diff options
Diffstat (limited to 'tools')
| -rw-r--r-- | tools/testing/nvdimm/Kbuild | 13 | ||||
| -rw-r--r-- | tools/testing/nvdimm/test/iomap.c | 85 | ||||
| -rw-r--r-- | tools/testing/nvdimm/test/nfit.c | 209 | ||||
| -rw-r--r-- | tools/testing/selftests/capabilities/.gitignore | 2 | ||||
| -rw-r--r-- | tools/testing/selftests/capabilities/Makefile | 18 | ||||
| -rw-r--r-- | tools/testing/selftests/capabilities/test_execve.c | 427 | ||||
| -rw-r--r-- | tools/testing/selftests/capabilities/validate_cap.c | 73 | ||||
| -rw-r--r-- | tools/testing/selftests/vm/Makefile | 3 | ||||
| -rwxr-xr-x | tools/testing/selftests/vm/run_vmtests | 11 | ||||
| -rw-r--r-- | tools/testing/selftests/vm/userfaultfd.c | 636 |
10 files changed, 1401 insertions, 76 deletions
diff --git a/tools/testing/nvdimm/Kbuild b/tools/testing/nvdimm/Kbuild index f56914c7929b..38b00ecb2ed5 100644 --- a/tools/testing/nvdimm/Kbuild +++ b/tools/testing/nvdimm/Kbuild @@ -1,9 +1,12 @@ -ldflags-y += --wrap=ioremap_wt ldflags-y += --wrap=ioremap_wc +ldflags-y += --wrap=memremap ldflags-y += --wrap=devm_ioremap_nocache -ldflags-y += --wrap=ioremap_cache +ldflags-y += --wrap=devm_memremap +ldflags-y += --wrap=devm_memunmap ldflags-y += --wrap=ioremap_nocache ldflags-y += --wrap=iounmap +ldflags-y += --wrap=memunmap +ldflags-y += --wrap=__devm_request_region ldflags-y += --wrap=__request_region ldflags-y += --wrap=__release_region @@ -15,6 +18,7 @@ obj-$(CONFIG_LIBNVDIMM) += libnvdimm.o obj-$(CONFIG_BLK_DEV_PMEM) += nd_pmem.o obj-$(CONFIG_ND_BTT) += nd_btt.o obj-$(CONFIG_ND_BLK) += nd_blk.o +obj-$(CONFIG_X86_PMEM_LEGACY) += nd_e820.o obj-$(CONFIG_ACPI_NFIT) += nfit.o nfit-y := $(ACPI_SRC)/nfit.o @@ -29,6 +33,9 @@ nd_btt-y += config_check.o nd_blk-y := $(NVDIMM_SRC)/blk.o nd_blk-y += config_check.o +nd_e820-y := $(NVDIMM_SRC)/e820.o +nd_e820-y += config_check.o + libnvdimm-y := $(NVDIMM_SRC)/core.o libnvdimm-y += $(NVDIMM_SRC)/bus.o libnvdimm-y += $(NVDIMM_SRC)/dimm_devs.o @@ -37,7 +44,9 @@ libnvdimm-y += $(NVDIMM_SRC)/region_devs.o libnvdimm-y += $(NVDIMM_SRC)/region.o libnvdimm-y += $(NVDIMM_SRC)/namespace_devs.o libnvdimm-y += $(NVDIMM_SRC)/label.o +libnvdimm-$(CONFIG_ND_CLAIM) += $(NVDIMM_SRC)/claim.o libnvdimm-$(CONFIG_BTT) += $(NVDIMM_SRC)/btt_devs.o +libnvdimm-$(CONFIG_NVDIMM_PFN) += $(NVDIMM_SRC)/pfn_devs.o libnvdimm-y += config_check.o obj-m += test/ diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c index 64bfaa50831c..b7251314bbc0 100644 --- a/tools/testing/nvdimm/test/iomap.c +++ b/tools/testing/nvdimm/test/iomap.c @@ -80,23 +80,52 @@ void __iomem *__wrap_devm_ioremap_nocache(struct device *dev, } EXPORT_SYMBOL(__wrap_devm_ioremap_nocache); -void __iomem *__wrap_ioremap_cache(resource_size_t offset, unsigned long size) +void *__wrap_devm_memremap(struct device *dev, resource_size_t offset, + size_t size, unsigned long flags) { - return __nfit_test_ioremap(offset, size, ioremap_cache); + struct nfit_test_resource *nfit_res; + + rcu_read_lock(); + nfit_res = get_nfit_res(offset); + rcu_read_unlock(); + if (nfit_res) + return nfit_res->buf + offset - nfit_res->res->start; + return devm_memremap(dev, offset, size, flags); } -EXPORT_SYMBOL(__wrap_ioremap_cache); +EXPORT_SYMBOL(__wrap_devm_memremap); -void __iomem *__wrap_ioremap_nocache(resource_size_t offset, unsigned long size) +void *__wrap_memremap(resource_size_t offset, size_t size, + unsigned long flags) { - return __nfit_test_ioremap(offset, size, ioremap_nocache); + struct nfit_test_resource *nfit_res; + + rcu_read_lock(); + nfit_res = get_nfit_res(offset); + rcu_read_unlock(); + if (nfit_res) + return nfit_res->buf + offset - nfit_res->res->start; + return memremap(offset, size, flags); } -EXPORT_SYMBOL(__wrap_ioremap_nocache); +EXPORT_SYMBOL(__wrap_memremap); + +void __wrap_devm_memunmap(struct device *dev, void *addr) +{ + struct nfit_test_resource *nfit_res; + + rcu_read_lock(); + nfit_res = get_nfit_res((unsigned long) addr); + rcu_read_unlock(); + if (nfit_res) + return; + return devm_memunmap(dev, addr); +} +EXPORT_SYMBOL(__wrap_devm_memunmap); -void __iomem *__wrap_ioremap_wt(resource_size_t offset, unsigned long size) +void __iomem *__wrap_ioremap_nocache(resource_size_t offset, unsigned long size) { - return __nfit_test_ioremap(offset, size, ioremap_wt); + return __nfit_test_ioremap(offset, size, ioremap_nocache); } -EXPORT_SYMBOL(__wrap_ioremap_wt); +EXPORT_SYMBOL(__wrap_ioremap_nocache); void __iomem *__wrap_ioremap_wc(resource_size_t offset, unsigned long size) { @@ -117,9 +146,22 @@ void __wrap_iounmap(volatile void __iomem *addr) } EXPORT_SYMBOL(__wrap_iounmap); -struct resource *__wrap___request_region(struct resource *parent, - resource_size_t start, resource_size_t n, const char *name, - int flags) +void __wrap_memunmap(void *addr) +{ + struct nfit_test_resource *nfit_res; + + rcu_read_lock(); + nfit_res = get_nfit_res((unsigned long) addr); + rcu_read_unlock(); + if (nfit_res) + return; + return memunmap(addr); +} +EXPORT_SYMBOL(__wrap_memunmap); + +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) { struct nfit_test_resource *nfit_res; @@ -147,10 +189,29 @@ struct resource *__wrap___request_region(struct resource *parent, return res; } } + if (dev) + return __devm_request_region(dev, parent, start, n, name); return __request_region(parent, start, n, name, flags); } + +struct resource *__wrap___request_region(struct resource *parent, + resource_size_t start, resource_size_t n, const char *name, + int flags) +{ + return nfit_test_request_region(NULL, parent, start, n, name, flags); +} EXPORT_SYMBOL(__wrap___request_region); +struct resource *__wrap___devm_request_region(struct device *dev, + struct resource *parent, resource_size_t start, + resource_size_t n, const char *name) +{ + if (!dev) + return NULL; + return nfit_test_request_region(dev, parent, start, n, name, 0); +} +EXPORT_SYMBOL(__wrap___devm_request_region); + void __wrap___release_region(struct resource *parent, resource_size_t start, resource_size_t n) { diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index d0bdae40ccc9..021e6f97f33e 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -147,75 +147,153 @@ static struct nfit_test *to_nfit_test(struct device *dev) return container_of(pdev, struct nfit_test, pdev); } +static int nfit_test_cmd_get_config_size(struct nd_cmd_get_config_size *nd_cmd, + unsigned int buf_len) +{ + if (buf_len < sizeof(*nd_cmd)) + return -EINVAL; + + nd_cmd->status = 0; + nd_cmd->config_size = LABEL_SIZE; + nd_cmd->max_xfer = SZ_4K; + + return 0; +} + +static int nfit_test_cmd_get_config_data(struct nd_cmd_get_config_data_hdr + *nd_cmd, unsigned int buf_len, void *label) +{ + unsigned int len, offset = nd_cmd->in_offset; + int rc; + + if (buf_len < sizeof(*nd_cmd)) + return -EINVAL; + if (offset >= LABEL_SIZE) + return -EINVAL; + if (nd_cmd->in_length + sizeof(*nd_cmd) > buf_len) + return -EINVAL; + + nd_cmd->status = 0; + len = min(nd_cmd->in_length, LABEL_SIZE - offset); + memcpy(nd_cmd->out_buf, label + offset, len); + rc = buf_len - sizeof(*nd_cmd) - len; + + return rc; +} + +static int nfit_test_cmd_set_config_data(struct nd_cmd_set_config_hdr *nd_cmd, + unsigned int buf_len, void *label) +{ + unsigned int len, offset = nd_cmd->in_offset; + u32 *status; + int rc; + + if (buf_len < sizeof(*nd_cmd)) + return -EINVAL; + if (offset >= LABEL_SIZE) + return -EINVAL; + if (nd_cmd->in_length + sizeof(*nd_cmd) + 4 > buf_len) + return -EINVAL; + + status = (void *)nd_cmd + nd_cmd->in_length + sizeof(*nd_cmd); + *status = 0; + len = min(nd_cmd->in_length, LABEL_SIZE - offset); + memcpy(label + offset, nd_cmd->in_buf, len); + rc = buf_len - sizeof(*nd_cmd) - (len + 4); + + return rc; +} + +static int nfit_test_cmd_ars_cap(struct nd_cmd_ars_cap *nd_cmd, + unsigned int buf_len) +{ + if (buf_len < sizeof(*nd_cmd)) + return -EINVAL; + + nd_cmd->max_ars_out = 256; + nd_cmd->status = (ND_ARS_PERSISTENT | ND_ARS_VOLATILE) << 16; + + return 0; +} + +static int nfit_test_cmd_ars_start(struct nd_cmd_ars_start *nd_cmd, + unsigned int buf_len) +{ + if (buf_len < sizeof(*nd_cmd)) + return -EINVAL; + + nd_cmd->status = 0; + + return 0; +} + +static int nfit_test_cmd_ars_status(struct nd_cmd_ars_status *nd_cmd, + unsigned int buf_len) +{ + if (buf_len < sizeof(*nd_cmd)) + return -EINVAL; + + nd_cmd->out_length = 256; + nd_cmd->num_records = 0; + nd_cmd->status = 0; + + return 0; +} + static int nfit_test_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, unsigned int cmd, void *buf, unsigned int buf_len) { struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc); struct nfit_test *t = container_of(acpi_desc, typeof(*t), acpi_desc); - struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm); - int i, rc; + int i, rc = 0; - if (!nfit_mem || !test_bit(cmd, &nfit_mem->dsm_mask)) - return -ENOTTY; + if (nvdimm) { + struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm); - /* lookup label space for the given dimm */ - for (i = 0; i < ARRAY_SIZE(handle); i++) - if (__to_nfit_memdev(nfit_mem)->device_handle == handle[i]) + if (!nfit_mem || !test_bit(cmd, &nfit_mem->dsm_mask)) + return -ENOTTY; + + /* lookup label space for the given dimm */ + for (i = 0; i < ARRAY_SIZE(handle); i++) + if (__to_nfit_memdev(nfit_mem)->device_handle == + handle[i]) + break; + if (i >= ARRAY_SIZE(handle)) + return -ENXIO; + + switch (cmd) { + case ND_CMD_GET_CONFIG_SIZE: + rc = nfit_test_cmd_get_config_size(buf, buf_len); break; - if (i >= ARRAY_SIZE(handle)) - return -ENXIO; + case ND_CMD_GET_CONFIG_DATA: + rc = nfit_test_cmd_get_config_data(buf, buf_len, + t->label[i]); + break; + case ND_CMD_SET_CONFIG_DATA: + rc = nfit_test_cmd_set_config_data(buf, buf_len, + t->label[i]); + break; + default: + return -ENOTTY; + } + } else { + if (!nd_desc || !test_bit(cmd, &nd_desc->dsm_mask)) + return -ENOTTY; - switch (cmd) { - case ND_CMD_GET_CONFIG_SIZE: { - struct nd_cmd_get_config_size *nd_cmd = buf; - - if (buf_len < sizeof(*nd_cmd)) - return -EINVAL; - nd_cmd->status = 0; - nd_cmd->config_size = LABEL_SIZE; - nd_cmd->max_xfer = SZ_4K; - rc = 0; - break; - } - case ND_CMD_GET_CONFIG_DATA: { - struct nd_cmd_get_config_data_hdr *nd_cmd = buf; - unsigned int len, offset = nd_cmd->in_offset; - - if (buf_len < sizeof(*nd_cmd)) - return -EINVAL; - if (offset >= LABEL_SIZE) - return -EINVAL; - if (nd_cmd->in_length + sizeof(*nd_cmd) > buf_len) - return -EINVAL; - - nd_cmd->status = 0; - len = min(nd_cmd->in_length, LABEL_SIZE - offset); - memcpy(nd_cmd->out_buf, t->label[i] + offset, len); - rc = buf_len - sizeof(*nd_cmd) - len; - break; - } - case ND_CMD_SET_CONFIG_DATA: { - struct nd_cmd_set_config_hdr *nd_cmd = buf; - unsigned int len, offset = nd_cmd->in_offset; - u32 *status; - - if (buf_len < sizeof(*nd_cmd)) - return -EINVAL; - if (offset >= LABEL_SIZE) - return -EINVAL; - if (nd_cmd->in_length + sizeof(*nd_cmd) + 4 > buf_len) - return -EINVAL; - - status = buf + nd_cmd->in_length + sizeof(*nd_cmd); - *status = 0; - len = min(nd_cmd->in_length, LABEL_SIZE - offset); - memcpy(t->label[i] + offset, nd_cmd->in_buf, len); - rc = buf_len - sizeof(*nd_cmd) - (len + 4); - break; - } - default: - return -ENOTTY; + switch (cmd) { + case ND_CMD_ARS_CAP: + rc = nfit_test_cmd_ars_cap(buf, buf_len); + break; + case ND_CMD_ARS_START: + rc = nfit_test_cmd_ars_start(buf, buf_len); + break; + case ND_CMD_ARS_STATUS: + rc = nfit_test_cmd_ars_status(buf, buf_len); + break; + default: + return -ENOTTY; + } } return rc; @@ -876,6 +954,9 @@ static void nfit_test0_setup(struct nfit_test *t) set_bit(ND_CMD_GET_CONFIG_SIZE, &acpi_desc->dimm_dsm_force_en); set_bit(ND_CMD_GET_CONFIG_DATA, &acpi_desc->dimm_dsm_force_en); set_bit(ND_CMD_SET_CONFIG_DATA, &acpi_desc->dimm_dsm_force_en); + set_bit(ND_CMD_ARS_CAP, &acpi_desc->bus_dsm_force_en); + set_bit(ND_CMD_ARS_START, &acpi_desc->bus_dsm_force_en); + set_bit(ND_CMD_ARS_STATUS, &acpi_desc->bus_dsm_force_en); nd_desc = &acpi_desc->nd_desc; nd_desc->ndctl = nfit_test_ctl; } @@ -948,9 +1029,13 @@ static int nfit_test_blk_do_io(struct nd_blk_region *ndbr, resource_size_t dpa, lane = nd_region_acquire_lane(nd_region); if (rw) - memcpy(mmio->base + dpa, iobuf, len); - else - memcpy(iobuf, mmio->base + dpa, len); + memcpy(mmio->addr.base + dpa, iobuf, len); + else { + memcpy(iobuf, mmio->addr.base + dpa, len); + + /* give us some some coverage of the mmio_flush_range() API */ + mmio_flush_range(mmio->addr.base + dpa, len); + } nd_region_release_lane(nd_region, lane); return 0; diff --git a/tools/testing/selftests/capabilities/.gitignore b/tools/testing/selftests/capabilities/.gitignore new file mode 100644 index 000000000000..b732dd0d4738 --- /dev/null +++ b/tools/testing/selftests/capabilities/.gitignore @@ -0,0 +1,2 @@ +test_execve +validate_cap diff --git a/tools/testing/selftests/capabilities/Makefile b/tools/testing/selftests/capabilities/Makefile new file mode 100644 index 000000000000..8c8f0c1f0889 --- /dev/null +++ b/tools/testing/selftests/capabilities/Makefile @@ -0,0 +1,18 @@ +all: + +include ../lib.mk + +.PHONY: all clean + +TARGETS := validate_cap test_execve +TEST_PROGS := test_execve + +CFLAGS := -O2 -g -std=gnu99 -Wall -lcap-ng + +all: $(TARGETS) + +clean: + $(RM) $(TARGETS) + +$(TARGETS): %: %.c + $(CC) -o $@ $(CFLAGS) $(EXTRA_CFLAGS) $^ -lrt -ldl diff --git a/tools/testing/selftests/capabilities/test_execve.c b/tools/testing/selftests/capabilities/test_execve.c new file mode 100644 index 000000000000..10a21a958aaf --- /dev/null +++ b/tools/testing/selftests/capabilities/test_execve.c @@ -0,0 +1,427 @@ +#define _GNU_SOURCE + +#include <cap-ng.h> +#include <err.h> +#include <linux/capability.h> +#include <stdbool.h> +#include <string.h> +#include <stdio.h> +#include <fcntl.h> +#include <errno.h> +#include <stdarg.h> +#include <sched.h> +#include <sys/mount.h> +#include <limits.h> +#include <libgen.h> +#include <malloc.h> +#include <sys/wait.h> +#include <sys/prctl.h> +#include <sys/stat.h> + +#ifndef PR_CAP_AMBIENT +#define PR_CAP_AMBIENT 47 +# define PR_CAP_AMBIENT_IS_SET 1 +# define PR_CAP_AMBIENT_RAISE 2 +# define PR_CAP_AMBIENT_LOWER 3 +# define PR_CAP_AMBIENT_CLEAR_ALL 4 +#endif + +static int nerrs; + +static void vmaybe_write_file(bool enoent_ok, char *filename, char *fmt, va_list ap) +{ + char buf[4096]; + int fd; + ssize_t written; + int buf_len; + + buf_len = vsnprintf(buf, sizeof(buf), fmt, ap); + if (buf_len < 0) { + err(1, "vsnprintf failed"); + } + if (buf_len >= sizeof(buf)) { + errx(1, "vsnprintf output truncated"); + } + + fd = open(filename, O_WRONLY); + if (fd < 0) { + if ((errno == ENOENT) && enoent_ok) + return; + err(1, "open of %s failed", filename); + } + written = write(fd, buf, buf_len); + if (written != buf_len) { + if (written >= 0) { + errx(1, "short write to %s", filename); + } else { + err(1, "write to %s failed", filename); + } + } + if (close(fd) != 0) { + err(1, "close of %s failed", filename); + } +} + +static void maybe_write_file(char *filename, char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + vmaybe_write_file(true, filename, fmt, ap); + va_end(ap); +} + +static void write_file(char *filename, char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + vmaybe_write_file(false, filename, fmt, ap); + va_end(ap); +} + +static bool create_and_enter_ns(uid_t inner_uid) +{ + uid_t outer_uid; + gid_t outer_gid; + int i; + bool have_outer_privilege; + + outer_uid = getuid(); + outer_gid = getgid(); + + /* + * TODO: If we're already root, we could skip creating the userns. + */ + + if (unshare(CLONE_NEWNS) == 0) { + printf("[NOTE]\tUsing global UIDs for tests\n"); + if (prctl(PR_SET_KEEPCAPS, 1, 0, 0, 0) != 0) + err(1, "PR_SET_KEEPCAPS"); + if (setresuid(inner_uid, inner_uid, -1) != 0) + err(1, "setresuid"); + + // Re-enable effective caps + capng_get_caps_process(); + for (i = 0; i < CAP_LAST_CAP; i++) + if (capng_have_capability(CAPNG_PERMITTED, i)) + capng_update(CAPNG_ADD, CAPNG_EFFECTIVE, i); + if (capng_apply(CAPNG_SELECT_CAPS) != 0) + err(1, "capng_apply"); + + have_outer_privilege = true; + } else if (unshare(CLONE_NEWUSER | CLONE_NEWNS) == 0) { + printf("[NOTE]\tUsing a user namespace for tests\n"); + maybe_write_file("/proc/self/setgroups", "deny"); + write_file("/proc/self/uid_map", "%d %d 1", inner_uid, outer_uid); + write_file("/proc/self/gid_map", "0 %d 1", outer_gid); + + have_outer_privilege = false; + } else { + errx(1, "must be root or be able to create a userns"); + } + + if (mount("none", "/", NULL, MS_REC | MS_PRIVATE, NULL) != 0) + err(1, "remount everything private"); + + return have_outer_privilege; +} + +static void chdir_to_tmpfs(void) +{ + char cwd[PATH_MAX]; + if (getcwd(cwd, sizeof(cwd)) != cwd) + err(1, "getcwd"); + + if (mount("private_tmp", ".", "tmpfs", 0, "mode=0777") != 0) + err(1, "mount private tmpfs"); + + if (chdir(cwd) != 0) + err(1, "chdir to private tmpfs"); + + if (umount2(".", MNT_DETACH) != 0) + err(1, "detach private tmpfs"); +} + +static void copy_fromat_to(int fromfd, const char *fromname, const char *toname) +{ + int from = openat(fromfd, fromname, O_RDONLY); + if (from == -1) + err(1, "open copy source"); + + int to = open(toname, O_CREAT | O_WRONLY | O_EXCL, 0700); + + while (true) { + char buf[4096]; + ssize_t sz = read(from, buf, sizeof(buf)); + if (sz == 0) + break; + if (sz < 0) + err(1, "read"); + + if (write(to, buf, sz) != sz) + err(1, "write"); /* no short writes on tmpfs */ + } + + close(from); + close(to); +} + +static bool fork_wait(void) +{ + pid_t child = fork(); + if (child == 0) { + nerrs = 0; + return true; + } else if (child > 0) { + int status; + if (waitpid(child, &status, 0) != child || + !WIFEXITED(status)) { + printf("[FAIL]\tChild died\n"); + nerrs++; + } else if (WEXITSTATUS(status) != 0) { + printf("[FAIL]\tChild failed\n"); + nerrs++; + } else { + printf("[OK]\tChild succeeded\n"); + } + + return false; + } else { + err(1, "fork"); + } +} + +static void exec_other_validate_cap(const char *name, + bool eff, bool perm, bool inh, bool ambient) +{ + execl(name, name, (eff ? "1" : "0"), + (perm ? "1" : "0"), (inh ? "1" : "0"), (ambient ? "1" : "0"), + NULL); + err(1, "execl"); +} + +static void exec_validate_cap(bool eff, bool perm, bool inh, bool ambient) +{ + exec_other_validate_cap("./validate_cap", eff, perm, inh, ambient); +} + +static int do_tests(int uid, const char *our_path) +{ + bool have_outer_privilege = create_and_enter_ns(uid); + + int ourpath_fd = open(our_path, O_RDONLY | O_DIRECTORY); + if (ourpath_fd == -1) + err(1, "open '%s'", our_path); + + chdir_to_tmpfs(); + + copy_fromat_to(ourpath_fd, "validate_cap", "validate_cap"); + + if (have_outer_privilege) { + uid_t gid = getegid(); + + copy_fromat_to(ourpath_fd, "validate_cap", + "validate_cap_suidroot"); + if (chown("validate_cap_suidroot", 0, -1) != 0) + err(1, "chown"); + if (chmod("validate_cap_suidroot", S_ISUID | 0700) != 0) + err(1, "chmod"); + + copy_fromat_to(ourpath_fd, "validate_cap", + "validate_cap_suidnonroot"); + if (chown("validate_cap_suidnonroot", uid + 1, -1) != 0) + err(1, "chown"); + if (chmod("validate_cap_suidnonroot", S_ISUID | 0700) != 0) + err(1, "chmod"); + + copy_fromat_to(ourpath_fd, "validate_cap", + "validate_cap_sgidroot"); + if (chown("validate_cap_sgidroot", -1, 0) != 0) + err(1, "chown"); + if (chmod("validate_cap_sgidroot", S_ISGID | 0710) != 0) + err(1, "chmod"); + + copy_fromat_to(ourpath_fd, "validate_cap", + "validate_cap_sgidnonroot"); + if (chown("validate_cap_sgidnonroot", -1, gid + 1) != 0) + err(1, "chown"); + if (chmod("validate_cap_sgidnonroot", S_ISGID | 0710) != 0) + err(1, "chmod"); +} + + capng_get_caps_process(); + + /* Make sure that i starts out clear */ + capng_update(CAPNG_DROP, CAPNG_INHERITABLE, CAP_NET_BIND_SERVICE); + if (capng_apply(CAPNG_SELECT_CAPS) != 0) + err(1, "capng_apply"); + + if (uid == 0) { + printf("[RUN]\tRoot => ep\n"); + if (fork_wait()) + exec_validate_cap(true, true, false, false); + } else { + printf("[RUN]\tNon-root => no caps\n"); + if (fork_wait()) + exec_validate_cap(false, false, false, false); + } + + printf("[OK]\tCheck cap_ambient manipulation rules\n"); + + /* We should not be able to add ambient caps yet. */ + if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_RAISE, CAP_NET_BIND_SERVICE, 0, 0, 0) != -1 || errno != EPERM) { + if (errno == EINVAL) + printf("[FAIL]\tPR_CAP_AMBIENT_RAISE isn't supported\n"); + else + printf("[FAIL]\tPR_CAP_AMBIENT_RAISE should have failed eith EPERM on a non-inheritable cap\n"); + return 1; + } + printf("[OK]\tPR_CAP_AMBIENT_RAISE failed on non-inheritable cap\n"); + + capng_update(CAPNG_ADD, CAPNG_INHERITABLE, CAP_NET_RAW); + capng_update(CAPNG_DROP, CAPNG_PERMITTED, CAP_NET_RAW); + capng_update(CAPNG_DROP, CAPNG_EFFECTIVE, CAP_NET_RAW); + if (capng_apply(CAPNG_SELECT_CAPS) != 0) + err(1, "capng_apply"); + if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_RAISE, CAP_NET_RAW, 0, 0, 0) != -1 || errno != EPERM) { + printf("[FAIL]\tPR_CAP_AMBIENT_RAISE should have failed on a non-permitted cap\n"); + return 1; + } + printf("[OK]\tPR_CAP_AMBIENT_RAISE failed on non-permitted cap\n"); + + capng_update(CAPNG_ADD, CAPNG_INHERITABLE, CAP_NET_BIND_SERVICE); + if (capng_apply(CAPNG_SELECT_CAPS) != 0) + err(1, "capng_apply"); + if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_RAISE, CAP_NET_BIND_SERVICE, 0, 0, 0) != 0) { + printf("[FAIL]\tPR_CAP_AMBIENT_RAISE should have succeeded\n"); + return 1; + } + printf("[OK]\tPR_CAP_AMBIENT_RAISE worked\n"); + + if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_IS_SET, CAP_NET_BIND_SERVICE, 0, 0, 0) != 1) { + printf("[FAIL]\tPR_CAP_AMBIENT_IS_SET is broken\n"); + return 1; + } + + if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_CLEAR_ALL, 0, 0, 0, 0) != 0) + err(1, "PR_CAP_AMBIENT_CLEAR_ALL"); + + if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_IS_SET, CAP_NET_BIND_SERVICE, 0, 0, 0) != 0) { + printf("[FAIL]\tPR_CAP_AMBIENT_CLEAR_ALL didn't work\n"); + return 1; + } + + if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_RAISE, CAP_NET_BIND_SERVICE, 0, 0, 0) != 0) + err(1, "PR_CAP_AMBIENT_RAISE"); + + capng_update(CAPNG_DROP, CAPNG_INHERITABLE, CAP_NET_BIND_SERVICE); + if (capng_apply(CAPNG_SELECT_CAPS) != 0) + err(1, "capng_apply"); + + if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_IS_SET, CAP_NET_BIND_SERVICE, 0, 0, 0) != 0) { + printf("[FAIL]\tDropping I should have dropped A\n"); + return 1; + } + + printf("[OK]\tBasic manipulation appears to work\n"); + + capng_update(CAPNG_ADD, CAPNG_INHERITABLE, CAP_NET_BIND_SERVICE); + if (capng_apply(CAPNG_SELECT_CAPS) != 0) + err(1, "capng_apply"); + if (uid == 0) { + printf("[RUN]\tRoot +i => eip\n"); + if (fork_wait()) + exec_validate_cap(true, true, true, false); + } else { + printf("[RUN]\tNon-root +i => i\n"); + if (fork_wait()) + exec_validate_cap(false, false, true, false); + } + + if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_RAISE, CAP_NET_BIND_SERVICE, 0, 0, 0) != 0) + err(1, "PR_CAP_AMBIENT_RAISE"); + + printf("[RUN]\tUID %d +ia => eipa\n", uid); + if (fork_wait()) + exec_validate_cap(true, true, true, true); + + /* The remaining tests need real privilege */ + + if (!have_outer_privilege) { + printf("[SKIP]\tSUID/SGID tests (needs privilege)\n"); + goto done; + } + + if (uid == 0) { + printf("[RUN]\tRoot +ia, suidroot => eipa\n"); + if (fork_wait()) + exec_other_validate_cap("./validate_cap_suidroot", + true, true, true, true); + + printf("[RUN]\tRoot +ia, suidnonroot => ip\n"); + if (fork_wait()) + exec_other_validate_cap("./validate_cap_suidnonroot", + false, true, true, false); + + printf("[RUN]\tRoot +ia, sgidroot => eipa\n"); + if (fork_wait()) + exec_other_validate_cap("./validate_cap_sgidroot", + true, true, true, true); + + if (fork_wait()) { + printf("[RUN]\tRoot, gid != 0, +ia, sgidroot => eip\n"); + if (setresgid(1, 1, 1) != 0) + err(1, "setresgid"); + exec_other_validate_cap("./validate_cap_sgidroot", + true, true, true, false); + } + + printf("[RUN]\tRoot +ia, sgidnonroot => eip\n"); + if (fork_wait()) + exec_other_validate_cap("./validate_cap_sgidnonroot", + true, true, true, false); + } else { + printf("[RUN]\tNon-root +ia, sgidnonroot => i\n"); + exec_other_validate_cap("./validate_cap_sgidnonroot", + false, false, true, false); + + if (fork_wait()) { + printf("[RUN]\tNon-root +ia, sgidroot => i\n"); + if (setresgid(1, 1, 1) != 0) + err(1, "setresgid"); + exec_other_validate_cap("./validate_cap_sgidroot", + false, false, true, false); + } + } + +done: + return nerrs ? 1 : 0; +} + +int main(int argc, char **argv) +{ + char *tmp1, *tmp2, *our_path; + + /* Find our path */ + tmp1 = strdup(argv[0]); + if (!tmp1) + err(1, "strdup"); + tmp2 = dirname(tmp1); + our_path = strdup(tmp2); + if (!our_path) + err(1, "strdup"); + free(tmp1); + + if (fork_wait()) { + printf("[RUN]\t+++ Tests with uid == 0 +++\n"); + return do_tests(0, our_path); + } + + if (fork_wait()) { + printf("[RUN]\t+++ Tests with uid != 0 +++\n"); + return do_tests(1, our_path); + } + + return nerrs ? 1 : 0; +} diff --git a/tools/testing/selftests/capabilities/validate_cap.c b/tools/testing/selftests/capabilities/validate_cap.c new file mode 100644 index 000000000000..dd3c45f7b23c --- /dev/null +++ b/tools/testing/selftests/capabilities/validate_cap.c @@ -0,0 +1,73 @@ +#include <cap-ng.h> +#include <err.h> +#include <linux/capability.h> +#include <stdbool.h> +#include <string.h> +#include <stdio.h> +#include <sys/prctl.h> +#include <sys/auxv.h> + +#ifndef PR_CAP_AMBIENT +#define PR_CAP_AMBIENT 47 +# define PR_CAP_AMBIENT_IS_SET 1 +# define PR_CAP_AMBIENT_RAISE 2 +# define PR_CAP_AMBIENT_LOWER 3 +# define PR_CAP_AMBIENT_CLEAR_ALL 4 +#endif + +#if __GLIBC__ > 2 || (__GLIBC__ == 2 && __GLIBC_MINOR__ >= 19) +# define HAVE_GETAUXVAL +#endif + +static bool bool_arg(char **argv, int i) +{ + if (!strcmp(argv[i], "0")) + return false; + else if (!strcmp(argv[i], "1")) + return true; + else + errx(1, "wrong argv[%d]", i); +} + +int main(int argc, char **argv) +{ + const char *atsec = ""; + + /* + * Be careful just in case a setgid or setcapped copy of this + * helper gets out. + */ + + if (argc != 5) + errx(1, "wrong argc"); + +#ifdef HAVE_GETAUXVAL + if (getauxval(AT_SECURE)) + atsec = " (AT_SECURE is set)"; + else + atsec = " (AT_SECURE is not set)"; +#endif + + capng_get_caps_process(); + + if (capng_have_capability(CAPNG_EFFECTIVE, CAP_NET_BIND_SERVICE) != bool_arg(argv, 1)) { + printf("[FAIL]\tWrong effective state%s\n", atsec); + return 1; + } + if (capng_have_capability(CAPNG_PERMITTED, CAP_NET_BIND_SERVICE) != bool_arg(argv, 2)) { + printf("[FAIL]\tWrong permitted state%s\n", atsec); + return 1; + } + if (capng_have_capability(CAPNG_INHERITABLE, CAP_NET_BIND_SERVICE) != bool_arg(argv, 3)) { + printf("[FAIL]\tWrong inheritable state%s\n", atsec); + return 1; + } + + if (prctl(PR_CAP_AMBIENT, PR_CAP_AMBIENT_IS_SET, CAP_NET_BIND_SERVICE, 0, 0, 0) != bool_arg(argv, 4)) { + printf("[FAIL]\tWrong ambient state%s\n", atsec); + return 1; + } + + printf("[OK]\tCapabilities after execve were correct\n"); + return 0; +} diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 231b9a031f6a..0d6854744b37 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -8,10 +8,13 @@ BINARIES += hugetlbfstest BINARIES += map_hugetlb BINARIES += thuge-gen BINARIES += transhuge-stress +BINARIES += userfaultfd all: $(BINARIES) %: %.c $(CC) $(CFLAGS) -o $@ $^ -lrt +userfaultfd: userfaultfd.c + $(CC) $(CFLAGS) -O2 -o $@ $^ -lpthread TEST_PROGS := run_vmtests TEST_FILES := $(BINARIES) diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests index 49ece11ff7fd..831adeb5fc55 100755 --- a/tools/testing/selftests/vm/run_vmtests +++ b/tools/testing/selftests/vm/run_vmtests @@ -86,6 +86,17 @@ else echo "[PASS]" fi +echo "--------------------" +echo "running userfaultfd" +echo "--------------------" +./userfaultfd 128 32 +if [ $? -ne 0 ]; then + echo "[FAIL]" + exitcode=1 +else + echo "[PASS]" +fi + #cleanup umount $mnt rm -rf $mnt diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c new file mode 100644 index 000000000000..76071b14cb93 --- /dev/null +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -0,0 +1,636 @@ +/* + * Stress userfaultfd syscall. + * + * Copyright (C) 2015 Red Hat, Inc. + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + * This test allocates two virtual areas and bounces the physical + * memory across the two virtual areas (from area_src to area_dst) + * using userfaultfd. + * + * There are three threads running per CPU: + * + * 1) one per-CPU thread takes a per-page pthread_mutex in a random + * page of the area_dst (while the physical page may still be in + * area_src), and increments a per-page counter in the same page, + * and checks its value against a verification region. + * + * 2) another per-CPU thread handles the userfaults generated by + * thread 1 above. userfaultfd blocking reads or poll() modes are + * exercised interleaved. + * + * 3) one last per-CPU thread transfers the memory in the background + * at maximum bandwidth (if not already transferred by thread + * 2). Each cpu thread takes cares of transferring a portion of the + * area. + * + * When all threads of type 3 completed the transfer, one bounce is + * complete. area_src and area_dst are then swapped. All threads are + * respawned and so the bounce is immediately restarted in the + * opposite direction. + * + * per-CPU threads 1 by triggering userfaults inside + * pthread_mutex_lock will also verify the atomicity of the memory + * transfer (UFFDIO_COPY). + * + * The program takes two parameters: the amounts of physical memory in + * megabytes (MiB) of the area and the number of bounces to execute. + * + * # 100MiB 99999 bounces + * ./userfaultfd 100 99999 + * + * # 1GiB 99 bounces + * ./userfaultfd 1000 99 + * + * # 10MiB-~6GiB 999 bounces, continue forever unless an error triggers + * while ./userfaultfd $[RANDOM % 6000 + 10] 999; do true; done + */ + +#define _GNU_SOURCE +#include <stdio.h> +#include <errno.h> +#include <unistd.h> +#include <stdlib.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <time.h> +#include <signal.h> +#include <poll.h> +#include <string.h> +#include <sys/mman.h> +#include <sys/syscall.h> +#include <sys/ioctl.h> +#include <pthread.h> +#include "../../../../include/uapi/linux/userfaultfd.h" + +#ifdef __x86_64__ +#define __NR_userfaultfd 323 +#elif defined(__i386__) +#define __NR_userfaultfd 374 +#elif defined(__powewrpc__) +#define __NR_userfaultfd 364 +#else +#error "missing __NR_userfaultfd definition" +#endif + +static unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size; + +#define BOUNCE_RANDOM (1<<0) +#define BOUNCE_RACINGFAULTS (1<<1) +#define BOUNCE_VERIFY (1<<2) +#define BOUNCE_POLL (1<<3) +static int bounces; + +static unsigned long long *count_verify; +static int uffd, finished, *pipefd; +static char *area_src, *area_dst; +static char *zeropage; +pthread_attr_t attr; + +/* pthread_mutex_t starts at page offset 0 */ +#define area_mutex(___area, ___nr) \ + ((pthread_mutex_t *) ((___area) + (___nr)*page_size)) +/* + * count is placed in the page after pthread_mutex_t naturally aligned + * to avoid non alignment faults on non-x86 archs. + */ +#define area_count(___area, ___nr) \ + ((volatile unsigned long long *) ((unsigned long) \ + ((___area) + (___nr)*page_size + \ + sizeof(pthread_mutex_t) + \ + sizeof(unsigned long long) - 1) & \ + ~(unsigned long)(sizeof(unsigned long long) \ + - 1))) + +static int my_bcmp(char *str1, char *str2, size_t n) +{ + unsigned long i; + for (i = 0; i < n; i++) + if (str1[i] != str2[i]) + return 1; + return 0; +} + +static void *locking_thread(void *arg) +{ + unsigned long cpu = (unsigned long) arg; + struct random_data rand; + unsigned long page_nr = *(&(page_nr)); /* uninitialized warning */ + int32_t rand_nr; + unsigned long long count; + char randstate[64]; + unsigned int seed; + time_t start; + + if (bounces & BOUNCE_RANDOM) { + seed = (unsigned int) time(NULL) - bounces; + if (!(bounces & BOUNCE_RACINGFAULTS)) + seed += cpu; + bzero(&rand, sizeof(rand)); + bzero(&randstate, sizeof(randstate)); + if (initstate_r(seed, randstate, sizeof(randstate), &rand)) + fprintf(stderr, "srandom_r error\n"), exit(1); + } else { + page_nr = -bounces; + if (!(bounces & BOUNCE_RACINGFAULTS)) + page_nr += cpu * nr_pages_per_cpu; + } + + while (!finished) { + if (bounces & BOUNCE_RANDOM) { + if (random_r(&rand, &rand_nr)) + fprintf(stderr, "random_r 1 error\n"), exit(1); + page_nr = rand_nr; + if (sizeof(page_nr) > sizeof(rand_nr)) { + if (random_r(&rand, &rand_nr)) + fprintf(stderr, "random_r 2 error\n"), exit(1); + page_nr |= ((unsigned long) rand_nr) << 32; + } + } else + page_nr += 1; + page_nr %= nr_pages; + + start = time(NULL); + if (bounces & BOUNCE_VERIFY) { + count = *area_count(area_dst, page_nr); + if (!count) + fprintf(stderr, + "page_nr %lu wrong count %Lu %Lu\n", + page_nr, count, + count_verify[page_nr]), exit(1); + + + /* + * We can't use bcmp (or memcmp) because that + * returns 0 erroneously if the memory is + * changing under it (even if the end of the + * page is never changing and always + * different). + */ +#if 1 + if (!my_bcmp(area_dst + page_nr * page_size, zeropage, + page_size)) + fprintf(stderr, + "my_bcmp page_nr %lu wrong count %Lu %Lu\n", + page_nr, count, + count_verify[page_nr]), exit(1); +#else + unsigned long loops; + + loops = 0; + /* uncomment the below line to test with mutex */ + /* pthread_mutex_lock(area_mutex(area_dst, page_nr)); */ + while (!bcmp(area_dst + page_nr * page_size, zeropage, + page_size)) { + loops += 1; + if (loops > 10) + break; + } + /* uncomment below line to test with mutex */ + /* pthread_mutex_unlock(area_mutex(area_dst, page_nr)); */ + if (loops) { + fprintf(stderr, + "page_nr %lu all zero thread %lu %p %lu\n", + page_nr, cpu, area_dst + page_nr * page_size, + loops); + if (loops > 10) + exit(1); + } +#endif + } + + pthread_mutex_lock(area_mutex(area_dst, page_nr)); + count = *area_count(area_dst, page_nr); + if (count != count_verify[page_nr]) { + fprintf(stderr, + "page_nr %lu memory corruption %Lu %Lu\n", + page_nr, count, + count_verify[page_nr]), exit(1); + } + count++; + *area_count(area_dst, page_nr) = count_verify[page_nr] = count; + pthread_mutex_unlock(area_mutex(area_dst, page_nr)); + + if (time(NULL) - start > 1) + fprintf(stderr, + "userfault too slow %ld " + "possible false positive with overcommit\n", + time(NULL) - start); + } + + return NULL; +} + +static int copy_page(unsigned long offset) +{ + struct uffdio_copy uffdio_copy; + + if (offset >= nr_pages * page_size) + fprintf(stderr, "unexpected offset %lu\n", + offset), exit(1); + uffdio_copy.dst = (unsigned long) area_dst + offset; + uffdio_copy.src = (unsigned long) area_src + offset; + uffdio_copy.len = page_size; + uffdio_copy.mode = 0; + uffdio_copy.copy = 0; + if (ioctl(uffd, UFFDIO_COPY, &uffdio_copy)) { + /* real retval in ufdio_copy.copy */ + if (uffdio_copy.copy != -EEXIST) + fprintf(stderr, "UFFDIO_COPY error %Ld\n", + uffdio_copy.copy), exit(1); + } else if (uffdio_copy.copy != page_size) { + fprintf(stderr, "UFFDIO_COPY unexpected copy %Ld\n", + uffdio_copy.copy), exit(1); + } else + return 1; + return 0; +} + +static void *uffd_poll_thread(void *arg) +{ + unsigned long cpu = (unsigned long) arg; + struct pollfd pollfd[2]; + struct uffd_msg msg; + int ret; + unsigned long offset; + char tmp_chr; + unsigned long userfaults = 0; + + pollfd[0].fd = uffd; + pollfd[0].events = POLLIN; + pollfd[1].fd = pipefd[cpu*2]; + pollfd[1].events = POLLIN; + + for (;;) { + ret = poll(pollfd, 2, -1); + if (!ret) + fprintf(stderr, "poll error %d\n", ret), exit(1); + if (ret < 0) + perror("poll"), exit(1); + if (pollfd[1].revents & POLLIN) { + if (read(pollfd[1].fd, &tmp_chr, 1) != 1) + fprintf(stderr, "read pipefd error\n"), + exit(1); + break; + } + if (!(pollfd[0].revents & POLLIN)) + fprintf(stderr, "pollfd[0].revents %d\n", + pollfd[0].revents), exit(1); + ret = read(uffd, &msg, sizeof(msg)); + if (ret < 0) { + if (errno == EAGAIN) + continue; + perror("nonblocking read error"), exit(1); + } + if (msg.event != UFFD_EVENT_PAGEFAULT) + fprintf(stderr, "unexpected msg event %u\n", + msg.event), exit(1); + if (msg.arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE) + fprintf(stderr, "unexpected write fault\n"), exit(1); + offset = (char *)msg.arg.pagefault.address - area_dst; + offset &= ~(page_size-1); + if (copy_page(offset)) + userfaults++; + } + return (void *)userfaults; +} + +pthread_mutex_t uffd_read_mutex = PTHREAD_MUTEX_INITIALIZER; + +static void *uffd_read_thread(void *arg) +{ + unsigned long *this_cpu_userfaults; + struct uffd_msg msg; + unsigned long offset; + int ret; + + this_cpu_userfaults = (unsigned long *) arg; + *this_cpu_userfaults = 0; + + pthread_mutex_unlock(&uffd_read_mutex); + /* from here cancellation is ok */ + + for (;;) { + ret = read(uffd, &msg, sizeof(msg)); + if (ret != sizeof(msg)) { + if (ret < 0) + perror("blocking read error"), exit(1); + else + fprintf(stderr, "short read\n"), exit(1); + } + if (msg.event != UFFD_EVENT_PAGEFAULT) + fprintf(stderr, "unexpected msg event %u\n", + msg.event), exit(1); + if (bounces & BOUNCE_VERIFY && + msg.arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE) + fprintf(stderr, "unexpected write fault\n"), exit(1); + offset = (char *)msg.arg.pagefault.address - area_dst; + offset &= ~(page_size-1); + if (copy_page(offset)) + (*this_cpu_userfaults)++; + } + return (void *)NULL; +} + +static void *background_thread(void *arg) +{ + unsigned long cpu = (unsigned long) arg; + unsigned long page_nr; + + for (page_nr = cpu * nr_pages_per_cpu; + page_nr < (cpu+1) * nr_pages_per_cpu; + page_nr++) + copy_page(page_nr * page_size); + + return NULL; +} + +static int stress(unsigned long *userfaults) +{ + unsigned long cpu; + pthread_t locking_threads[nr_cpus]; + pthread_t uffd_threads[nr_cpus]; + pthread_t background_threads[nr_cpus]; + void **_userfaults = (void **) userfaults; + + finished = 0; + for (cpu = 0; cpu < nr_cpus; cpu++) { + if (pthread_create(&locking_threads[cpu], &attr, + locking_thread, (void *)cpu)) + return 1; + if (bounces & BOUNCE_POLL) { + if (pthread_create(&uffd_threads[cpu], &attr, + uffd_poll_thread, (void *)cpu)) + return 1; + } else { + if (pthread_create(&uffd_threads[cpu], &attr, + uffd_read_thread, + &_userfaults[cpu])) + return 1; + pthread_mutex_lock(&uffd_read_mutex); + } + if (pthread_create(&background_threads[cpu], &attr, + background_thread, (void *)cpu)) + return 1; + } + for (cpu = 0; cpu < nr_cpus; cpu++) + if (pthread_join(background_threads[cpu], NULL)) + return 1; + + /* + * Be strict and immediately zap area_src, the whole area has + * been transferred already by the background treads. The + * area_src could then be faulted in in a racy way by still + * running uffdio_threads reading zeropages after we zapped + * area_src (but they're guaranteed to get -EEXIST from + * UFFDIO_COPY without writing zero pages into area_dst + * because the background threads already completed). + */ + if (madvise(area_src, nr_pages * page_size, MADV_DONTNEED)) { + perror("madvise"); + return 1; + } + + for (cpu = 0; cpu < nr_cpus; cpu++) { + char c; + if (bounces & BOUNCE_POLL) { + if (write(pipefd[cpu*2+1], &c, 1) != 1) { + fprintf(stderr, "pipefd write error\n"); + return 1; + } + if (pthread_join(uffd_threads[cpu], &_userfaults[cpu])) + return 1; + } else { + if (pthread_cancel(uffd_threads[cpu])) + return 1; + if (pthread_join(uffd_threads[cpu], NULL)) + return 1; + } + } + + finished = 1; + for (cpu = 0; cpu < nr_cpus; cpu++) + if (pthread_join(locking_threads[cpu], NULL)) + return 1; + + return 0; +} + +static int userfaultfd_stress(void) +{ + void *area; + char *tmp_area; + unsigned long nr; + struct uffdio_register uffdio_register; + struct uffdio_api uffdio_api; + unsigned long cpu; + int uffd_flags; + unsigned long userfaults[nr_cpus]; + + if (posix_memalign(&area, page_size, nr_pages * page_size)) { + fprintf(stderr, "out of memory\n"); + return 1; + } + area_src = area; + if (posix_memalign(&area, page_size, nr_pages * page_size)) { + fprintf(stderr, "out of memory\n"); + return 1; + } + area_dst = area; + + uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK); + if (uffd < 0) { + fprintf(stderr, + "userfaultfd syscall not available in this kernel\n"); + return 1; + } + uffd_flags = fcntl(uffd, F_GETFD, NULL); + + uffdio_api.api = UFFD_API; + uffdio_api.features = 0; + if (ioctl(uffd, UFFDIO_API, &uffdio_api)) { + fprintf(stderr, "UFFDIO_API\n"); + return 1; + } + if (uffdio_api.api != UFFD_API) { + fprintf(stderr, "UFFDIO_API error %Lu\n", uffdio_api.api); + return 1; + } + + count_verify = malloc(nr_pages * sizeof(unsigned long long)); + if (!count_verify) { + perror("count_verify"); + return 1; + } + + for (nr = 0; nr < nr_pages; nr++) { + *area_mutex(area_src, nr) = (pthread_mutex_t) + PTHREAD_MUTEX_INITIALIZER; + count_verify[nr] = *area_count(area_src, nr) = 1; + } + + pipefd = malloc(sizeof(int) * nr_cpus * 2); + if (!pipefd) { + perror("pipefd"); + return 1; + } + for (cpu = 0; cpu < nr_cpus; cpu++) { + if (pipe2(&pipefd[cpu*2], O_CLOEXEC | O_NONBLOCK)) { + perror("pipe"); + return 1; + } + } + + if (posix_memalign(&area, page_size, page_size)) { + fprintf(stderr, "out of memory\n"); + return 1; + } + zeropage = area; + bzero(zeropage, page_size); + + pthread_mutex_lock(&uffd_read_mutex); + + pthread_attr_init(&attr); + pthread_attr_setstacksize(&attr, 16*1024*1024); + + while (bounces--) { + unsigned long expected_ioctls; + + printf("bounces: %d, mode:", bounces); + if (bounces & BOUNCE_RANDOM) + printf(" rnd"); + if (bounces & BOUNCE_RACINGFAULTS) + printf(" racing"); + if (bounces & BOUNCE_VERIFY) + printf(" ver"); + if (bounces & BOUNCE_POLL) + printf(" poll"); + printf(", "); + fflush(stdout); + + if (bounces & BOUNCE_POLL) + fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK); + else + fcntl(uffd, F_SETFL, uffd_flags & ~O_NONBLOCK); + + /* register */ + uffdio_register.range.start = (unsigned long) area_dst; + uffdio_register.range.len = nr_pages * page_size; + uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING; + if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) { + fprintf(stderr, "register failure\n"); + return 1; + } + expected_ioctls = (1 << _UFFDIO_WAKE) | + (1 << _UFFDIO_COPY) | + (1 << _UFFDIO_ZEROPAGE); + if ((uffdio_register.ioctls & expected_ioctls) != + expected_ioctls) { + fprintf(stderr, + "unexpected missing ioctl for anon memory\n"); + return 1; + } + + /* + * The madvise done previously isn't enough: some + * uffd_thread could have read userfaults (one of + * those already resolved by the background thread) + * and it may be in the process of calling + * UFFDIO_COPY. UFFDIO_COPY will read the zapped + * area_src and it would map a zero page in it (of + * course such a UFFDIO_COPY is perfectly safe as it'd + * return -EEXIST). The problem comes at the next + * bounce though: that racing UFFDIO_COPY would + * generate zeropages in the area_src, so invalidating + * the previous MADV_DONTNEED. Without this additional + * MADV_DONTNEED those zeropages leftovers in the + * area_src would lead to -EEXIST failure during the + * next bounce, effectively leaving a zeropage in the + * area_dst. + * + * Try to comment this out madvise to see the memory + * corruption being caught pretty quick. + * + * khugepaged is also inhibited to collapse THP after + * MADV_DONTNEED only after the UFFDIO_REGISTER, so it's + * required to MADV_DONTNEED here. + */ + if (madvise(area_dst, nr_pages * page_size, MADV_DONTNEED)) { + perror("madvise 2"); + return 1; + } + + /* bounce pass */ + if (stress(userfaults)) + return 1; + + /* unregister */ + if (ioctl(uffd, UFFDIO_UNREGISTER, &uffdio_register.range)) { + fprintf(stderr, "register failure\n"); + return 1; + } + + /* verification */ + if (bounces & BOUNCE_VERIFY) { + for (nr = 0; nr < nr_pages; nr++) { + if (my_bcmp(area_dst, + area_dst + nr * page_size, + sizeof(pthread_mutex_t))) { + fprintf(stderr, + "error mutex 2 %lu\n", + nr); + bounces = 0; + } + if (*area_count(area_dst, nr) != count_verify[nr]) { + fprintf(stderr, + "error area_count %Lu %Lu %lu\n", + *area_count(area_src, nr), + count_verify[nr], + nr); + bounces = 0; + } + } + } + + /* prepare next bounce */ + tmp_area = area_src; + area_src = area_dst; + area_dst = tmp_area; + + printf("userfaults:"); + for (cpu = 0; cpu < nr_cpus; cpu++) + printf(" %lu", userfaults[cpu]); + printf("\n"); + } + + return 0; +} + +int main(int argc, char **argv) +{ + if (argc < 3) + fprintf(stderr, "Usage: <MiB> <bounces>\n"), exit(1); + nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); + page_size = sysconf(_SC_PAGE_SIZE); + if ((unsigned long) area_count(NULL, 0) + sizeof(unsigned long long) > + page_size) + fprintf(stderr, "Impossible to run this test\n"), exit(2); + nr_pages_per_cpu = atol(argv[1]) * 1024*1024 / page_size / + nr_cpus; + if (!nr_pages_per_cpu) { + fprintf(stderr, "invalid MiB\n"); + fprintf(stderr, "Usage: <MiB> <bounces>\n"), exit(1); + } + bounces = atoi(argv[2]); + if (bounces <= 0) { + fprintf(stderr, "invalid bounces\n"); + fprintf(stderr, "Usage: <MiB> <bounces>\n"), exit(1); + } + nr_pages = nr_pages_per_cpu * nr_cpus; + printf("nr_pages: %lu, nr_pages_per_cpu: %lu\n", + nr_pages, nr_pages_per_cpu); + return userfaultfd_stress(); +} |
