diff options
Diffstat (limited to 'tools/testing')
26 files changed, 2660 insertions, 143 deletions
diff --git a/tools/testing/nvdimm/Kbuild b/tools/testing/nvdimm/Kbuild index ad6dd0543019..582db95127ed 100644 --- a/tools/testing/nvdimm/Kbuild +++ b/tools/testing/nvdimm/Kbuild @@ -13,6 +13,7 @@ ldflags-y += --wrap=__release_region ldflags-y += --wrap=devm_memremap_pages ldflags-y += --wrap=insert_resource ldflags-y += --wrap=remove_resource +ldflags-y += --wrap=acpi_evaluate_object DRIVERS := ../../../drivers NVDIMM_SRC := $(DRIVERS)/nvdimm diff --git a/tools/testing/nvdimm/config_check.c b/tools/testing/nvdimm/config_check.c index 878daf3429e8..7dc5a0af9b54 100644 --- a/tools/testing/nvdimm/config_check.c +++ b/tools/testing/nvdimm/config_check.c @@ -1,4 +1,3 @@ -#include <linux/kconfig.h> #include <linux/bug.h> void check(void) diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c index c29f8dca9e67..3ccef732fce9 100644 --- a/tools/testing/nvdimm/test/iomap.c +++ b/tools/testing/nvdimm/test/iomap.c @@ -17,6 +17,7 @@ #include <linux/module.h> #include <linux/types.h> #include <linux/pfn_t.h> +#include <linux/acpi.h> #include <linux/io.h> #include <linux/mm.h> #include "nfit_test.h" @@ -73,7 +74,7 @@ void __iomem *__nfit_test_ioremap(resource_size_t offset, unsigned long size, if (nfit_res) return (void __iomem *) nfit_res->buf + offset - - nfit_res->res->start; + - nfit_res->res.start; return fallback_fn(offset, size); } @@ -84,7 +85,7 @@ void __iomem *__wrap_devm_ioremap_nocache(struct device *dev, if (nfit_res) return (void __iomem *) nfit_res->buf + offset - - nfit_res->res->start; + - nfit_res->res.start; return devm_ioremap_nocache(dev, offset, size); } EXPORT_SYMBOL(__wrap_devm_ioremap_nocache); @@ -95,7 +96,7 @@ void *__wrap_devm_memremap(struct device *dev, resource_size_t offset, struct nfit_test_resource *nfit_res = get_nfit_res(offset); if (nfit_res) - return nfit_res->buf + offset - nfit_res->res->start; + return nfit_res->buf + offset - nfit_res->res.start; return devm_memremap(dev, offset, size, flags); } EXPORT_SYMBOL(__wrap_devm_memremap); @@ -107,7 +108,7 @@ void *__wrap_devm_memremap_pages(struct device *dev, struct resource *res, struct nfit_test_resource *nfit_res = get_nfit_res(offset); if (nfit_res) - return nfit_res->buf + offset - nfit_res->res->start; + return nfit_res->buf + offset - nfit_res->res.start; return devm_memremap_pages(dev, res, ref, altmap); } EXPORT_SYMBOL(__wrap_devm_memremap_pages); @@ -128,7 +129,7 @@ void *__wrap_memremap(resource_size_t offset, size_t size, struct nfit_test_resource *nfit_res = get_nfit_res(offset); if (nfit_res) - return nfit_res->buf + offset - nfit_res->res->start; + return nfit_res->buf + offset - nfit_res->res.start; return memremap(offset, size, flags); } EXPORT_SYMBOL(__wrap_memremap); @@ -174,6 +175,63 @@ void __wrap_memunmap(void *addr) } EXPORT_SYMBOL(__wrap_memunmap); +static bool nfit_test_release_region(struct device *dev, + struct resource *parent, resource_size_t start, + resource_size_t n); + +static void nfit_devres_release(struct device *dev, void *data) +{ + struct resource *res = *((struct resource **) data); + + WARN_ON(!nfit_test_release_region(NULL, &iomem_resource, res->start, + resource_size(res))); +} + +static int match(struct device *dev, void *__res, void *match_data) +{ + struct resource *res = *((struct resource **) __res); + resource_size_t start = *((resource_size_t *) match_data); + + return res->start == start; +} + +static bool nfit_test_release_region(struct device *dev, + struct resource *parent, resource_size_t start, + resource_size_t n) +{ + if (parent == &iomem_resource) { + struct nfit_test_resource *nfit_res = get_nfit_res(start); + + if (nfit_res) { + struct nfit_test_request *req; + struct resource *res = NULL; + + if (dev) { + devres_release(dev, nfit_devres_release, match, + &start); + return true; + } + + spin_lock(&nfit_res->lock); + list_for_each_entry(req, &nfit_res->requests, list) + if (req->res.start == start) { + res = &req->res; + list_del(&req->list); + break; + } + spin_unlock(&nfit_res->lock); + + WARN(!res || resource_size(res) != n, + "%s: start: %llx n: %llx mismatch: %pr\n", + __func__, start, n, res); + if (res) + kfree(req); + return true; + } + } + return false; +} + static struct resource *nfit_test_request_region(struct device *dev, struct resource *parent, resource_size_t start, resource_size_t n, const char *name, int flags) @@ -183,21 +241,57 @@ static struct resource *nfit_test_request_region(struct device *dev, if (parent == &iomem_resource) { nfit_res = get_nfit_res(start); if (nfit_res) { - struct resource *res = nfit_res->res + 1; + struct nfit_test_request *req; + struct resource *res = NULL; - if (start + n > nfit_res->res->start - + resource_size(nfit_res->res)) { + if (start + n > nfit_res->res.start + + resource_size(&nfit_res->res)) { pr_debug("%s: start: %llx n: %llx overflow: %pr\n", __func__, start, n, - nfit_res->res); + &nfit_res->res); return NULL; } + spin_lock(&nfit_res->lock); + list_for_each_entry(req, &nfit_res->requests, list) + if (start == req->res.start) { + res = &req->res; + break; + } + spin_unlock(&nfit_res->lock); + + if (res) { + WARN(1, "%pr already busy\n", res); + return NULL; + } + + req = kzalloc(sizeof(*req), GFP_KERNEL); + if (!req) + return NULL; + INIT_LIST_HEAD(&req->list); + res = &req->res; + res->start = start; res->end = start + n - 1; res->name = name; res->flags = resource_type(parent); res->flags |= IORESOURCE_BUSY | flags; + spin_lock(&nfit_res->lock); + list_add(&req->list, &nfit_res->requests); + spin_unlock(&nfit_res->lock); + + if (dev) { + struct resource **d; + + d = devres_alloc(nfit_devres_release, + sizeof(struct resource *), + GFP_KERNEL); + if (!d) + return NULL; + *d = res; + devres_add(dev, d); + } + pr_debug("%s: %pr\n", __func__, res); return res; } @@ -241,29 +335,10 @@ struct resource *__wrap___devm_request_region(struct device *dev, } EXPORT_SYMBOL(__wrap___devm_request_region); -static bool nfit_test_release_region(struct resource *parent, - resource_size_t start, resource_size_t n) -{ - if (parent == &iomem_resource) { - struct nfit_test_resource *nfit_res = get_nfit_res(start); - if (nfit_res) { - struct resource *res = nfit_res->res + 1; - - if (start != res->start || resource_size(res) != n) - pr_info("%s: start: %llx n: %llx mismatch: %pr\n", - __func__, start, n, res); - else - memset(res, 0, sizeof(*res)); - return true; - } - } - return false; -} - void __wrap___release_region(struct resource *parent, resource_size_t start, resource_size_t n) { - if (!nfit_test_release_region(parent, start, n)) + if (!nfit_test_release_region(NULL, parent, start, n)) __release_region(parent, start, n); } EXPORT_SYMBOL(__wrap___release_region); @@ -271,9 +346,25 @@ EXPORT_SYMBOL(__wrap___release_region); void __wrap___devm_release_region(struct device *dev, struct resource *parent, resource_size_t start, resource_size_t n) { - if (!nfit_test_release_region(parent, start, n)) + if (!nfit_test_release_region(dev, parent, start, n)) __devm_release_region(dev, parent, start, n); } EXPORT_SYMBOL(__wrap___devm_release_region); +acpi_status __wrap_acpi_evaluate_object(acpi_handle handle, acpi_string path, + struct acpi_object_list *p, struct acpi_buffer *buf) +{ + struct nfit_test_resource *nfit_res = get_nfit_res((long) handle); + union acpi_object **obj; + + if (!nfit_res || strcmp(path, "_FIT") || !buf) + return acpi_evaluate_object(handle, path, p, buf); + + obj = nfit_res->buf; + buf->length = sizeof(union acpi_object); + buf->pointer = *obj; + return AE_OK; +} +EXPORT_SYMBOL(__wrap_acpi_evaluate_object); + MODULE_LICENSE("GPL v2"); diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index dd48f421844c..c9a6458cb63e 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -132,6 +132,8 @@ static u32 handle[NUM_DCR] = { [4] = NFIT_DIMM_HANDLE(0, 1, 0, 0, 0), }; +static unsigned long dimm_fail_cmd_flags[NUM_DCR]; + struct nfit_test { struct acpi_nfit_desc acpi_desc; struct platform_device pdev; @@ -154,11 +156,14 @@ struct nfit_test { int (*alloc)(struct nfit_test *t); void (*setup)(struct nfit_test *t); int setup_hotplug; + union acpi_object **_fit; + dma_addr_t _fit_dma; struct ars_state { struct nd_cmd_ars_status *ars_status; unsigned long deadline; spinlock_t lock; } ars_state; + struct device *dimm_dev[NUM_DCR]; }; static struct nfit_test *to_nfit_test(struct device *dev) @@ -411,6 +416,9 @@ static int nfit_test_ctl(struct nvdimm_bus_descriptor *nd_desc, if (i >= ARRAY_SIZE(handle)) return -ENXIO; + if ((1 << func) & dimm_fail_cmd_flags[i]) + return -EIO; + switch (func) { case ND_CMD_GET_CONFIG_SIZE: rc = nfit_test_cmd_get_config_size(buf, buf_len); @@ -428,6 +436,9 @@ static int nfit_test_ctl(struct nvdimm_bus_descriptor *nd_desc, break; case ND_CMD_SMART_THRESHOLD: rc = nfit_test_cmd_smart_threshold(buf, buf_len); + device_lock(&t->pdev.dev); + __acpi_nvdimm_notify(t->dimm_dev[i], 0x81); + device_unlock(&t->pdev.dev); break; default: return -ENOTTY; @@ -467,14 +478,12 @@ static struct nfit_test *instances[NUM_NFITS]; static void release_nfit_res(void *data) { struct nfit_test_resource *nfit_res = data; - struct resource *res = nfit_res->res; spin_lock(&nfit_test_lock); list_del(&nfit_res->list); spin_unlock(&nfit_test_lock); vfree(nfit_res->buf); - kfree(res); kfree(nfit_res); } @@ -482,12 +491,11 @@ static void *__test_alloc(struct nfit_test *t, size_t size, dma_addr_t *dma, void *buf) { struct device *dev = &t->pdev.dev; - struct resource *res = kzalloc(sizeof(*res) * 2, GFP_KERNEL); struct nfit_test_resource *nfit_res = kzalloc(sizeof(*nfit_res), GFP_KERNEL); int rc; - if (!res || !buf || !nfit_res) + if (!buf || !nfit_res) goto err; rc = devm_add_action(dev, release_nfit_res, nfit_res); if (rc) @@ -496,10 +504,11 @@ static void *__test_alloc(struct nfit_test *t, size_t size, dma_addr_t *dma, memset(buf, 0, size); nfit_res->dev = dev; nfit_res->buf = buf; - nfit_res->res = res; - res->start = *dma; - res->end = *dma + size - 1; - res->name = "NFIT"; + nfit_res->res.start = *dma; + nfit_res->res.end = *dma + size - 1; + nfit_res->res.name = "NFIT"; + spin_lock_init(&nfit_res->lock); + INIT_LIST_HEAD(&nfit_res->requests); spin_lock(&nfit_test_lock); list_add(&nfit_res->list, &t->resources); spin_unlock(&nfit_test_lock); @@ -508,7 +517,6 @@ static void *__test_alloc(struct nfit_test *t, size_t size, dma_addr_t *dma, err: if (buf) vfree(buf); - kfree(res); kfree(nfit_res); return NULL; } @@ -533,13 +541,13 @@ static struct nfit_test_resource *nfit_test_lookup(resource_size_t addr) continue; spin_lock(&nfit_test_lock); list_for_each_entry(n, &t->resources, list) { - if (addr >= n->res->start && (addr < n->res->start - + resource_size(n->res))) { + if (addr >= n->res.start && (addr < n->res.start + + resource_size(&n->res))) { nfit_res = n; break; } else if (addr >= (unsigned long) n->buf && (addr < (unsigned long) n->buf - + resource_size(n->res))) { + + resource_size(&n->res))) { nfit_res = n; break; } @@ -564,6 +572,86 @@ static int ars_state_init(struct device *dev, struct ars_state *ars_state) return 0; } +static void put_dimms(void *data) +{ + struct device **dimm_dev = data; + int i; + + for (i = 0; i < NUM_DCR; i++) + if (dimm_dev[i]) + device_unregister(dimm_dev[i]); +} + +static struct class *nfit_test_dimm; + +static int dimm_name_to_id(struct device *dev) +{ + int dimm; + + if (sscanf(dev_name(dev), "test_dimm%d", &dimm) != 1 + || dimm >= NUM_DCR || dimm < 0) + return -ENXIO; + return dimm; +} + + +static ssize_t handle_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + int dimm = dimm_name_to_id(dev); + + if (dimm < 0) + return dimm; + + return sprintf(buf, "%#x", handle[dimm]); +} +DEVICE_ATTR_RO(handle); + +static ssize_t fail_cmd_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + int dimm = dimm_name_to_id(dev); + + if (dimm < 0) + return dimm; + + return sprintf(buf, "%#lx\n", dimm_fail_cmd_flags[dimm]); +} + +static ssize_t fail_cmd_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t size) +{ + int dimm = dimm_name_to_id(dev); + unsigned long val; + ssize_t rc; + + if (dimm < 0) + return dimm; + + rc = kstrtol(buf, 0, &val); + if (rc) + return rc; + + dimm_fail_cmd_flags[dimm] = val; + return size; +} +static DEVICE_ATTR_RW(fail_cmd); + +static struct attribute *nfit_test_dimm_attributes[] = { + &dev_attr_fail_cmd.attr, + &dev_attr_handle.attr, + NULL, +}; + +static struct attribute_group nfit_test_dimm_attribute_group = { + .attrs = nfit_test_dimm_attributes, +}; + +static const struct attribute_group *nfit_test_dimm_attribute_groups[] = { + &nfit_test_dimm_attribute_group, + NULL, +}; + static int nfit_test0_alloc(struct nfit_test *t) { size_t nfit_size = sizeof(struct acpi_nfit_system_address) * NUM_SPA @@ -603,7 +691,8 @@ static int nfit_test0_alloc(struct nfit_test *t) return -ENOMEM; sprintf(t->label[i], "label%d", i); - t->flush[i] = test_alloc(t, sizeof(u64) * NUM_HINTS, + t->flush[i] = test_alloc(t, max(PAGE_SIZE, + sizeof(u64) * NUM_HINTS), &t->flush_dma[i]); if (!t->flush[i]) return -ENOMEM; @@ -615,6 +704,21 @@ static int nfit_test0_alloc(struct nfit_test *t) return -ENOMEM; } + t->_fit = test_alloc(t, sizeof(union acpi_object **), &t->_fit_dma); + if (!t->_fit) + return -ENOMEM; + + if (devm_add_action_or_reset(&t->pdev.dev, put_dimms, t->dimm_dev)) + return -ENOMEM; + for (i = 0; i < NUM_DCR; i++) { + t->dimm_dev[i] = device_create_with_groups(nfit_test_dimm, + &t->pdev.dev, 0, NULL, + nfit_test_dimm_attribute_groups, + "test_dimm%d", i); + if (!t->dimm_dev[i]) + return -ENOMEM; + } + return ars_state_init(&t->pdev.dev, &t->ars_state); } @@ -1408,6 +1512,8 @@ static int nfit_test_probe(struct platform_device *pdev) struct acpi_nfit_desc *acpi_desc; struct device *dev = &pdev->dev; struct nfit_test *nfit_test; + struct nfit_mem *nfit_mem; + union acpi_object *obj; int rc; nfit_test = to_nfit_test(&pdev->dev); @@ -1475,14 +1581,30 @@ static int nfit_test_probe(struct platform_device *pdev) if (nfit_test->setup != nfit_test0_setup) return 0; - flush_work(&acpi_desc->work); nfit_test->setup_hotplug = 1; nfit_test->setup(nfit_test); - rc = acpi_nfit_init(acpi_desc, nfit_test->nfit_buf, - nfit_test->nfit_size); - if (rc) - return rc; + obj = kzalloc(sizeof(*obj), GFP_KERNEL); + if (!obj) + return -ENOMEM; + obj->type = ACPI_TYPE_BUFFER; + obj->buffer.length = nfit_test->nfit_size; + obj->buffer.pointer = nfit_test->nfit_buf; + *(nfit_test->_fit) = obj; + __acpi_nfit_notify(&pdev->dev, nfit_test, 0x80); + + /* associate dimm devices with nfit_mem data for notification testing */ + mutex_lock(&acpi_desc->init_mutex); + list_for_each_entry(nfit_mem, &acpi_desc->dimms, list) { + u32 nfit_handle = __to_nfit_memdev(nfit_mem)->device_handle; + int i; + + for (i = 0; i < NUM_DCR; i++) + if (nfit_handle == handle[i]) + dev_set_drvdata(nfit_test->dimm_dev[i], + nfit_mem); + } + mutex_unlock(&acpi_desc->init_mutex); return 0; } @@ -1517,6 +1639,10 @@ 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); for (i = 0; i < NUM_NFITS; i++) { @@ -1583,6 +1709,7 @@ static __exit void nfit_test_exit(void) for (i = 0; i < NUM_NFITS; i++) platform_device_unregister(&instances[i]->pdev); nfit_test_teardown(); + class_destroy(nfit_test_dimm); } module_init(nfit_test_init); diff --git a/tools/testing/nvdimm/test/nfit_test.h b/tools/testing/nvdimm/test/nfit_test.h index 9f18e2a4a862..c281dd2e5e2d 100644 --- a/tools/testing/nvdimm/test/nfit_test.h +++ b/tools/testing/nvdimm/test/nfit_test.h @@ -13,11 +13,21 @@ #ifndef __NFIT_TEST_H__ #define __NFIT_TEST_H__ #include <linux/list.h> +#include <linux/ioport.h> +#include <linux/spinlock_types.h> + +struct nfit_test_request { + struct list_head list; + struct resource res; +}; struct nfit_test_resource { + struct list_head requests; struct list_head list; - struct resource *res; + struct resource res; struct device *dev; + spinlock_t lock; + int req_count; void *buf; }; diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile index 3b530467148e..f2e07f2fd4b4 100644 --- a/tools/testing/radix-tree/Makefile +++ b/tools/testing/radix-tree/Makefile @@ -1,9 +1,10 @@ -CFLAGS += -I. -g -Wall -D_LGPL_SOURCE +CFLAGS += -I. -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 + regression1.o regression2.o regression3.o multiorder.o \ + iteration_check.o targets: $(TARGETS) diff --git a/tools/testing/radix-tree/iteration_check.c b/tools/testing/radix-tree/iteration_check.c new file mode 100644 index 000000000000..9adb8e7415a6 --- /dev/null +++ b/tools/testing/radix-tree/iteration_check.c @@ -0,0 +1,180 @@ +/* + * iteration_check.c: test races having to do with radix tree iteration + * Copyright (c) 2016 Intel Corporation + * Author: Ross Zwisler <ross.zwisler@linux.intel.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 <pthread.h> +#include "test.h" + +#define NUM_THREADS 4 +#define TAG 0 +static pthread_mutex_t tree_lock = PTHREAD_MUTEX_INITIALIZER; +static pthread_t threads[NUM_THREADS]; +RADIX_TREE(tree, GFP_KERNEL); +bool test_complete; + +/* relentlessly fill the tree with tagged entries */ +static void *add_entries_fn(void *arg) +{ + int pgoff; + + while (!test_complete) { + for (pgoff = 0; pgoff < 100; pgoff++) { + pthread_mutex_lock(&tree_lock); + if (item_insert(&tree, pgoff) == 0) + item_tag_set(&tree, pgoff, TAG); + pthread_mutex_unlock(&tree_lock); + } + } + + 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 + * NULL 'slot' variable. + */ +static void *tagged_iteration_fn(void *arg) +{ + struct radix_tree_iter iter; + void **slot; + + 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); + if (unlikely(!entry)) + continue; + + if (radix_tree_deref_retry(entry)) { + slot = radix_tree_iter_retry(&iter); + continue; + } + + if (rand() % 50 == 0) + slot = radix_tree_iter_next(&iter); + } + rcu_read_unlock(); + } + + 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 + * NULL 'slot' variable. + */ +static void *untagged_iteration_fn(void *arg) +{ + struct radix_tree_iter iter; + void **slot; + + 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); + if (unlikely(!entry)) + continue; + + if (radix_tree_deref_retry(entry)) { + slot = radix_tree_iter_retry(&iter); + continue; + } + + if (rand() % 50 == 0) + slot = radix_tree_iter_next(&iter); + } + rcu_read_unlock(); + } + + return NULL; +} + +/* + * Randomly remove entries to help induce radix_tree_iter_retry() calls in the + * two iteration functions. + */ +static void *remove_entries_fn(void *arg) +{ + while (!test_complete) { + int pgoff; + + pgoff = rand() % 100; + + pthread_mutex_lock(&tree_lock); + item_delete(&tree, pgoff); + pthread_mutex_unlock(&tree_lock); + } + + return NULL; +} + +/* This is a unit test for a bug found by the syzkaller tester */ +void iteration_test(void) +{ + int i; + + printf("Running iteration tests for 10 seconds\n"); + + srand(time(0)); + test_complete = false; + + if (pthread_create(&threads[0], NULL, tagged_iteration_fn, NULL)) { + perror("pthread_create"); + exit(1); + } + if (pthread_create(&threads[1], NULL, untagged_iteration_fn, NULL)) { + perror("pthread_create"); + exit(1); + } + if (pthread_create(&threads[2], NULL, add_entries_fn, NULL)) { + perror("pthread_create"); + exit(1); + } + if (pthread_create(&threads[3], NULL, remove_entries_fn, NULL)) { + perror("pthread_create"); + exit(1); + } + + sleep(10); + test_complete = true; + + for (i = 0; i < NUM_THREADS; i++) { + if (pthread_join(threads[i], NULL)) { + perror("pthread_join"); + exit(1); + } + } + + item_kill_tree(&tree); +} diff --git a/tools/testing/radix-tree/linux/cpu.h b/tools/testing/radix-tree/linux/cpu.h index 60a40459f269..7cf412103205 100644 --- a/tools/testing/radix-tree/linux/cpu.h +++ b/tools/testing/radix-tree/linux/cpu.h @@ -7,19 +7,8 @@ #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_DYING 0x0008 /* CPU (unsigned)v not running any task, - * not handling interrupts, soon dead. - * Called on the dying cpu, interrupts - * are already disabled. Must not - * sleep, must not fail */ #define CPU_POST_DEAD 0x0009 /* CPU (unsigned)v dead, cpu_hotplug * lock is dropped */ -#define CPU_STARTING 0x000A /* CPU (unsigned)v soon running. - * Called on the new cpu, just before - * enabling interrupts. Must not sleep, - * must not fail */ -#define CPU_DYING_IDLE 0x000B /* CPU (unsigned)v dying, reached - * idle loop. */ #define CPU_BROKEN 0x000C /* CPU (unsigned)v did not die properly, * perhaps due to preemption. */ #define CPU_TASKS_FROZEN 0x0010 @@ -30,5 +19,3 @@ #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 CPU_DYING_FROZEN (CPU_DYING | CPU_TASKS_FROZEN) -#define CPU_STARTING_FROZEN (CPU_STARTING | CPU_TASKS_FROZEN) diff --git a/tools/testing/radix-tree/main.c b/tools/testing/radix-tree/main.c index b7619ff3b552..daa9010693e8 100644 --- a/tools/testing/radix-tree/main.c +++ b/tools/testing/radix-tree/main.c @@ -332,6 +332,7 @@ int main(int argc, char **argv) regression1_test(); regression2_test(); regression3_test(); + iteration_test(); single_thread_tests(long_run); sleep(1); diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c index 39d9b9568fe2..05d7bc488971 100644 --- a/tools/testing/radix-tree/multiorder.c +++ b/tools/testing/radix-tree/multiorder.c @@ -124,6 +124,8 @@ static void multiorder_check(unsigned long index, int order) unsigned long i; unsigned long min = index & ~((1UL << order) - 1); unsigned long max = min + (1UL << order); + void **slot; + struct item *item2 = item_create(min); RADIX_TREE(tree, GFP_KERNEL); printf("Multiorder index %ld, order %d\n", index, order); @@ -139,13 +141,19 @@ static void multiorder_check(unsigned long index, int order) item_check_absent(&tree, i); for (i = max; i < 2*max; i++) item_check_absent(&tree, i); + for (i = min; i < max; i++) + assert(radix_tree_insert(&tree, i, item2) == -EEXIST); + + slot = radix_tree_lookup_slot(&tree, index); + free(*slot); + radix_tree_replace_slot(slot, item2); for (i = min; i < max; i++) { - static void *entry = (void *) - (0xA0 | RADIX_TREE_EXCEPTIONAL_ENTRY); - assert(radix_tree_insert(&tree, i, entry) == -EEXIST); + struct item *item = item_lookup(&tree, i); + assert(item != 0); + assert(item->index == min); } - assert(item_delete(&tree, index) != 0); + assert(item_delete(&tree, min) != 0); for (i = 0; i < 2*max; i++) item_check_absent(&tree, i); diff --git a/tools/testing/radix-tree/regression1.c b/tools/testing/radix-tree/regression1.c index 2d03a63bb79c..0d6813a61b37 100644 --- a/tools/testing/radix-tree/regression1.c +++ b/tools/testing/radix-tree/regression1.c @@ -43,7 +43,7 @@ #include "regression.h" static RADIX_TREE(mt_tree, GFP_KERNEL); -static pthread_mutex_t mt_lock; +static pthread_mutex_t mt_lock = PTHREAD_MUTEX_INITIALIZER; struct page { pthread_mutex_t lock; diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h index e85131369723..217fb2403f09 100644 --- a/tools/testing/radix-tree/test.h +++ b/tools/testing/radix-tree/test.h @@ -27,6 +27,7 @@ void item_kill_tree(struct radix_tree_root *root); void tag_check(void); void multiorder_checks(void); +void iteration_test(void); struct item * item_tag_set(struct radix_tree_root *root, unsigned long index, int tag); diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index ff9e5f20a5a7..f770dba2a6f6 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -15,6 +15,7 @@ TARGETS += memory-hotplug TARGETS += mount TARGETS += mqueue TARGETS += net +TARGETS += nsfs TARGETS += powerpc TARGETS += pstore TARGETS += ptrace diff --git a/tools/testing/selftests/nsfs/Makefile b/tools/testing/selftests/nsfs/Makefile new file mode 100644 index 000000000000..2306054a901a --- /dev/null +++ b/tools/testing/selftests/nsfs/Makefile @@ -0,0 +1,12 @@ +TEST_PROGS := owner pidns + +CFLAGS := -Wall -Werror + +all: owner pidns +owner: owner.c +pidns: pidns.c + +clean: + $(RM) owner pidns + +include ../lib.mk diff --git a/tools/testing/selftests/nsfs/owner.c b/tools/testing/selftests/nsfs/owner.c new file mode 100644 index 000000000000..437205f8b714 --- /dev/null +++ b/tools/testing/selftests/nsfs/owner.c @@ -0,0 +1,91 @@ +#define _GNU_SOURCE +#include <sched.h> +#include <unistd.h> +#include <stdio.h> +#include <stdlib.h> +#include <signal.h> +#include <errno.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <sys/ioctl.h> +#include <sys/prctl.h> +#include <sys/wait.h> + +#define NSIO 0xb7 +#define NS_GET_USERNS _IO(NSIO, 0x1) + +#define pr_err(fmt, ...) \ + ({ \ + fprintf(stderr, "%s:%d:" fmt ": %m\n", \ + __func__, __LINE__, ##__VA_ARGS__); \ + 1; \ + }) + +int main(int argc, char *argvp[]) +{ + int pfd[2], ns, uns, init_uns; + struct stat st1, st2; + char path[128]; + pid_t pid; + char c; + + if (pipe(pfd)) + return 1; + + pid = fork(); + if (pid < 0) + return pr_err("fork"); + if (pid == 0) { + prctl(PR_SET_PDEATHSIG, SIGKILL); + if (unshare(CLONE_NEWUTS | CLONE_NEWUSER)) + return pr_err("unshare"); + close(pfd[0]); + close(pfd[1]); + while (1) + sleep(1); + return 0; + } + close(pfd[1]); + if (read(pfd[0], &c, 1) != 0) + return pr_err("Unable to read from pipe"); + close(pfd[0]); + + snprintf(path, sizeof(path), "/proc/%d/ns/uts", pid); + ns = open(path, O_RDONLY); + if (ns < 0) + return pr_err("Unable to open %s", path); + + uns = ioctl(ns, NS_GET_USERNS); + if (uns < 0) + return pr_err("Unable to get an owning user namespace"); + + if (fstat(uns, &st1)) + return pr_err("fstat"); + + snprintf(path, sizeof(path), "/proc/%d/ns/user", pid); + if (stat(path, &st2)) + return pr_err("stat"); + + if (st1.st_ino != st2.st_ino) + return pr_err("NS_GET_USERNS returned a wrong namespace"); + + init_uns = ioctl(uns, NS_GET_USERNS); + if (uns < 0) + return pr_err("Unable to get an owning user namespace"); + + if (ioctl(init_uns, NS_GET_USERNS) >= 0 || errno != EPERM) + return pr_err("Don't get EPERM"); + + if (unshare(CLONE_NEWUSER)) + return pr_err("unshare"); + + if (ioctl(ns, NS_GET_USERNS) >= 0 || errno != EPERM) + return pr_err("Don't get EPERM"); + if (ioctl(init_uns, NS_GET_USERNS) >= 0 || errno != EPERM) + return pr_err("Don't get EPERM"); + + kill(pid, SIGKILL); + wait(NULL); + return 0; +} diff --git a/tools/testing/selftests/nsfs/pidns.c b/tools/testing/selftests/nsfs/pidns.c new file mode 100644 index 000000000000..ae3a0d68e966 --- /dev/null +++ b/tools/testing/selftests/nsfs/pidns.c @@ -0,0 +1,78 @@ +#define _GNU_SOURCE +#include <sched.h> +#include <unistd.h> +#include <stdio.h> +#include <stdlib.h> +#include <signal.h> +#include <errno.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <sys/ioctl.h> +#include <sys/prctl.h> +#include <sys/wait.h> + +#define pr_err(fmt, ...) \ + ({ \ + fprintf(stderr, "%s:%d:" fmt ": %m\n", \ + __func__, __LINE__, ##__VA_ARGS__); \ + 1; \ + }) + +#define NSIO 0xb7 +#define NS_GET_USERNS _IO(NSIO, 0x1) +#define NS_GET_PARENT _IO(NSIO, 0x2) + +#define __stack_aligned__ __attribute__((aligned(16))) +struct cr_clone_arg { + char stack[128] __stack_aligned__; + char stack_ptr[0]; +}; + +static int child(void *args) +{ + prctl(PR_SET_PDEATHSIG, SIGKILL); + while (1) + sleep(1); + exit(0); +} + +int main(int argc, char *argv[]) +{ + char *ns_strs[] = {"pid", "user"}; + char path[] = "/proc/0123456789/ns/pid"; + struct cr_clone_arg ca; + struct stat st1, st2; + int ns, pns, i; + pid_t pid; + + pid = clone(child, ca.stack_ptr, CLONE_NEWUSER | CLONE_NEWPID | SIGCHLD, NULL); + if (pid < 0) + return pr_err("clone"); + + for (i = 0; i < 2; i++) { + snprintf(path, sizeof(path), "/proc/%d/ns/%s", pid, ns_strs[i]); + ns = open(path, O_RDONLY); + if (ns < 0) + return pr_err("Unable to open %s", path); + + pns = ioctl(ns, NS_GET_PARENT); + if (pns < 0) + return pr_err("Unable to get a parent pidns"); + + snprintf(path, sizeof(path), "/proc/self/ns/%s", ns_strs[i]); + if (stat(path, &st2)) + return pr_err("Unable to stat %s", path); + if (fstat(pns, &st1)) + return pr_err("Unable to stat the parent pidns"); + if (st1.st_ino != st2.st_ino) + return pr_err("NS_GET_PARENT returned a wrong namespace"); + + if (ioctl(pns, NS_GET_PARENT) >= 0 || errno != EPERM) + return pr_err("Don't get EPERM");; + } + + kill(pid, SIGKILL); + wait(NULL); + return 0; +} diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore index a937a9d26b60..142c565bb351 100644 --- a/tools/testing/selftests/vm/.gitignore +++ b/tools/testing/selftests/vm/.gitignore @@ -7,3 +7,4 @@ mlock2-tests on-fault-limit transhuge-stress userfaultfd +mlock-intersect-test diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index e4bb1de1d526..bbab7f4664ac 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -10,6 +10,7 @@ BINARIES += on-fault-limit BINARIES += thuge-gen BINARIES += transhuge-stress BINARIES += userfaultfd +BINARIES += mlock-random-test all: $(BINARIES) %: %.c @@ -17,6 +18,9 @@ all: $(BINARIES) userfaultfd: userfaultfd.c ../../../../usr/include/linux/kernel.h $(CC) $(CFLAGS) -O2 -o $@ $< -lpthread +mlock-random-test: mlock-random-test.c + $(CC) $(CFLAGS) -o $@ $< -lcap + ../../../../usr/include/linux/kernel.h: make -C ../../../.. headers_install diff --git a/tools/testing/selftests/vm/mlock-random-test.c b/tools/testing/selftests/vm/mlock-random-test.c new file mode 100644 index 000000000000..83de4f58d262 --- /dev/null +++ b/tools/testing/selftests/vm/mlock-random-test.c @@ -0,0 +1,293 @@ +/* + * It tests the mlock/mlock2() when they are invoked + * on randomly memory region. + */ +#include <unistd.h> +#include <sys/resource.h> +#include <sys/capability.h> +#include <sys/mman.h> +#include <fcntl.h> +#include <string.h> +#include <sys/ipc.h> +#include <sys/shm.h> +#include <time.h> +#include "mlock2.h" + +#define CHUNK_UNIT (128 * 1024) +#define MLOCK_RLIMIT_SIZE (CHUNK_UNIT * 2) +#define MLOCK_WITHIN_LIMIT_SIZE CHUNK_UNIT +#define MLOCK_OUTOF_LIMIT_SIZE (CHUNK_UNIT * 3) + +#define TEST_LOOP 100 +#define PAGE_ALIGN(size, ps) (((size) + ((ps) - 1)) & ~((ps) - 1)) + +int set_cap_limits(rlim_t max) +{ + struct rlimit new; + cap_t cap = cap_init(); + + new.rlim_cur = max; + new.rlim_max = max; + if (setrlimit(RLIMIT_MEMLOCK, &new)) { + perror("setrlimit() returns error\n"); + return -1; + } + + /* drop capabilities including CAP_IPC_LOCK */ + if (cap_set_proc(cap)) { + perror("cap_set_proc() returns error\n"); + return -2; + } + + return 0; +} + +int get_proc_locked_vm_size(void) +{ + FILE *f; + int ret = -1; + char line[1024] = {0}; + unsigned long lock_size = 0; + + f = fopen("/proc/self/status", "r"); + if (!f) { + perror("fopen"); + return -1; + } + + while (fgets(line, 1024, f)) { + if (strstr(line, "VmLck")) { + ret = sscanf(line, "VmLck:\t%8lu kB", &lock_size); + if (ret <= 0) { + printf("sscanf() on VmLck error: %s: %d\n", + line, ret); + fclose(f); + return -1; + } + fclose(f); + return (int)(lock_size << 10); + } + } + + perror("cann't parse VmLck in /proc/self/status\n"); + fclose(f); + return -1; +} + +/* + * Get the MMUPageSize of the memory region including input + * address from proc file. + * + * return value: on error case, 0 will be returned. + * Otherwise the page size(in bytes) is returned. + */ +int get_proc_page_size(unsigned long addr) +{ + FILE *smaps; + char *line; + unsigned long mmupage_size = 0; + size_t size; + + smaps = seek_to_smaps_entry(addr); + if (!smaps) { + printf("Unable to parse /proc/self/smaps\n"); + return 0; + } + + while (getline(&line, &size, smaps) > 0) { + if (!strstr(line, "MMUPageSize")) { + free(line); + line = NULL; + size = 0; + continue; + } + + /* found the MMUPageSize of this section */ + if (sscanf(line, "MMUPageSize: %8lu kB", + &mmupage_size) < 1) { + printf("Unable to parse smaps entry for Size:%s\n", + line); + break; + } + + } + free(line); + if (smaps) + fclose(smaps); + return mmupage_size << 10; +} + +/* + * Test mlock/mlock2() on provided memory chunk. + * It expects the mlock/mlock2() to be successful (within rlimit) + * + * With allocated memory chunk [p, p + alloc_size), this + * test will choose start/len randomly to perform mlock/mlock2 + * [start, start + len] memory range. The range is within range + * of the allocated chunk. + * + * The memory region size alloc_size is within the rlimit. + * So we always expect a success of mlock/mlock2. + * + * VmLck is assumed to be 0 before this test. + * + * return value: 0 - success + * else: failure + */ +int test_mlock_within_limit(char *p, int alloc_size) +{ + int i; + int ret = 0; + int locked_vm_size = 0; + struct rlimit cur; + int page_size = 0; + + getrlimit(RLIMIT_MEMLOCK, &cur); + if (cur.rlim_cur < alloc_size) { + printf("alloc_size[%d] < %u rlimit,lead to mlock failure\n", + alloc_size, (unsigned int)cur.rlim_cur); + return -1; + } + + srand(time(NULL)); + for (i = 0; i < TEST_LOOP; i++) { + /* + * - choose mlock/mlock2 randomly + * - choose lock_size randomly but lock_size < alloc_size + * - choose start_offset randomly but p+start_offset+lock_size + * < p+alloc_size + */ + int is_mlock = !!(rand() % 2); + int lock_size = rand() % alloc_size; + int start_offset = rand() % (alloc_size - lock_size); + + if (is_mlock) + ret = mlock(p + start_offset, lock_size); + else + ret = mlock2_(p + start_offset, lock_size, + MLOCK_ONFAULT); + + if (ret) { + printf("%s() failure at |%p(%d)| mlock:|%p(%d)|\n", + is_mlock ? "mlock" : "mlock2", + p, alloc_size, + p + start_offset, lock_size); + return ret; + } + } + + /* + * Check VmLck left by the tests. + */ + locked_vm_size = get_proc_locked_vm_size(); + page_size = get_proc_page_size((unsigned long)p); + if (page_size == 0) { + printf("cannot get proc MMUPageSize\n"); + return -1; + } + + if (locked_vm_size > PAGE_ALIGN(alloc_size, page_size) + page_size) { + printf("test_mlock_within_limit() left VmLck:%d on %d chunk\n", + locked_vm_size, alloc_size); + return -1; + } + + return 0; +} + + +/* + * We expect the mlock/mlock2() to be fail (outof limitation) + * + * With allocated memory chunk [p, p + alloc_size), this + * test will randomly choose start/len and perform mlock/mlock2 + * on [start, start+len] range. + * + * The memory region size alloc_size is above the rlimit. + * And the len to be locked is higher than rlimit. + * So we always expect a failure of mlock/mlock2. + * No locked page number should be increased as a side effect. + * + * return value: 0 - success + * else: failure + */ +int test_mlock_outof_limit(char *p, int alloc_size) +{ + int i; + int ret = 0; + int locked_vm_size = 0, old_locked_vm_size = 0; + struct rlimit cur; + + getrlimit(RLIMIT_MEMLOCK, &cur); + if (cur.rlim_cur >= alloc_size) { + printf("alloc_size[%d] >%u rlimit, violates test condition\n", + alloc_size, (unsigned int)cur.rlim_cur); + return -1; + } + + old_locked_vm_size = get_proc_locked_vm_size(); + srand(time(NULL)); + for (i = 0; i < TEST_LOOP; i++) { + int is_mlock = !!(rand() % 2); + int lock_size = (rand() % (alloc_size - cur.rlim_cur)) + + cur.rlim_cur; + int start_offset = rand() % (alloc_size - lock_size); + + if (is_mlock) + ret = mlock(p + start_offset, lock_size); + else + ret = mlock2_(p + start_offset, lock_size, + MLOCK_ONFAULT); + if (ret == 0) { + printf("%s() succeeds? on %p(%d) mlock%p(%d)\n", + is_mlock ? "mlock" : "mlock2", + p, alloc_size, + p + start_offset, lock_size); + return -1; + } + } + + locked_vm_size = get_proc_locked_vm_size(); + if (locked_vm_size != old_locked_vm_size) { + printf("tests leads to new mlocked page: old[%d], new[%d]\n", + old_locked_vm_size, + locked_vm_size); + return -1; + } + + return 0; +} + +int main(int argc, char **argv) +{ + char *p = NULL; + int ret = 0; + + if (set_cap_limits(MLOCK_RLIMIT_SIZE)) + return -1; + + p = malloc(MLOCK_WITHIN_LIMIT_SIZE); + if (p == NULL) { + perror("malloc() failure\n"); + return -1; + } + ret = test_mlock_within_limit(p, MLOCK_WITHIN_LIMIT_SIZE); + if (ret) + return ret; + munlock(p, MLOCK_WITHIN_LIMIT_SIZE); + free(p); + + + p = malloc(MLOCK_OUTOF_LIMIT_SIZE); + if (p == NULL) { + perror("malloc() failure\n"); + return -1; + } + ret = test_mlock_outof_limit(p, MLOCK_OUTOF_LIMIT_SIZE); + if (ret) + return ret; + munlock(p, MLOCK_OUTOF_LIMIT_SIZE); + free(p); + + return 0; +} diff --git a/tools/testing/selftests/vm/mlock2-tests.c b/tools/testing/selftests/vm/mlock2-tests.c index 02ca5e0177c5..ff0cda2b19c9 100644 --- a/tools/testing/selftests/vm/mlock2-tests.c +++ b/tools/testing/selftests/vm/mlock2-tests.c @@ -1,33 +1,12 @@ #define _GNU_SOURCE #include <sys/mman.h> #include <stdint.h> -#include <stdio.h> -#include <stdlib.h> #include <unistd.h> #include <string.h> #include <sys/time.h> #include <sys/resource.h> -#include <syscall.h> -#include <errno.h> #include <stdbool.h> - -#ifndef MLOCK_ONFAULT -#define MLOCK_ONFAULT 1 -#endif - -#ifndef MCL_ONFAULT -#define MCL_ONFAULT (MCL_FUTURE << 1) -#endif - -static int mlock2_(void *start, size_t len, int flags) -{ -#ifdef __NR_mlock2 - return syscall(__NR_mlock2, start, len, flags); -#else - errno = ENOSYS; - return -1; -#endif -} +#include "mlock2.h" struct vm_boundaries { unsigned long start; @@ -138,46 +117,6 @@ static uint64_t get_kpageflags(unsigned long pfn) return flags; } -static FILE *seek_to_smaps_entry(unsigned long addr) -{ - FILE *file; - char *line = NULL; - size_t size = 0; - unsigned long start, end; - char perms[5]; - unsigned long offset; - char dev[32]; - unsigned long inode; - char path[BUFSIZ]; - - file = fopen("/proc/self/smaps", "r"); - if (!file) { - perror("fopen smaps"); - _exit(1); - } - - while (getline(&line, &size, file) > 0) { - if (sscanf(line, "%lx-%lx %s %lx %s %lu %s\n", - &start, &end, perms, &offset, dev, &inode, path) < 6) - goto next; - - if (start <= addr && addr < end) - goto out; - -next: - free(line); - line = NULL; - size = 0; - } - - fclose(file); - file = NULL; - -out: - free(line); - return file; -} - #define VMFLAGS "VmFlags:" static bool is_vmflag_set(unsigned long addr, const char *vmflag) diff --git a/tools/testing/selftests/vm/mlock2.h b/tools/testing/selftests/vm/mlock2.h new file mode 100644 index 000000000000..7ee062929d3e --- /dev/null +++ b/tools/testing/selftests/vm/mlock2.h @@ -0,0 +1,62 @@ +#include <syscall.h> +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> + +#ifndef MLOCK_ONFAULT +#define MLOCK_ONFAULT 1 +#endif + +#ifndef MCL_ONFAULT +#define MCL_ONFAULT (MCL_FUTURE << 1) +#endif + +static int mlock2_(void *start, size_t len, int flags) +{ +#ifdef __NR_mlock2 + return syscall(__NR_mlock2, start, len, flags); +#else + errno = ENOSYS; + return -1; +#endif +} + +static FILE *seek_to_smaps_entry(unsigned long addr) +{ + FILE *file; + char *line = NULL; + size_t size = 0; + unsigned long start, end; + char perms[5]; + unsigned long offset; + char dev[32]; + unsigned long inode; + char path[BUFSIZ]; + + file = fopen("/proc/self/smaps", "r"); + if (!file) { + perror("fopen smaps"); + _exit(1); + } + + while (getline(&line, &size, file) > 0) { + if (sscanf(line, "%lx-%lx %s %lx %s %lu %s\n", + &start, &end, perms, &offset, dev, &inode, path) < 6) + goto next; + + if (start <= addr && addr < end) + goto out; + +next: + free(line); + line = NULL; + size = 0; + } + + fclose(file); + file = NULL; + +out: + free(line); + return file; +} diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index 4f747ee07f10..a89f80a5b711 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -5,7 +5,8 @@ include ../lib.mk .PHONY: all all_32 all_64 warn_32bit_failure clean TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_syscall test_mremap_vdso \ - check_initial_reg_state sigreturn ldt_gdt iopl mpx-mini-test + check_initial_reg_state sigreturn ldt_gdt iopl \ + protection_keys 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/pkey-helpers.h b/tools/testing/selftests/x86/pkey-helpers.h new file mode 100644 index 000000000000..b20293956eec --- /dev/null +++ b/tools/testing/selftests/x86/pkey-helpers.h @@ -0,0 +1,219 @@ +#ifndef _PKEYS_HELPER_H +#define _PKEYS_HELPER_H +#define _GNU_SOURCE +#include <string.h> +#include <stdarg.h> +#include <stdio.h> +#include <stdint.h> +#include <stdbool.h> +#include <signal.h> +#include <assert.h> +#include <stdlib.h> +#include <ucontext.h> +#include <sys/mman.h> + +#define NR_PKEYS 16 +#define PKRU_BITS_PER_PKEY 2 + +#ifndef DEBUG_LEVEL +#define DEBUG_LEVEL 0 +#endif +#define DPRINT_IN_SIGNAL_BUF_SIZE 4096 +extern int dprint_in_signal; +extern char dprint_in_signal_buffer[DPRINT_IN_SIGNAL_BUF_SIZE]; +static inline void sigsafe_printf(const char *format, ...) +{ + va_list ap; + + va_start(ap, format); + if (!dprint_in_signal) { + vprintf(format, ap); + } else { + int len = vsnprintf(dprint_in_signal_buffer, + DPRINT_IN_SIGNAL_BUF_SIZE, + format, ap); + /* + * len is amount that would have been printed, + * but actual write is truncated at BUF_SIZE. + */ + if (len > DPRINT_IN_SIGNAL_BUF_SIZE) + len = DPRINT_IN_SIGNAL_BUF_SIZE; + write(1, dprint_in_signal_buffer, len); + } + va_end(ap); +} +#define dprintf_level(level, args...) do { \ + if (level <= DEBUG_LEVEL) \ + sigsafe_printf(args); \ + fflush(NULL); \ +} while (0) +#define dprintf0(args...) dprintf_level(0, args) +#define dprintf1(args...) dprintf_level(1, args) +#define dprintf2(args...) dprintf_level(2, args) +#define dprintf3(args...) dprintf_level(3, args) +#define dprintf4(args...) dprintf_level(4, args) + +extern unsigned int shadow_pkru; +static inline unsigned int __rdpkru(void) +{ + unsigned int eax, edx; + unsigned int ecx = 0; + unsigned int pkru; + + asm volatile(".byte 0x0f,0x01,0xee\n\t" + : "=a" (eax), "=d" (edx) + : "c" (ecx)); + pkru = eax; + return pkru; +} + +static inline unsigned int _rdpkru(int line) +{ + unsigned int pkru = __rdpkru(); + + dprintf4("rdpkru(line=%d) pkru: %x shadow: %x\n", + line, pkru, shadow_pkru); + assert(pkru == shadow_pkru); + + return pkru; +} + +#define rdpkru() _rdpkru(__LINE__) + +static inline void __wrpkru(unsigned int pkru) +{ + unsigned int eax = pkru; + unsigned int ecx = 0; + unsigned int edx = 0; + + dprintf4("%s() changing %08x to %08x\n", __func__, __rdpkru(), pkru); + asm volatile(".byte 0x0f,0x01,0xef\n\t" + : : "a" (eax), "c" (ecx), "d" (edx)); + assert(pkru == __rdpkru()); +} + +static inline void wrpkru(unsigned int pkru) +{ + dprintf4("%s() changing %08x to %08x\n", __func__, __rdpkru(), pkru); + /* will do the shadow check for us: */ + rdpkru(); + __wrpkru(pkru); + shadow_pkru = pkru; + dprintf4("%s(%08x) pkru: %08x\n", __func__, pkru, __rdpkru()); +} + +/* + * These are technically racy. since something could + * change PKRU between the read and the write. + */ +static inline void __pkey_access_allow(int pkey, int do_allow) +{ + unsigned int pkru = rdpkru(); + int bit = pkey * 2; + + if (do_allow) + pkru &= (1<<bit); + else + pkru |= (1<<bit); + + dprintf4("pkru now: %08x\n", rdpkru()); + wrpkru(pkru); +} + +static inline void __pkey_write_allow(int pkey, int do_allow_write) +{ + long pkru = rdpkru(); + int bit = pkey * 2 + 1; + + if (do_allow_write) + pkru &= (1<<bit); + else + pkru |= (1<<bit); + + wrpkru(pkru); + dprintf4("pkru now: %08x\n", rdpkru()); +} + +#define PROT_PKEY0 0x10 /* protection key value (bit 0) */ +#define PROT_PKEY1 0x20 /* protection key value (bit 1) */ +#define PROT_PKEY2 0x40 /* protection key value (bit 2) */ +#define PROT_PKEY3 0x80 /* protection key value (bit 3) */ + +#define PAGE_SIZE 4096 +#define MB (1<<20) + +static inline void __cpuid(unsigned int *eax, unsigned int *ebx, + unsigned int *ecx, unsigned int *edx) +{ + /* ecx is often an input as well as an output. */ + asm volatile( + "cpuid;" + : "=a" (*eax), + "=b" (*ebx), + "=c" (*ecx), + "=d" (*edx) + : "0" (*eax), "2" (*ecx)); +} + +/* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx) */ +#define X86_FEATURE_PKU (1<<3) /* Protection Keys for Userspace */ +#define X86_FEATURE_OSPKE (1<<4) /* OS Protection Keys Enable */ + +static inline int cpu_has_pku(void) +{ + unsigned int eax; + unsigned int ebx; + unsigned int ecx; + unsigned int edx; + + eax = 0x7; + ecx = 0x0; + __cpuid(&eax, &ebx, &ecx, &edx); + + if (!(ecx & X86_FEATURE_PKU)) { + dprintf2("cpu does not have PKU\n"); + return 0; + } + if (!(ecx & X86_FEATURE_OSPKE)) { + dprintf2("cpu does not have OSPKE\n"); + return 0; + } + return 1; +} + +#define XSTATE_PKRU_BIT (9) +#define XSTATE_PKRU 0x200 + +int pkru_xstate_offset(void) +{ + unsigned int eax; + unsigned int ebx; + unsigned int ecx; + unsigned int edx; + int xstate_offset; + int xstate_size; + unsigned long XSTATE_CPUID = 0xd; + int leaf; + + /* assume that XSTATE_PKRU is set in XCR0 */ + leaf = XSTATE_PKRU_BIT; + { + eax = XSTATE_CPUID; + ecx = leaf; + __cpuid(&eax, &ebx, &ecx, &edx); + + if (leaf == XSTATE_PKRU_BIT) { + xstate_offset = ebx; + xstate_size = eax; + } + } + + if (xstate_size == 0) { + printf("could not find size/offset of PKRU in xsave state\n"); + return 0; + } + + return xstate_offset; +} + +#endif /* _PKEYS_HELPER_H */ diff --git a/tools/testing/selftests/x86/protection_keys.c b/tools/testing/selftests/x86/protection_keys.c new file mode 100644 index 000000000000..bdd58c78902e --- /dev/null +++ b/tools/testing/selftests/x86/protection_keys.c @@ -0,0 +1,1410 @@ +/* + * Tests x86 Memory Protection Keys (see Documentation/x86/protection-keys.txt) + * + * There are examples in here of: + * * how to set protection keys on memory + * * how to set/clear bits in PKRU (the rights register) + * * how to handle SEGV_PKRU signals and extract pkey-relevant + * information from the siginfo + * + * Things to add: + * make sure KSM and KSM COW breaking works + * prefault pages in at malloc, or not + * protect MPX bounds tables with protection keys? + * make sure VMA splitting/merging is working correctly + * OOMs can destroy mm->mmap (see exit_mmap()), so make sure it is immune to pkeys + * look for pkey "leaks" where it is still set on a VMA but "freed" back to the kernel + * do a plain mprotect() to a mprotect_pkey() area and make sure the pkey sticks + * + * Compile like this: + * gcc -o protection_keys -O2 -g -std=gnu99 -pthread -Wall protection_keys.c -lrt -ldl -lm + * gcc -m32 -o protection_keys_32 -O2 -g -std=gnu99 -pthread -Wall protection_keys.c -lrt -ldl -lm + */ +#define _GNU_SOURCE +#include <errno.h> +#include <linux/futex.h> +#include <sys/time.h> +#include <sys/syscall.h> +#include <string.h> +#include <stdio.h> +#include <stdint.h> +#include <stdbool.h> +#include <signal.h> +#include <assert.h> +#include <stdlib.h> +#include <ucontext.h> +#include <sys/mman.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <unistd.h> +#include <sys/ptrace.h> +#include <setjmp.h> + +#include "pkey-helpers.h" + +int iteration_nr = 1; +int test_nr; + +unsigned int shadow_pkru; + +#define HPAGE_SIZE (1UL<<21) +#define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x))) +#define ALIGN_UP(x, align_to) (((x) + ((align_to)-1)) & ~((align_to)-1)) +#define ALIGN_DOWN(x, align_to) ((x) & ~((align_to)-1)) +#define ALIGN_PTR_UP(p, ptr_align_to) ((typeof(p))ALIGN_UP((unsigned long)(p), ptr_align_to)) +#define ALIGN_PTR_DOWN(p, ptr_align_to) ((typeof(p))ALIGN_DOWN((unsigned long)(p), ptr_align_to)) +#define __stringify_1(x...) #x +#define __stringify(x...) __stringify_1(x) + +#define PTR_ERR_ENOTSUP ((void *)-ENOTSUP) + +int dprint_in_signal; +char dprint_in_signal_buffer[DPRINT_IN_SIGNAL_BUF_SIZE]; + +extern void abort_hooks(void); +#define pkey_assert(condition) do { \ + if (!(condition)) { \ + dprintf0("assert() at %s::%d test_nr: %d iteration: %d\n", \ + __FILE__, __LINE__, \ + test_nr, iteration_nr); \ + dprintf0("errno at assert: %d", errno); \ + abort_hooks(); \ + assert(condition); \ + } \ +} while (0) +#define raw_assert(cond) assert(cond) + +void cat_into_file(char *str, char *file) +{ + int fd = open(file, O_RDWR); + int ret; + + dprintf2("%s(): writing '%s' to '%s'\n", __func__, str, file); + /* + * these need to be raw because they are called under + * pkey_assert() + */ + raw_assert(fd >= 0); + ret = write(fd, str, strlen(str)); + if (ret != strlen(str)) { + perror("write to file failed"); + fprintf(stderr, "filename: '%s' str: '%s'\n", file, str); + raw_assert(0); + } + close(fd); +} + +#if CONTROL_TRACING > 0 +static int warned_tracing; +int tracing_root_ok(void) +{ + if (geteuid() != 0) { + if (!warned_tracing) + fprintf(stderr, "WARNING: not run as root, " + "can not do tracing control\n"); + warned_tracing = 1; + return 0; + } + return 1; +} +#endif + +void tracing_on(void) +{ +#if CONTROL_TRACING > 0 +#define TRACEDIR "/sys/kernel/debug/tracing" + char pidstr[32]; + + if (!tracing_root_ok()) + return; + + sprintf(pidstr, "%d", getpid()); + cat_into_file("0", TRACEDIR "/tracing_on"); + cat_into_file("\n", TRACEDIR "/trace"); + if (1) { + cat_into_file("function_graph", TRACEDIR "/current_tracer"); + cat_into_file("1", TRACEDIR "/options/funcgraph-proc"); + } else { + cat_into_file("nop", TRACEDIR "/current_tracer"); + } + cat_into_file(pidstr, TRACEDIR "/set_ftrace_pid"); + cat_into_file("1", TRACEDIR "/tracing_on"); + dprintf1("enabled tracing\n"); +#endif +} + +void tracing_off(void) +{ +#if CONTROL_TRACING > 0 + if (!tracing_root_ok()) + return; + cat_into_file("0", "/sys/kernel/debug/tracing/tracing_on"); +#endif +} + +void abort_hooks(void) +{ + fprintf(stderr, "running %s()...\n", __func__); + tracing_off(); +#ifdef SLEEP_ON_ABORT + sleep(SLEEP_ON_ABORT); +#endif +} + +static inline void __page_o_noops(void) +{ + /* 8-bytes of instruction * 512 bytes = 1 page */ + asm(".rept 512 ; nopl 0x7eeeeeee(%eax) ; .endr"); +} + +/* + * This attempts to have roughly a page of instructions followed by a few + * instructions that do a write, and another page of instructions. That + * way, we are pretty sure that the write is in the second page of + * instructions and has at least a page of padding behind it. + * + * *That* lets us be sure to madvise() away the write instruction, which + * will then fault, which makes sure that the fault code handles + * execute-only memory properly. + */ +__attribute__((__aligned__(PAGE_SIZE))) +void lots_o_noops_around_write(int *write_to_me) +{ + dprintf3("running %s()\n", __func__); + __page_o_noops(); + /* Assume this happens in the second page of instructions: */ + *write_to_me = __LINE__; + /* pad out by another page: */ + __page_o_noops(); + dprintf3("%s() done\n", __func__); +} + +/* Define some kernel-like types */ +#define u8 uint8_t +#define u16 uint16_t +#define u32 uint32_t +#define u64 uint64_t + +#ifdef __i386__ +#define SYS_mprotect_key 380 +#define SYS_pkey_alloc 381 +#define SYS_pkey_free 382 +#define REG_IP_IDX REG_EIP +#define si_pkey_offset 0x18 +#else +#define SYS_mprotect_key 329 +#define SYS_pkey_alloc 330 +#define SYS_pkey_free 331 +#define REG_IP_IDX REG_RIP +#define si_pkey_offset 0x20 +#endif + +void dump_mem(void *dumpme, int len_bytes) +{ + char *c = (void *)dumpme; + int i; + + for (i = 0; i < len_bytes; i += sizeof(u64)) { + u64 *ptr = (u64 *)(c + i); + dprintf1("dump[%03d][@%p]: %016jx\n", i, ptr, *ptr); + } +} + +#define __SI_FAULT (3 << 16) +#define SEGV_BNDERR (__SI_FAULT|3) /* failed address bound checks */ +#define SEGV_PKUERR (__SI_FAULT|4) + +static char *si_code_str(int si_code) +{ + if (si_code & SEGV_MAPERR) + return "SEGV_MAPERR"; + if (si_code & SEGV_ACCERR) + return "SEGV_ACCERR"; + if (si_code & SEGV_BNDERR) + return "SEGV_BNDERR"; + if (si_code & SEGV_PKUERR) + return "SEGV_PKUERR"; + return "UNKNOWN"; +} + +int pkru_faults; +int last_si_pkey = -1; +void signal_handler(int signum, siginfo_t *si, void *vucontext) +{ + ucontext_t *uctxt = vucontext; + int trapno; + unsigned long ip; + char *fpregs; + u32 *pkru_ptr; + u64 si_pkey; + u32 *si_pkey_ptr; + int pkru_offset; + fpregset_t fpregset; + + dprint_in_signal = 1; + dprintf1(">>>>===============SIGSEGV============================\n"); + dprintf1("%s()::%d, pkru: 0x%x shadow: %x\n", __func__, __LINE__, + __rdpkru(), shadow_pkru); + + trapno = uctxt->uc_mcontext.gregs[REG_TRAPNO]; + ip = uctxt->uc_mcontext.gregs[REG_IP_IDX]; + fpregset = uctxt->uc_mcontext.fpregs; + fpregs = (void *)fpregset; + + dprintf2("%s() trapno: %d ip: 0x%lx info->si_code: %s/%d\n", __func__, + trapno, ip, si_code_str(si->si_code), si->si_code); +#ifdef __i386__ + /* + * 32-bit has some extra padding so that userspace can tell whether + * the XSTATE header is present in addition to the "legacy" FPU + * state. We just assume that it is here. + */ + fpregs += 0x70; +#endif + pkru_offset = pkru_xstate_offset(); + pkru_ptr = (void *)(&fpregs[pkru_offset]); + + dprintf1("siginfo: %p\n", si); + dprintf1(" fpregs: %p\n", fpregs); + /* + * If we got a PKRU fault, we *HAVE* to have at least one bit set in + * here. + */ + dprintf1("pkru_xstate_offset: %d\n", pkru_xstate_offset()); + if (DEBUG_LEVEL > 4) + dump_mem(pkru_ptr - 128, 256); + pkey_assert(*pkru_ptr); + + si_pkey_ptr = (u32 *)(((u8 *)si) + si_pkey_offset); + dprintf1("si_pkey_ptr: %p\n", si_pkey_ptr); + dump_mem(si_pkey_ptr - 8, 24); + si_pkey = *si_pkey_ptr; + pkey_assert(si_pkey < NR_PKEYS); + last_si_pkey = si_pkey; + + if ((si->si_code == SEGV_MAPERR) || + (si->si_code == SEGV_ACCERR) || + (si->si_code == SEGV_BNDERR)) { + printf("non-PK si_code, exiting...\n"); + exit(4); + } + + dprintf1("signal pkru from xsave: %08x\n", *pkru_ptr); + /* need __rdpkru() version so we do not do shadow_pkru checking */ + dprintf1("signal pkru from pkru: %08x\n", __rdpkru()); + dprintf1("si_pkey from siginfo: %jx\n", si_pkey); + *(u64 *)pkru_ptr = 0x00000000; + dprintf1("WARNING: set PRKU=0 to allow faulting instruction to continue\n"); + pkru_faults++; + dprintf1("<<<<==================================================\n"); + return; + if (trapno == 14) { + fprintf(stderr, + "ERROR: In signal handler, page fault, trapno = %d, ip = %016lx\n", + trapno, ip); + fprintf(stderr, "si_addr %p\n", si->si_addr); + fprintf(stderr, "REG_ERR: %lx\n", + (unsigned long)uctxt->uc_mcontext.gregs[REG_ERR]); + exit(1); + } else { + fprintf(stderr, "unexpected trap %d! at 0x%lx\n", trapno, ip); + fprintf(stderr, "si_addr %p\n", si->si_addr); + fprintf(stderr, "REG_ERR: %lx\n", + (unsigned long)uctxt->uc_mcontext.gregs[REG_ERR]); + exit(2); + } + dprint_in_signal = 0; +} + +int wait_all_children(void) +{ + int status; + return waitpid(-1, &status, 0); +} + +void sig_chld(int x) +{ + dprint_in_signal = 1; + dprintf2("[%d] SIGCHLD: %d\n", getpid(), x); + dprint_in_signal = 0; +} + +void setup_sigsegv_handler(void) +{ + int r, rs; + struct sigaction newact; + struct sigaction oldact; + + /* #PF is mapped to sigsegv */ + int signum = SIGSEGV; + + newact.sa_handler = 0; + newact.sa_sigaction = signal_handler; + + /*sigset_t - signals to block while in the handler */ + /* get the old signal mask. */ + rs = sigprocmask(SIG_SETMASK, 0, &newact.sa_mask); + pkey_assert(rs == 0); + + /* call sa_sigaction, not sa_handler*/ + newact.sa_flags = SA_SIGINFO; + + newact.sa_restorer = 0; /* void(*)(), obsolete */ + r = sigaction(signum, &newact, &oldact); + r = sigaction(SIGALRM, &newact, &oldact); + pkey_assert(r == 0); +} + +void setup_handlers(void) +{ + signal(SIGCHLD, &sig_chld); + setup_sigsegv_handler(); +} + +pid_t fork_lazy_child(void) +{ + pid_t forkret; + + forkret = fork(); + pkey_assert(forkret >= 0); + dprintf3("[%d] fork() ret: %d\n", getpid(), forkret); + + if (!forkret) { + /* in the child */ + while (1) { + dprintf1("child sleeping...\n"); + sleep(30); + } + } + return forkret; +} + +void davecmp(void *_a, void *_b, int len) +{ + int i; + unsigned long *a = _a; + unsigned long *b = _b; + + for (i = 0; i < len / sizeof(*a); i++) { + if (a[i] == b[i]) + continue; + + dprintf3("[%3d]: a: %016lx b: %016lx\n", i, a[i], b[i]); + } +} + +void dumpit(char *f) +{ + int fd = open(f, O_RDONLY); + char buf[100]; + int nr_read; + + dprintf2("maps fd: %d\n", fd); + do { + nr_read = read(fd, &buf[0], sizeof(buf)); + write(1, buf, nr_read); + } while (nr_read > 0); + close(fd); +} + +#define PKEY_DISABLE_ACCESS 0x1 +#define PKEY_DISABLE_WRITE 0x2 + +u32 pkey_get(int pkey, unsigned long flags) +{ + u32 mask = (PKEY_DISABLE_ACCESS|PKEY_DISABLE_WRITE); + u32 pkru = __rdpkru(); + u32 shifted_pkru; + u32 masked_pkru; + + dprintf1("%s(pkey=%d, flags=%lx) = %x / %d\n", + __func__, pkey, flags, 0, 0); + dprintf2("%s() raw pkru: %x\n", __func__, pkru); + + shifted_pkru = (pkru >> (pkey * PKRU_BITS_PER_PKEY)); + dprintf2("%s() shifted_pkru: %x\n", __func__, shifted_pkru); + masked_pkru = shifted_pkru & mask; + dprintf2("%s() masked pkru: %x\n", __func__, masked_pkru); + /* + * shift down the relevant bits to the lowest two, then + * mask off all the other high bits. + */ + return masked_pkru; +} + +int pkey_set(int pkey, unsigned long rights, unsigned long flags) +{ + u32 mask = (PKEY_DISABLE_ACCESS|PKEY_DISABLE_WRITE); + u32 old_pkru = __rdpkru(); + u32 new_pkru; + + /* make sure that 'rights' only contains the bits we expect: */ + assert(!(rights & ~mask)); + + /* copy old pkru */ + new_pkru = old_pkru; + /* mask out bits from pkey in old value: */ + new_pkru &= ~(mask << (pkey * PKRU_BITS_PER_PKEY)); + /* OR in new bits for pkey: */ + new_pkru |= (rights << (pkey * PKRU_BITS_PER_PKEY)); + + __wrpkru(new_pkru); + + dprintf3("%s(pkey=%d, rights=%lx, flags=%lx) = %x pkru now: %x old_pkru: %x\n", + __func__, pkey, rights, flags, 0, __rdpkru(), old_pkru); + return 0; +} + +void pkey_disable_set(int pkey, int flags) +{ + unsigned long syscall_flags = 0; + int ret; + int pkey_rights; + u32 orig_pkru; + + dprintf1("START->%s(%d, 0x%x)\n", __func__, + pkey, flags); + pkey_assert(flags & (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE)); + + pkey_rights = pkey_get(pkey, syscall_flags); + + dprintf1("%s(%d) pkey_get(%d): %x\n", __func__, + pkey, pkey, pkey_rights); + pkey_assert(pkey_rights >= 0); + + pkey_rights |= flags; + + ret = pkey_set(pkey, pkey_rights, syscall_flags); + assert(!ret); + /*pkru and flags have the same format */ + shadow_pkru |= flags << (pkey * 2); + dprintf1("%s(%d) shadow: 0x%x\n", __func__, pkey, shadow_pkru); + + pkey_assert(ret >= 0); + + pkey_rights = pkey_get(pkey, syscall_flags); + dprintf1("%s(%d) pkey_get(%d): %x\n", __func__, + pkey, pkey, pkey_rights); + + dprintf1("%s(%d) pkru: 0x%x\n", __func__, pkey, rdpkru()); + if (flags) + pkey_assert(rdpkru() > orig_pkru); + dprintf1("END<---%s(%d, 0x%x)\n", __func__, + pkey, flags); +} + +void pkey_disable_clear(int pkey, int flags) +{ + unsigned long syscall_flags = 0; + int ret; + int pkey_rights = pkey_get(pkey, syscall_flags); + u32 orig_pkru = rdpkru(); + + pkey_assert(flags & (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE)); + + dprintf1("%s(%d) pkey_get(%d): %x\n", __func__, + pkey, pkey, pkey_rights); + pkey_assert(pkey_rights >= 0); + + pkey_rights |= flags; + + ret = pkey_set(pkey, pkey_rights, 0); + /* pkru and flags have the same format */ + shadow_pkru &= ~(flags << (pkey * 2)); + pkey_assert(ret >= 0); + + pkey_rights = pkey_get(pkey, syscall_flags); + dprintf1("%s(%d) pkey_get(%d): %x\n", __func__, + pkey, pkey, pkey_rights); + + dprintf1("%s(%d) pkru: 0x%x\n", __func__, pkey, rdpkru()); + if (flags) + assert(rdpkru() > orig_pkru); +} + +void pkey_write_allow(int pkey) +{ + pkey_disable_clear(pkey, PKEY_DISABLE_WRITE); +} +void pkey_write_deny(int pkey) +{ + pkey_disable_set(pkey, PKEY_DISABLE_WRITE); +} +void pkey_access_allow(int pkey) +{ + pkey_disable_clear(pkey, PKEY_DISABLE_ACCESS); +} +void pkey_access_deny(int pkey) +{ + pkey_disable_set(pkey, PKEY_DISABLE_ACCESS); +} + +int sys_mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot, + unsigned long pkey) +{ + int sret; + + dprintf2("%s(0x%p, %zx, prot=%lx, pkey=%lx)\n", __func__, + ptr, size, orig_prot, pkey); + + errno = 0; + sret = syscall(SYS_mprotect_key, ptr, size, orig_prot, pkey); + if (errno) { + dprintf2("SYS_mprotect_key sret: %d\n", sret); + dprintf2("SYS_mprotect_key prot: 0x%lx\n", orig_prot); + dprintf2("SYS_mprotect_key failed, errno: %d\n", errno); + if (DEBUG_LEVEL >= 2) + perror("SYS_mprotect_pkey"); + } + return sret; +} + +int sys_pkey_alloc(unsigned long flags, unsigned long init_val) +{ + int ret = syscall(SYS_pkey_alloc, flags, init_val); + dprintf1("%s(flags=%lx, init_val=%lx) syscall ret: %d errno: %d\n", + __func__, flags, init_val, ret, errno); + return ret; +} + +int alloc_pkey(void) +{ + int ret; + unsigned long init_val = 0x0; + + dprintf1("alloc_pkey()::%d, pkru: 0x%x shadow: %x\n", + __LINE__, __rdpkru(), shadow_pkru); + ret = sys_pkey_alloc(0, init_val); + /* + * pkey_alloc() sets PKRU, so we need to reflect it in + * shadow_pkru: + */ + dprintf4("alloc_pkey()::%d, ret: %d pkru: 0x%x shadow: 0x%x\n", + __LINE__, ret, __rdpkru(), shadow_pkru); + if (ret) { + /* clear both the bits: */ + shadow_pkru &= ~(0x3 << (ret * 2)); + dprintf4("alloc_pkey()::%d, ret: %d pkru: 0x%x shadow: 0x%x\n", + __LINE__, ret, __rdpkru(), shadow_pkru); + /* + * move the new state in from init_val + * (remember, we cheated and init_val == pkru format) + */ + shadow_pkru |= (init_val << (ret * 2)); + } + dprintf4("alloc_pkey()::%d, ret: %d pkru: 0x%x shadow: 0x%x\n", + __LINE__, ret, __rdpkru(), shadow_pkru); + dprintf1("alloc_pkey()::%d errno: %d\n", __LINE__, errno); + /* for shadow checking: */ + rdpkru(); + dprintf4("alloc_pkey()::%d, ret: %d pkru: 0x%x shadow: 0x%x\n", + __LINE__, ret, __rdpkru(), shadow_pkru); + return ret; +} + +int sys_pkey_free(unsigned long pkey) +{ + int ret = syscall(SYS_pkey_free, pkey); + dprintf1("%s(pkey=%ld) syscall ret: %d\n", __func__, pkey, ret); + return ret; +} + +/* + * I had a bug where pkey bits could be set by mprotect() but + * not cleared. This ensures we get lots of random bit sets + * and clears on the vma and pte pkey bits. + */ +int alloc_random_pkey(void) +{ + int max_nr_pkey_allocs; + int ret; + int i; + int alloced_pkeys[NR_PKEYS]; + int nr_alloced = 0; + int random_index; + memset(alloced_pkeys, 0, sizeof(alloced_pkeys)); + + /* allocate every possible key and make a note of which ones we got */ + max_nr_pkey_allocs = NR_PKEYS; + max_nr_pkey_allocs = 1; + for (i = 0; i < max_nr_pkey_allocs; i++) { + int new_pkey = alloc_pkey(); + if (new_pkey < 0) + break; + alloced_pkeys[nr_alloced++] = new_pkey; + } + + pkey_assert(nr_alloced > 0); + /* select a random one out of the allocated ones */ + random_index = rand() % nr_alloced; + ret = alloced_pkeys[random_index]; + /* now zero it out so we don't free it next */ + alloced_pkeys[random_index] = 0; + + /* go through the allocated ones that we did not want and free them */ + for (i = 0; i < nr_alloced; i++) { + int free_ret; + if (!alloced_pkeys[i]) + continue; + free_ret = sys_pkey_free(alloced_pkeys[i]); + pkey_assert(!free_ret); + } + dprintf1("%s()::%d, ret: %d pkru: 0x%x shadow: 0x%x\n", __func__, + __LINE__, ret, __rdpkru(), shadow_pkru); + return ret; +} + +int mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot, + unsigned long pkey) +{ + int nr_iterations = random() % 100; + int ret; + + while (0) { + int rpkey = alloc_random_pkey(); + ret = sys_mprotect_pkey(ptr, size, orig_prot, pkey); + dprintf1("sys_mprotect_pkey(%p, %zx, prot=0x%lx, pkey=%ld) ret: %d\n", + ptr, size, orig_prot, pkey, ret); + if (nr_iterations-- < 0) + break; + + dprintf1("%s()::%d, ret: %d pkru: 0x%x shadow: 0x%x\n", __func__, + __LINE__, ret, __rdpkru(), shadow_pkru); + sys_pkey_free(rpkey); + dprintf1("%s()::%d, ret: %d pkru: 0x%x shadow: 0x%x\n", __func__, + __LINE__, ret, __rdpkru(), shadow_pkru); + } + pkey_assert(pkey < NR_PKEYS); + + ret = sys_mprotect_pkey(ptr, size, orig_prot, pkey); + dprintf1("mprotect_pkey(%p, %zx, prot=0x%lx, pkey=%ld) ret: %d\n", + ptr, size, orig_prot, pkey, ret); + pkey_assert(!ret); + dprintf1("%s()::%d, ret: %d pkru: 0x%x shadow: 0x%x\n", __func__, + __LINE__, ret, __rdpkru(), shadow_pkru); + return ret; +} + +struct pkey_malloc_record { + void *ptr; + long size; +}; +struct pkey_malloc_record *pkey_malloc_records; +long nr_pkey_malloc_records; +void record_pkey_malloc(void *ptr, long size) +{ + long i; + struct pkey_malloc_record *rec = NULL; + + for (i = 0; i < nr_pkey_malloc_records; i++) { + rec = &pkey_malloc_records[i]; + /* find a free record */ + if (rec) + break; + } + if (!rec) { + /* every record is full */ + size_t old_nr_records = nr_pkey_malloc_records; + size_t new_nr_records = (nr_pkey_malloc_records * 2 + 1); + size_t new_size = new_nr_records * sizeof(struct pkey_malloc_record); + dprintf2("new_nr_records: %zd\n", new_nr_records); + dprintf2("new_size: %zd\n", new_size); + pkey_malloc_records = realloc(pkey_malloc_records, new_size); + pkey_assert(pkey_malloc_records != NULL); + rec = &pkey_malloc_records[nr_pkey_malloc_records]; + /* + * realloc() does not initialize memory, so zero it from + * the first new record all the way to the end. + */ + for (i = 0; i < new_nr_records - old_nr_records; i++) + memset(rec + i, 0, sizeof(*rec)); + } + dprintf3("filling malloc record[%d/%p]: {%p, %ld}\n", + (int)(rec - pkey_malloc_records), rec, ptr, size); + rec->ptr = ptr; + rec->size = size; + nr_pkey_malloc_records++; +} + +void free_pkey_malloc(void *ptr) +{ + long i; + int ret; + dprintf3("%s(%p)\n", __func__, ptr); + for (i = 0; i < nr_pkey_malloc_records; i++) { + struct pkey_malloc_record *rec = &pkey_malloc_records[i]; + dprintf4("looking for ptr %p at record[%ld/%p]: {%p, %ld}\n", + ptr, i, rec, rec->ptr, rec->size); + if ((ptr < rec->ptr) || + (ptr >= rec->ptr + rec->size)) + continue; + + dprintf3("found ptr %p at record[%ld/%p]: {%p, %ld}\n", + ptr, i, rec, rec->ptr, rec->size); + nr_pkey_malloc_records--; + ret = munmap(rec->ptr, rec->size); + dprintf3("munmap ret: %d\n", ret); + pkey_assert(!ret); + dprintf3("clearing rec->ptr, rec: %p\n", rec); + rec->ptr = NULL; + dprintf3("done clearing rec->ptr, rec: %p\n", rec); + return; + } + pkey_assert(false); +} + + +void *malloc_pkey_with_mprotect(long size, int prot, u16 pkey) +{ + void *ptr; + int ret; + + rdpkru(); + dprintf1("doing %s(size=%ld, prot=0x%x, pkey=%d)\n", __func__, + size, prot, pkey); + pkey_assert(pkey < NR_PKEYS); + ptr = mmap(NULL, size, prot, MAP_ANONYMOUS|MAP_PRIVATE, -1, 0); + pkey_assert(ptr != (void *)-1); + ret = mprotect_pkey((void *)ptr, PAGE_SIZE, prot, pkey); + pkey_assert(!ret); + record_pkey_malloc(ptr, size); + rdpkru(); + + dprintf1("%s() for pkey %d @ %p\n", __func__, pkey, ptr); + return ptr; +} + +void *malloc_pkey_anon_huge(long size, int prot, u16 pkey) +{ + int ret; + void *ptr; + + dprintf1("doing %s(size=%ld, prot=0x%x, pkey=%d)\n", __func__, + size, prot, pkey); + /* + * Guarantee we can fit at least one huge page in the resulting + * allocation by allocating space for 2: + */ + size = ALIGN_UP(size, HPAGE_SIZE * 2); + ptr = mmap(NULL, size, PROT_NONE, MAP_ANONYMOUS|MAP_PRIVATE, -1, 0); + pkey_assert(ptr != (void *)-1); + record_pkey_malloc(ptr, size); + mprotect_pkey(ptr, size, prot, pkey); + + dprintf1("unaligned ptr: %p\n", ptr); + ptr = ALIGN_PTR_UP(ptr, HPAGE_SIZE); + dprintf1(" aligned ptr: %p\n", ptr); + ret = madvise(ptr, HPAGE_SIZE, MADV_HUGEPAGE); + dprintf1("MADV_HUGEPAGE ret: %d\n", ret); + ret = madvise(ptr, HPAGE_SIZE, MADV_WILLNEED); + dprintf1("MADV_WILLNEED ret: %d\n", ret); + memset(ptr, 0, HPAGE_SIZE); + + dprintf1("mmap()'d thp for pkey %d @ %p\n", pkey, ptr); + return ptr; +} + +int hugetlb_setup_ok; +#define GET_NR_HUGE_PAGES 10 +void setup_hugetlbfs(void) +{ + int err; + int fd; + int validated_nr_pages; + int i; + char buf[] = "123"; + + if (geteuid() != 0) { + fprintf(stderr, "WARNING: not run as root, can not do hugetlb test\n"); + return; + } + + cat_into_file(__stringify(GET_NR_HUGE_PAGES), "/proc/sys/vm/nr_hugepages"); + + /* + * Now go make sure that we got the pages and that they + * are 2M pages. Someone might have made 1G the default. + */ + fd = open("/sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages", O_RDONLY); + if (fd < 0) { + perror("opening sysfs 2M hugetlb config"); + return; + } + + /* -1 to guarantee leaving the trailing \0 */ + err = read(fd, buf, sizeof(buf)-1); + close(fd); + if (err <= 0) { + perror("reading sysfs 2M hugetlb config"); + return; + } + + if (atoi(buf) != GET_NR_HUGE_PAGES) { + fprintf(stderr, "could not confirm 2M pages, got: '%s' expected %d\n", + buf, GET_NR_HUGE_PAGES); + return; + } + + hugetlb_setup_ok = 1; +} + +void *malloc_pkey_hugetlb(long size, int prot, u16 pkey) +{ + void *ptr; + int flags = MAP_ANONYMOUS|MAP_PRIVATE|MAP_HUGETLB; + + if (!hugetlb_setup_ok) + return PTR_ERR_ENOTSUP; + + dprintf1("doing %s(%ld, %x, %x)\n", __func__, size, prot, pkey); + size = ALIGN_UP(size, HPAGE_SIZE * 2); + pkey_assert(pkey < NR_PKEYS); + ptr = mmap(NULL, size, PROT_NONE, flags, -1, 0); + pkey_assert(ptr != (void *)-1); + mprotect_pkey(ptr, size, prot, pkey); + + record_pkey_malloc(ptr, size); + + dprintf1("mmap()'d hugetlbfs for pkey %d @ %p\n", pkey, ptr); + return ptr; +} + +void *malloc_pkey_mmap_dax(long size, int prot, u16 pkey) +{ + void *ptr; + int fd; + + dprintf1("doing %s(size=%ld, prot=0x%x, pkey=%d)\n", __func__, + size, prot, pkey); + pkey_assert(pkey < NR_PKEYS); + fd = open("/dax/foo", O_RDWR); + pkey_assert(fd >= 0); + + ptr = mmap(0, size, prot, MAP_SHARED, fd, 0); + pkey_assert(ptr != (void *)-1); + + mprotect_pkey(ptr, size, prot, pkey); + + record_pkey_malloc(ptr, size); + + dprintf1("mmap()'d for pkey %d @ %p\n", pkey, ptr); + close(fd); + return ptr; +} + +void *(*pkey_malloc[])(long size, int prot, u16 pkey) = { + + malloc_pkey_with_mprotect, + malloc_pkey_anon_huge, + malloc_pkey_hugetlb +/* can not do direct with the pkey_mprotect() API: + malloc_pkey_mmap_direct, + malloc_pkey_mmap_dax, +*/ +}; + +void *malloc_pkey(long size, int prot, u16 pkey) +{ + void *ret; + static int malloc_type; + int nr_malloc_types = ARRAY_SIZE(pkey_malloc); + + pkey_assert(pkey < NR_PKEYS); + + while (1) { + pkey_assert(malloc_type < nr_malloc_types); + + ret = pkey_malloc[malloc_type](size, prot, pkey); + pkey_assert(ret != (void *)-1); + + malloc_type++; + if (malloc_type >= nr_malloc_types) + malloc_type = (random()%nr_malloc_types); + + /* try again if the malloc_type we tried is unsupported */ + if (ret == PTR_ERR_ENOTSUP) + continue; + + break; + } + + dprintf3("%s(%ld, prot=%x, pkey=%x) returning: %p\n", __func__, + size, prot, pkey, ret); + return ret; +} + +int last_pkru_faults; +void expected_pk_fault(int pkey) +{ + dprintf2("%s(): last_pkru_faults: %d pkru_faults: %d\n", + __func__, last_pkru_faults, pkru_faults); + dprintf2("%s(%d): last_si_pkey: %d\n", __func__, pkey, last_si_pkey); + pkey_assert(last_pkru_faults + 1 == pkru_faults); + pkey_assert(last_si_pkey == pkey); + /* + * The signal handler shold have cleared out PKRU to let the + * test program continue. We now have to restore it. + */ + if (__rdpkru() != 0) + pkey_assert(0); + + __wrpkru(shadow_pkru); + dprintf1("%s() set PKRU=%x to restore state after signal nuked it\n", + __func__, shadow_pkru); + last_pkru_faults = pkru_faults; + last_si_pkey = -1; +} + +void do_not_expect_pk_fault(void) +{ + pkey_assert(last_pkru_faults == pkru_faults); +} + +int test_fds[10] = { -1 }; +int nr_test_fds; +void __save_test_fd(int fd) +{ + pkey_assert(fd >= 0); + pkey_assert(nr_test_fds < ARRAY_SIZE(test_fds)); + test_fds[nr_test_fds] = fd; + nr_test_fds++; +} + +int get_test_read_fd(void) +{ + int test_fd = open("/etc/passwd", O_RDONLY); + __save_test_fd(test_fd); + return test_fd; +} + +void close_test_fds(void) +{ + int i; + + for (i = 0; i < nr_test_fds; i++) { + if (test_fds[i] < 0) + continue; + close(test_fds[i]); + test_fds[i] = -1; + } + nr_test_fds = 0; +} + +#define barrier() __asm__ __volatile__("": : :"memory") +__attribute__((noinline)) int read_ptr(int *ptr) +{ + /* + * Keep GCC from optimizing this away somehow + */ + barrier(); + return *ptr; +} + +void test_read_of_write_disabled_region(int *ptr, u16 pkey) +{ + int ptr_contents; + + dprintf1("disabling write access to PKEY[1], doing read\n"); + pkey_write_deny(pkey); + ptr_contents = read_ptr(ptr); + dprintf1("*ptr: %d\n", ptr_contents); + dprintf1("\n"); +} +void test_read_of_access_disabled_region(int *ptr, u16 pkey) +{ + int ptr_contents; + + dprintf1("disabling access to PKEY[%02d], doing read @ %p\n", pkey, ptr); + rdpkru(); + pkey_access_deny(pkey); + ptr_contents = read_ptr(ptr); + dprintf1("*ptr: %d\n", ptr_contents); + expected_pk_fault(pkey); +} +void test_write_of_write_disabled_region(int *ptr, u16 pkey) +{ + dprintf1("disabling write access to PKEY[%02d], doing write\n", pkey); + pkey_write_deny(pkey); + *ptr = __LINE__; + expected_pk_fault(pkey); +} +void test_write_of_access_disabled_region(int *ptr, u16 pkey) +{ + dprintf1("disabling access to PKEY[%02d], doing write\n", pkey); + pkey_access_deny(pkey); + *ptr = __LINE__; + expected_pk_fault(pkey); +} +void test_kernel_write_of_access_disabled_region(int *ptr, u16 pkey) +{ + int ret; + int test_fd = get_test_read_fd(); + + dprintf1("disabling access to PKEY[%02d], " + "having kernel read() to buffer\n", pkey); + pkey_access_deny(pkey); + ret = read(test_fd, ptr, 1); + dprintf1("read ret: %d\n", ret); + pkey_assert(ret); +} +void test_kernel_write_of_write_disabled_region(int *ptr, u16 pkey) +{ + int ret; + int test_fd = get_test_read_fd(); + + pkey_write_deny(pkey); + ret = read(test_fd, ptr, 100); + dprintf1("read ret: %d\n", ret); + if (ret < 0 && (DEBUG_LEVEL > 0)) + perror("verbose read result (OK for this to be bad)"); + pkey_assert(ret); +} + +void test_kernel_gup_of_access_disabled_region(int *ptr, u16 pkey) +{ + int pipe_ret, vmsplice_ret; + struct iovec iov; + int pipe_fds[2]; + + pipe_ret = pipe(pipe_fds); + + pkey_assert(pipe_ret == 0); + dprintf1("disabling access to PKEY[%02d], " + "having kernel vmsplice from buffer\n", pkey); + pkey_access_deny(pkey); + iov.iov_base = ptr; + iov.iov_len = PAGE_SIZE; + vmsplice_ret = vmsplice(pipe_fds[1], &iov, 1, SPLICE_F_GIFT); + dprintf1("vmsplice() ret: %d\n", vmsplice_ret); + pkey_assert(vmsplice_ret == -1); + + close(pipe_fds[0]); + close(pipe_fds[1]); +} + +void test_kernel_gup_write_to_write_disabled_region(int *ptr, u16 pkey) +{ + int ignored = 0xdada; + int futex_ret; + int some_int = __LINE__; + + dprintf1("disabling write to PKEY[%02d], " + "doing futex gunk in buffer\n", pkey); + *ptr = some_int; + pkey_write_deny(pkey); + futex_ret = syscall(SYS_futex, ptr, FUTEX_WAIT, some_int-1, NULL, + &ignored, ignored); + if (DEBUG_LEVEL > 0) + perror("futex"); + dprintf1("futex() ret: %d\n", futex_ret); +} + +/* Assumes that all pkeys other than 'pkey' are unallocated */ +void test_pkey_syscalls_on_non_allocated_pkey(int *ptr, u16 pkey) +{ + int err; + int i; + + /* Note: 0 is the default pkey, so don't mess with it */ + for (i = 1; i < NR_PKEYS; i++) { + if (pkey == i) + continue; + + dprintf1("trying get/set/free to non-allocated pkey: %2d\n", i); + err = sys_pkey_free(i); + pkey_assert(err); + + /* not enforced when pkey_get() is not a syscall + err = pkey_get(i, 0); + pkey_assert(err < 0); + */ + + err = sys_pkey_free(i); + pkey_assert(err); + + err = sys_mprotect_pkey(ptr, PAGE_SIZE, PROT_READ, i); + pkey_assert(err); + } +} + +/* Assumes that all pkeys other than 'pkey' are unallocated */ +void test_pkey_syscalls_bad_args(int *ptr, u16 pkey) +{ + int err; + int bad_flag = (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE) + 1; + int bad_pkey = NR_PKEYS+99; + + /* not enforced when pkey_get() is not a syscall + err = pkey_get(bad_pkey, bad_flag); + pkey_assert(err < 0); + */ + + /* pass a known-invalid pkey in: */ + err = sys_mprotect_pkey(ptr, PAGE_SIZE, PROT_READ, bad_pkey); + pkey_assert(err); +} + +/* Assumes that all pkeys other than 'pkey' are unallocated */ +void test_pkey_alloc_exhaust(int *ptr, u16 pkey) +{ + unsigned long flags; + unsigned long init_val; + int err; + int allocated_pkeys[NR_PKEYS] = {0}; + int nr_allocated_pkeys = 0; + int i; + + for (i = 0; i < NR_PKEYS*2; i++) { + int new_pkey; + dprintf1("%s() alloc loop: %d\n", __func__, i); + new_pkey = alloc_pkey(); + dprintf4("%s()::%d, err: %d pkru: 0x%x shadow: 0x%x\n", __func__, + __LINE__, err, __rdpkru(), shadow_pkru); + rdpkru(); /* for shadow checking */ + dprintf2("%s() errno: %d ENOSPC: %d\n", __func__, errno, ENOSPC); + if ((new_pkey == -1) && (errno == ENOSPC)) { + dprintf2("%s() failed to allocate pkey after %d tries\n", + __func__, nr_allocated_pkeys); + break; + } + pkey_assert(nr_allocated_pkeys < NR_PKEYS); + allocated_pkeys[nr_allocated_pkeys++] = new_pkey; + } + + dprintf3("%s()::%d\n", __func__, __LINE__); + + /* + * ensure it did not reach the end of the loop without + * failure: + */ + pkey_assert(i < NR_PKEYS*2); + + /* + * There are 16 pkeys supported in hardware. One is taken + * up for the default (0) and another can be taken up by + * an execute-only mapping. Ensure that we can allocate + * at least 14 (16-2). + */ + pkey_assert(i >= NR_PKEYS-2); + + for (i = 0; i < nr_allocated_pkeys; i++) { + err = sys_pkey_free(allocated_pkeys[i]); + pkey_assert(!err); + rdpkru(); /* for shadow checking */ + } +} + +void test_ptrace_of_child(int *ptr, u16 pkey) +{ + __attribute__((__unused__)) int peek_result; + pid_t child_pid; + void *ignored = 0; + long ret; + int status; + /* + * This is the "control" for our little expermient. Make sure + * we can always access it when ptracing. + */ + int *plain_ptr_unaligned = malloc(HPAGE_SIZE); + int *plain_ptr = ALIGN_PTR_UP(plain_ptr_unaligned, PAGE_SIZE); + + /* + * Fork a child which is an exact copy of this process, of course. + * That means we can do all of our tests via ptrace() and then plain + * memory access and ensure they work differently. + */ + child_pid = fork_lazy_child(); + dprintf1("[%d] child pid: %d\n", getpid(), child_pid); + + ret = ptrace(PTRACE_ATTACH, child_pid, ignored, ignored); + if (ret) + perror("attach"); + dprintf1("[%d] attach ret: %ld %d\n", getpid(), ret, __LINE__); + pkey_assert(ret != -1); + ret = waitpid(child_pid, &status, WUNTRACED); + if ((ret != child_pid) || !(WIFSTOPPED(status))) { + fprintf(stderr, "weird waitpid result %ld stat %x\n", + ret, status); + pkey_assert(0); + } + dprintf2("waitpid ret: %ld\n", ret); + dprintf2("waitpid status: %d\n", status); + + pkey_access_deny(pkey); + pkey_write_deny(pkey); + + /* Write access, untested for now: + ret = ptrace(PTRACE_POKEDATA, child_pid, peek_at, data); + pkey_assert(ret != -1); + dprintf1("poke at %p: %ld\n", peek_at, ret); + */ + + /* + * Try to access the pkey-protected "ptr" via ptrace: + */ + ret = ptrace(PTRACE_PEEKDATA, child_pid, ptr, ignored); + /* expect it to work, without an error: */ + pkey_assert(ret != -1); + /* Now access from the current task, and expect an exception: */ + peek_result = read_ptr(ptr); + expected_pk_fault(pkey); + + /* + * Try to access the NON-pkey-protected "plain_ptr" via ptrace: + */ + ret = ptrace(PTRACE_PEEKDATA, child_pid, plain_ptr, ignored); + /* expect it to work, without an error: */ + pkey_assert(ret != -1); + /* Now access from the current task, and expect NO exception: */ + peek_result = read_ptr(plain_ptr); + do_not_expect_pk_fault(); + + ret = ptrace(PTRACE_DETACH, child_pid, ignored, 0); + pkey_assert(ret != -1); + + ret = kill(child_pid, SIGKILL); + pkey_assert(ret != -1); + + wait(&status); + + free(plain_ptr_unaligned); +} + +void test_executing_on_unreadable_memory(int *ptr, u16 pkey) +{ + void *p1; + int scratch; + int ptr_contents; + int ret; + + p1 = ALIGN_PTR_UP(&lots_o_noops_around_write, PAGE_SIZE); + dprintf3("&lots_o_noops: %p\n", &lots_o_noops_around_write); + /* lots_o_noops_around_write should be page-aligned already */ + assert(p1 == &lots_o_noops_around_write); + + /* Point 'p1' at the *second* page of the function: */ + p1 += PAGE_SIZE; + + madvise(p1, PAGE_SIZE, MADV_DONTNEED); + lots_o_noops_around_write(&scratch); + ptr_contents = read_ptr(p1); + dprintf2("ptr (%p) contents@%d: %x\n", p1, __LINE__, ptr_contents); + + ret = mprotect_pkey(p1, PAGE_SIZE, PROT_EXEC, (u64)pkey); + pkey_assert(!ret); + pkey_access_deny(pkey); + + dprintf2("pkru: %x\n", rdpkru()); + + /* + * Make sure this is an *instruction* fault + */ + madvise(p1, PAGE_SIZE, MADV_DONTNEED); + lots_o_noops_around_write(&scratch); + do_not_expect_pk_fault(); + ptr_contents = read_ptr(p1); + dprintf2("ptr (%p) contents@%d: %x\n", p1, __LINE__, ptr_contents); + expected_pk_fault(pkey); +} + +void test_mprotect_pkey_on_unsupported_cpu(int *ptr, u16 pkey) +{ + int size = PAGE_SIZE; + int sret; + + if (cpu_has_pku()) { + dprintf1("SKIP: %s: no CPU support\n", __func__); + return; + } + + sret = syscall(SYS_mprotect_key, ptr, size, PROT_READ, pkey); + pkey_assert(sret < 0); +} + +void (*pkey_tests[])(int *ptr, u16 pkey) = { + test_read_of_write_disabled_region, + test_read_of_access_disabled_region, + test_write_of_write_disabled_region, + test_write_of_access_disabled_region, + test_kernel_write_of_access_disabled_region, + test_kernel_write_of_write_disabled_region, + test_kernel_gup_of_access_disabled_region, + test_kernel_gup_write_to_write_disabled_region, + test_executing_on_unreadable_memory, + test_ptrace_of_child, + test_pkey_syscalls_on_non_allocated_pkey, + test_pkey_syscalls_bad_args, + test_pkey_alloc_exhaust, +}; + +void run_tests_once(void) +{ + int *ptr; + int prot = PROT_READ|PROT_WRITE; + + for (test_nr = 0; test_nr < ARRAY_SIZE(pkey_tests); test_nr++) { + int pkey; + int orig_pkru_faults = pkru_faults; + + dprintf1("======================\n"); + dprintf1("test %d preparing...\n", test_nr); + + tracing_on(); + pkey = alloc_random_pkey(); + dprintf1("test %d starting with pkey: %d\n", test_nr, pkey); + ptr = malloc_pkey(PAGE_SIZE, prot, pkey); + dprintf1("test %d starting...\n", test_nr); + pkey_tests[test_nr](ptr, pkey); + dprintf1("freeing test memory: %p\n", ptr); + free_pkey_malloc(ptr); + sys_pkey_free(pkey); + + dprintf1("pkru_faults: %d\n", pkru_faults); + dprintf1("orig_pkru_faults: %d\n", orig_pkru_faults); + + tracing_off(); + close_test_fds(); + + printf("test %2d PASSED (itertation %d)\n", test_nr, iteration_nr); + dprintf1("======================\n\n"); + } + iteration_nr++; +} + +void pkey_setup_shadow(void) +{ + shadow_pkru = __rdpkru(); +} + +int main(void) +{ + int nr_iterations = 22; + + setup_handlers(); + + printf("has pku: %d\n", cpu_has_pku()); + + if (!cpu_has_pku()) { + int size = PAGE_SIZE; + int *ptr; + + printf("running PKEY tests for unsupported CPU/OS\n"); + + ptr = mmap(NULL, size, PROT_NONE, MAP_ANONYMOUS|MAP_PRIVATE, -1, 0); + assert(ptr != (void *)-1); + test_mprotect_pkey_on_unsupported_cpu(ptr, 1); + exit(0); + } + + pkey_setup_shadow(); + printf("startup pkru: %x\n", rdpkru()); + setup_hugetlbfs(); + + while (nr_iterations-- > 0) + run_tests_once(); + + printf("done (all tests OK)\n"); + return 0; +} diff --git a/tools/testing/selftests/x86/ptrace_syscall.c b/tools/testing/selftests/x86/ptrace_syscall.c index 421456784bc6..b037ce9cf116 100644 --- a/tools/testing/selftests/x86/ptrace_syscall.c +++ b/tools/testing/selftests/x86/ptrace_syscall.c @@ -147,7 +147,7 @@ static void test_sys32_regs(void (*do_syscall)(struct syscall_args32 *)) if (args.nr != getpid() || args.arg0 != 10 || args.arg1 != 11 || args.arg2 != 12 || args.arg3 != 13 || args.arg4 != 14 || args.arg5 != 15) { - printf("[FAIL]\tgetpid() failed to preseve regs\n"); + printf("[FAIL]\tgetpid() failed to preserve regs\n"); nerrs++; } else { printf("[OK]\tgetpid() preserves regs\n"); @@ -162,7 +162,7 @@ static void test_sys32_regs(void (*do_syscall)(struct syscall_args32 *)) if (args.nr != 0 || args.arg0 != getpid() || args.arg1 != SIGUSR1 || args.arg2 != 12 || args.arg3 != 13 || args.arg4 != 14 || args.arg5 != 15) { - printf("[FAIL]\tkill(getpid(), SIGUSR1) failed to preseve regs\n"); + printf("[FAIL]\tkill(getpid(), SIGUSR1) failed to preserve regs\n"); nerrs++; } else { printf("[OK]\tkill(getpid(), SIGUSR1) preserves regs\n"); diff --git a/tools/testing/selftests/x86/sigreturn.c b/tools/testing/selftests/x86/sigreturn.c index 8a577e7070c6..246145b84a12 100644 --- a/tools/testing/selftests/x86/sigreturn.c +++ b/tools/testing/selftests/x86/sigreturn.c @@ -106,7 +106,7 @@ asm (".pushsection .text\n\t" ".type int3, @function\n\t" ".align 4096\n\t" "int3:\n\t" - "mov %ss,%eax\n\t" + "mov %ss,%ecx\n\t" "int3\n\t" ".size int3, . - int3\n\t" ".align 4096, 0xcc\n\t" @@ -306,7 +306,7 @@ static volatile sig_atomic_t sig_corrupt_final_ss; #ifdef __x86_64__ # define REG_IP REG_RIP # define REG_SP REG_RSP -# define REG_AX REG_RAX +# define REG_CX REG_RCX struct selectors { unsigned short cs, gs, fs, ss; @@ -326,7 +326,7 @@ static unsigned short *csptr(ucontext_t *ctx) #else # define REG_IP REG_EIP # define REG_SP REG_ESP -# define REG_AX REG_EAX +# define REG_CX REG_ECX static greg_t *ssptr(ucontext_t *ctx) { @@ -457,10 +457,10 @@ static void sigusr1(int sig, siginfo_t *info, void *ctx_void) ctx->uc_mcontext.gregs[REG_IP] = sig_cs == code16_sel ? 0 : (unsigned long)&int3; ctx->uc_mcontext.gregs[REG_SP] = (unsigned long)0x8badf00d5aadc0deULL; - ctx->uc_mcontext.gregs[REG_AX] = 0; + ctx->uc_mcontext.gregs[REG_CX] = 0; memcpy(&requested_regs, &ctx->uc_mcontext.gregs, sizeof(gregset_t)); - requested_regs[REG_AX] = *ssptr(ctx); /* The asm code does this. */ + requested_regs[REG_CX] = *ssptr(ctx); /* The asm code does this. */ return; } @@ -482,7 +482,7 @@ static void sigtrap(int sig, siginfo_t *info, void *ctx_void) unsigned short ss; asm ("mov %%ss,%0" : "=r" (ss)); - greg_t asm_ss = ctx->uc_mcontext.gregs[REG_AX]; + greg_t asm_ss = ctx->uc_mcontext.gregs[REG_CX]; if (asm_ss != sig_ss && sig == SIGTRAP) { /* Sanity check failure. */ printf("[FAIL]\tSIGTRAP: ss = %hx, frame ss = %hx, ax = %llx\n", @@ -654,8 +654,8 @@ static int test_valid_sigreturn(int cs_bits, bool use_16bit_ss, int force_ss) #endif /* Sanity check on the kernel */ - if (i == REG_AX && requested_regs[i] != resulting_regs[i]) { - printf("[FAIL]\tAX (saved SP) mismatch: requested 0x%llx; got 0x%llx\n", + if (i == REG_CX && requested_regs[i] != resulting_regs[i]) { + printf("[FAIL]\tCX (saved SP) mismatch: requested 0x%llx; got 0x%llx\n", (unsigned long long)requested_regs[i], (unsigned long long)resulting_regs[i]); nerrs++; |