -375,6 +376,10 @@ function dump(first, pastlast, batchnum) njitter = ncpus; else njitter = ja[1]; + if (TORTURE_BUILDONLY && njitter != 0) { + njitter = 0; + print "echo Build-only run, so suppressing jitter >> " rd "/log" + } for (j = 0; j < njitter; j++) print "jitter.sh " j " " dur " " ja[2] " " ja[3] "&" print "wait" diff --git a/tools/testing/selftests/timers/skew_consistency.c b/tools/testing/selftests/timers/skew_consistency.c index 5562f84ee07c..2a996e072259 100644 --- a/tools/testing/selftests/timers/skew_consistency.c +++ b/tools/testing/selftests/timers/skew_consistency.c @@ -57,7 +57,7 @@ int main(int argv, char **argc) pid_t pid; - printf("Running Asyncrhonous Frequency Changing Tests...\n"); + printf("Running Asynchronous Frequency Changing Tests...\n"); pid = fork(); if (!pid) diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index a89f80a5b711..8c1cb423cfe6 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -6,7 +6,7 @@ include ../lib.mk TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_syscall test_mremap_vdso \ check_initial_reg_state sigreturn ldt_gdt iopl \ - protection_keys + protection_keys test_vdso TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault test_syscall_vdso unwind_vdso \ test_FCMOV test_FCOMI test_FISTTP \ vdso_restorer diff --git a/tools/testing/selftests/x86/test_vdso.c b/tools/testing/selftests/x86/test_vdso.c new file mode 100644 index 000000000000..65d7a2bf7e14 --- /dev/null +++ b/tools/testing/selftests/x86/test_vdso.c @@ -0,0 +1,123 @@ +/* + * ldt_gdt.c - Test cases for LDT and GDT access + * Copyright (c) 2011-2015 Andrew Lutomirski + */ + +#define _GNU_SOURCE + +#include <stdio.h> +#include <sys/time.h> +#include <time.h> +#include <stdlib.h> +#include <unistd.h> +#include <sys/syscall.h> +#include <dlfcn.h> +#include <string.h> +#include <errno.h> +#include <sched.h> +#include <stdbool.h> + +#ifndef SYS_getcpu +# ifdef __x86_64__ +# define SYS_getcpu 309 +# else +# define SYS_getcpu 318 +# endif +#endif + +int nerrs = 0; + +#ifdef __x86_64__ +# define VSYS(x) (x) +#else +# define VSYS(x) 0 +#endif + +typedef long (*getcpu_t)(unsigned *, unsigned *, void *); + +const getcpu_t vgetcpu = (getcpu_t)VSYS(0xffffffffff600800); +getcpu_t vdso_getcpu; + +void fill_function_pointers() +{ + void *vdso = dlopen("linux-vdso.so.1", + RTLD_LAZY | RTLD_LOCAL | RTLD_NOLOAD); + if (!vdso) + vdso = dlopen("linux-gate.so.1", + RTLD_LAZY | RTLD_LOCAL | RTLD_NOLOAD); + if (!vdso) { + printf("[WARN]\tfailed to find vDSO\n"); + return; + } + + vdso_getcpu = (getcpu_t)dlsym(vdso, "__vdso_getcpu"); + if (!vdso_getcpu) + printf("Warning: failed to find getcpu in vDSO\n"); +} + +static long sys_getcpu(unsigned * cpu, unsigned * node, + void* cache) +{ + return syscall(__NR_getcpu, cpu, node, cache); +} + +static void test_getcpu(void) +{ + printf("[RUN]\tTesting getcpu...\n"); + + for (int cpu = 0; ; cpu++) { + cpu_set_t cpuset; + CPU_ZERO(&cpuset); + CPU_SET(cpu, &cpuset); + if (sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0) + return; + + unsigned cpu_sys, cpu_vdso, cpu_vsys, + node_sys, node_vdso, node_vsys; + long ret_sys, ret_vdso = 1, ret_vsys = 1; + unsigned node; + + ret_sys = sys_getcpu(&cpu_sys, &node_sys, 0); + if (vdso_getcpu) + ret_vdso = vdso_getcpu(&cpu_vdso, &node_vdso, 0); + if (vgetcpu) + ret_vsys = vgetcpu(&cpu_vsys, &node_vsys, 0); + + if (!ret_sys) + node = node_sys; + else if (!ret_vdso) + node = node_vdso; + else if (!ret_vsys) + node = node_vsys; + + bool ok = true; + if (!ret_sys && (cpu_sys != cpu || node_sys != node)) + ok = false; + if (!ret_vdso && (cpu_vdso != cpu || node_vdso != node)) + ok = false; + if (!ret_vsys && (cpu_vsys != cpu || node_vsys != node)) + ok = false; + + printf("[%s]\tCPU %u:", ok ? "OK" : "FAIL", cpu); + if (!ret_sys) + printf(" syscall: cpu %u, node %u", cpu_sys, node_sys); + if (!ret_vdso) + printf(" vdso: cpu %u, node %u", cpu_vdso, node_vdso); + if (!ret_vsys) + printf(" vsyscall: cpu %u, node %u", cpu_vsys, + node_vsys); + printf("\n"); + + if (!ok) + nerrs++; + } +} + +int main(int argc, char **argv) +{ + fill_function_pointers(); + + test_getcpu(); + + return nerrs ? 1 : 0; +} |