diff options
Diffstat (limited to 'tools')
27 files changed, 3306 insertions, 409 deletions
diff --git a/tools/hv/Build b/tools/hv/Build index 6cf51fa4b306..7d1f1698069b 100644 --- a/tools/hv/Build +++ b/tools/hv/Build @@ -1,3 +1,4 @@ hv_kvp_daemon-y += hv_kvp_daemon.o hv_vss_daemon-y += hv_vss_daemon.o -hv_fcopy_daemon-y += hv_fcopy_daemon.o +hv_fcopy_uio_daemon-y += hv_fcopy_uio_daemon.o +hv_fcopy_uio_daemon-y += vmbus_bufring.o diff --git a/tools/hv/Makefile b/tools/hv/Makefile index fe770e679ae8..bb52871da341 100644 --- a/tools/hv/Makefile +++ b/tools/hv/Makefile @@ -2,6 +2,7 @@ # Makefile for Hyper-V tools include ../scripts/Makefile.include +ARCH := $(shell uname -m 2>/dev/null) sbindir ?= /usr/sbin libexecdir ?= /usr/libexec sharedstatedir ?= /var/lib @@ -17,7 +18,10 @@ MAKEFLAGS += -r override CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include -ALL_TARGETS := hv_kvp_daemon hv_vss_daemon hv_fcopy_daemon +ALL_TARGETS := hv_kvp_daemon hv_vss_daemon +ifneq ($(ARCH), aarch64) +ALL_TARGETS += hv_fcopy_uio_daemon +endif ALL_PROGRAMS := $(patsubst %,$(OUTPUT)%,$(ALL_TARGETS)) ALL_SCRIPTS := hv_get_dhcp_info.sh hv_get_dns_info.sh hv_set_ifconfig.sh @@ -39,10 +43,10 @@ $(HV_VSS_DAEMON_IN): FORCE $(OUTPUT)hv_vss_daemon: $(HV_VSS_DAEMON_IN) $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@ -HV_FCOPY_DAEMON_IN := $(OUTPUT)hv_fcopy_daemon-in.o -$(HV_FCOPY_DAEMON_IN): FORCE - $(Q)$(MAKE) $(build)=hv_fcopy_daemon -$(OUTPUT)hv_fcopy_daemon: $(HV_FCOPY_DAEMON_IN) +HV_FCOPY_UIO_DAEMON_IN := $(OUTPUT)hv_fcopy_uio_daemon-in.o +$(HV_FCOPY_UIO_DAEMON_IN): FORCE + $(Q)$(MAKE) $(build)=hv_fcopy_uio_daemon +$(OUTPUT)hv_fcopy_uio_daemon: $(HV_FCOPY_UIO_DAEMON_IN) $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@ clean: diff --git a/tools/hv/hv_fcopy_daemon.c b/tools/hv/hv_fcopy_daemon.c deleted file mode 100644 index 16d629b22c25..000000000000 --- a/tools/hv/hv_fcopy_daemon.c +++ /dev/null @@ -1,266 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * An implementation of host to guest copy functionality for Linux. - * - * Copyright (C) 2014, Microsoft, Inc. - * - * Author : K. Y. Srinivasan <kys@microsoft.com> - */ - - -#include <sys/types.h> -#include <stdio.h> -#include <stdlib.h> -#include <unistd.h> -#include <string.h> -#include <errno.h> -#include <linux/hyperv.h> -#include <linux/limits.h> -#include <syslog.h> -#include <sys/stat.h> -#include <fcntl.h> -#include <getopt.h> - -static int target_fd; -static char target_fname[PATH_MAX]; -static unsigned long long filesize; - -static int hv_start_fcopy(struct hv_start_fcopy *smsg) -{ - int error = HV_E_FAIL; - char *q, *p; - - filesize = 0; - p = (char *)smsg->path_name; - snprintf(target_fname, sizeof(target_fname), "%s/%s", - (char *)smsg->path_name, (char *)smsg->file_name); - - syslog(LOG_INFO, "Target file name: %s", target_fname); - /* - * Check to see if the path is already in place; if not, - * create if required. - */ - while ((q = strchr(p, '/')) != NULL) { - if (q == p) { - p++; - continue; - } - *q = '\0'; - if (access((char *)smsg->path_name, F_OK)) { - if (smsg->copy_flags & CREATE_PATH) { - if (mkdir((char *)smsg->path_name, 0755)) { - syslog(LOG_ERR, "Failed to create %s", - (char *)smsg->path_name); - goto done; - } - } else { - syslog(LOG_ERR, "Invalid path: %s", - (char *)smsg->path_name); - goto done; - } - } - p = q + 1; - *q = '/'; - } - - if (!access(target_fname, F_OK)) { - syslog(LOG_INFO, "File: %s exists", target_fname); - if (!(smsg->copy_flags & OVER_WRITE)) { - error = HV_ERROR_ALREADY_EXISTS; - goto done; - } - } - - target_fd = open(target_fname, - O_RDWR | O_CREAT | O_TRUNC | O_CLOEXEC, 0744); - if (target_fd == -1) { - syslog(LOG_INFO, "Open Failed: %s", strerror(errno)); - goto done; - } - - error = 0; -done: - if (error) - target_fname[0] = '\0'; - return error; -} - -static int hv_copy_data(struct hv_do_fcopy *cpmsg) -{ - ssize_t bytes_written; - int ret = 0; - - bytes_written = pwrite(target_fd, cpmsg->data, cpmsg->size, - cpmsg->offset); - - filesize += cpmsg->size; - if (bytes_written != cpmsg->size) { - switch (errno) { - case ENOSPC: - ret = HV_ERROR_DISK_FULL; - break; - default: - ret = HV_E_FAIL; - break; - } - syslog(LOG_ERR, "pwrite failed to write %llu bytes: %ld (%s)", - filesize, (long)bytes_written, strerror(errno)); - } - - return ret; -} - -/* - * Reset target_fname to "" in the two below functions for hibernation: if - * the fcopy operation is aborted by hibernation, the daemon should remove the - * partially-copied file; to achieve this, the hv_utils driver always fakes a - * CANCEL_FCOPY message upon suspend, and later when the VM resumes back, - * the daemon calls hv_copy_cancel() to remove the file; if a file is copied - * successfully before suspend, hv_copy_finished() must reset target_fname to - * avoid that the file can be incorrectly removed upon resume, since the faked - * CANCEL_FCOPY message is spurious in this case. - */ -static int hv_copy_finished(void) -{ - close(target_fd); - target_fname[0] = '\0'; - return 0; -} -static int hv_copy_cancel(void) -{ - close(target_fd); - if (strlen(target_fname) > 0) { - unlink(target_fname); - target_fname[0] = '\0'; - } - return 0; - -} - -void print_usage(char *argv[]) -{ - fprintf(stderr, "Usage: %s [options]\n" - "Options are:\n" - " -n, --no-daemon stay in foreground, don't daemonize\n" - " -h, --help print this help\n", argv[0]); -} - -int main(int argc, char *argv[]) -{ - int fcopy_fd = -1; - int error; - int daemonize = 1, long_index = 0, opt; - int version = FCOPY_CURRENT_VERSION; - union { - struct hv_fcopy_hdr hdr; - struct hv_start_fcopy start; - struct hv_do_fcopy copy; - __u32 kernel_modver; - } buffer = { }; - int in_handshake; - - static struct option long_options[] = { - {"help", no_argument, 0, 'h' }, - {"no-daemon", no_argument, 0, 'n' }, - {0, 0, 0, 0 } - }; - - while ((opt = getopt_long(argc, argv, "hn", long_options, - &long_index)) != -1) { - switch (opt) { - case 'n': - daemonize = 0; - break; - case 'h': - default: - print_usage(argv); - exit(EXIT_FAILURE); - } - } - - if (daemonize && daemon(1, 0)) { - syslog(LOG_ERR, "daemon() failed; error: %s", strerror(errno)); - exit(EXIT_FAILURE); - } - - openlog("HV_FCOPY", 0, LOG_USER); - syslog(LOG_INFO, "starting; pid is:%d", getpid()); - -reopen_fcopy_fd: - if (fcopy_fd != -1) - close(fcopy_fd); - /* Remove any possible partially-copied file on error */ - hv_copy_cancel(); - in_handshake = 1; - fcopy_fd = open("/dev/vmbus/hv_fcopy", O_RDWR); - - if (fcopy_fd < 0) { - syslog(LOG_ERR, "open /dev/vmbus/hv_fcopy failed; error: %d %s", - errno, strerror(errno)); - exit(EXIT_FAILURE); - } - - /* - * Register with the kernel. - */ - if ((write(fcopy_fd, &version, sizeof(int))) != sizeof(int)) { - syslog(LOG_ERR, "Registration failed: %s", strerror(errno)); - exit(EXIT_FAILURE); - } - - while (1) { - /* - * In this loop we process fcopy messages after the - * handshake is complete. - */ - ssize_t len; - - len = pread(fcopy_fd, &buffer, sizeof(buffer), 0); - if (len < 0) { - syslog(LOG_ERR, "pread failed: %s", strerror(errno)); - goto reopen_fcopy_fd; - } - - if (in_handshake) { - if (len != sizeof(buffer.kernel_modver)) { - syslog(LOG_ERR, "invalid version negotiation"); - exit(EXIT_FAILURE); - } - in_handshake = 0; - syslog(LOG_INFO, "kernel module version: %u", - buffer.kernel_modver); - continue; - } - - switch (buffer.hdr.operation) { - case START_FILE_COPY: - error = hv_start_fcopy(&buffer.start); - break; - case WRITE_TO_FILE: - error = hv_copy_data(&buffer.copy); - break; - case COMPLETE_FCOPY: - error = hv_copy_finished(); - break; - case CANCEL_FCOPY: - error = hv_copy_cancel(); - break; - - default: - error = HV_E_FAIL; - syslog(LOG_ERR, "Unknown operation: %d", - buffer.hdr.operation); - - } - - /* - * pwrite() may return an error due to the faked CANCEL_FCOPY - * message upon hibernation. Ignore the error by resetting the - * dev file, i.e. closing and re-opening it. - */ - if (pwrite(fcopy_fd, &error, sizeof(int), 0) != sizeof(int)) { - syslog(LOG_ERR, "pwrite failed: %s", strerror(errno)); - goto reopen_fcopy_fd; - } - } -} diff --git a/tools/hv/hv_fcopy_uio_daemon.c b/tools/hv/hv_fcopy_uio_daemon.c new file mode 100644 index 000000000000..3ce316cc9f97 --- /dev/null +++ b/tools/hv/hv_fcopy_uio_daemon.c @@ -0,0 +1,490 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * An implementation of host to guest copy functionality for Linux. + * + * Copyright (C) 2023, Microsoft, Inc. + * + * Author : K. Y. Srinivasan <kys@microsoft.com> + * Author : Saurabh Sengar <ssengar@microsoft.com> + * + */ + +#include <dirent.h> +#include <errno.h> +#include <fcntl.h> +#include <getopt.h> +#include <locale.h> +#include <stdbool.h> +#include <stddef.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <syslog.h> +#include <unistd.h> +#include <wchar.h> +#include <sys/stat.h> +#include <linux/hyperv.h> +#include <linux/limits.h> +#include "vmbus_bufring.h" + +#define ICMSGTYPE_NEGOTIATE 0 +#define ICMSGTYPE_FCOPY 7 + +#define WIN8_SRV_MAJOR 1 +#define WIN8_SRV_MINOR 1 +#define WIN8_SRV_VERSION (WIN8_SRV_MAJOR << 16 | WIN8_SRV_MINOR) + +#define MAX_FOLDER_NAME 15 +#define MAX_PATH_LEN 15 +#define FCOPY_UIO "/sys/bus/vmbus/devices/eb765408-105f-49b6-b4aa-c123b64d17d4/uio" + +#define FCOPY_VER_COUNT 1 +static const int fcopy_versions[] = { + WIN8_SRV_VERSION +}; + +#define FW_VER_COUNT 1 +static const int fw_versions[] = { + UTIL_FW_VERSION +}; + +#define HV_RING_SIZE 0x4000 /* 16KB ring buffer size */ + +unsigned char desc[HV_RING_SIZE]; + +static int target_fd; +static char target_fname[PATH_MAX]; +static unsigned long long filesize; + +static int hv_fcopy_create_file(char *file_name, char *path_name, __u32 flags) +{ + int error = HV_E_FAIL; + char *q, *p; + + filesize = 0; + p = path_name; + snprintf(target_fname, sizeof(target_fname), "%s/%s", + path_name, file_name); + + /* + * Check to see if the path is already in place; if not, + * create if required. + */ + while ((q = strchr(p, '/')) != NULL) { + if (q == p) { + p++; + continue; + } + *q = '\0'; + if (access(path_name, F_OK)) { + if (flags & CREATE_PATH) { + if (mkdir(path_name, 0755)) { + syslog(LOG_ERR, "Failed to create %s", + path_name); + goto done; + } + } else { + syslog(LOG_ERR, "Invalid path: %s", path_name); + goto done; + } + } + p = q + 1; + *q = '/'; + } + + if (!access(target_fname, F_OK)) { + syslog(LOG_INFO, "File: %s exists", target_fname); + if (!(flags & OVER_WRITE)) { + error = HV_ERROR_ALREADY_EXISTS; + goto done; + } + } + + target_fd = open(target_fname, + O_RDWR | O_CREAT | O_TRUNC | O_CLOEXEC, 0744); + if (target_fd == -1) { + syslog(LOG_INFO, "Open Failed: %s", strerror(errno)); + goto done; + } + + error = 0; +done: + if (error) + target_fname[0] = '\0'; + return error; +} + +/* copy the data into the file */ +static int hv_copy_data(struct hv_do_fcopy *cpmsg) +{ + ssize_t len; + int ret = 0; + + len = pwrite(target_fd, cpmsg->data, cpmsg->size, cpmsg->offset); + + filesize += cpmsg->size; + if (len != cpmsg->size) { + switch (errno) { + case ENOSPC: + ret = HV_ERROR_DISK_FULL; + break; + default: + ret = HV_E_FAIL; + break; + } + syslog(LOG_ERR, "pwrite failed to write %llu bytes: %ld (%s)", + filesize, (long)len, strerror(errno)); + } + + return ret; +} + +static int hv_copy_finished(void) +{ + close(target_fd); + target_fname[0] = '\0'; + + return 0; +} + +static void print_usage(char *argv[]) +{ + fprintf(stderr, "Usage: %s [options]\n" + "Options are:\n" + " -n, --no-daemon stay in foreground, don't daemonize\n" + " -h, --help print this help\n", argv[0]); +} + +static bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp, unsigned char *buf, + unsigned int buflen, const int *fw_version, int fw_vercnt, + const int *srv_version, int srv_vercnt, + int *nego_fw_version, int *nego_srv_version) +{ + int icframe_major, icframe_minor; + int icmsg_major, icmsg_minor; + int fw_major, fw_minor; + int srv_major, srv_minor; + int i, j; + bool found_match = false; + struct icmsg_negotiate *negop; + + /* Check that there's enough space for icframe_vercnt, icmsg_vercnt */ + if (buflen < ICMSG_HDR + offsetof(struct icmsg_negotiate, reserved)) { + syslog(LOG_ERR, "Invalid icmsg negotiate"); + return false; + } + + icmsghdrp->icmsgsize = 0x10; + negop = (struct icmsg_negotiate *)&buf[ICMSG_HDR]; + + icframe_major = negop->icframe_vercnt; + icframe_minor = 0; + + icmsg_major = negop->icmsg_vercnt; + icmsg_minor = 0; + + /* Validate negop packet */ + if (icframe_major > IC_VERSION_NEGOTIATION_MAX_VER_COUNT || + icmsg_major > IC_VERSION_NEGOTIATION_MAX_VER_COUNT || + ICMSG_NEGOTIATE_PKT_SIZE(icframe_major, icmsg_major) > buflen) { + syslog(LOG_ERR, "Invalid icmsg negotiate - icframe_major: %u, icmsg_major: %u\n", + icframe_major, icmsg_major); + goto fw_error; + } + + /* + * Select the framework version number we will + * support. + */ + + for (i = 0; i < fw_vercnt; i++) { + fw_major = (fw_version[i] >> 16); + fw_minor = (fw_version[i] & 0xFFFF); + + for (j = 0; j < negop->icframe_vercnt; j++) { + if (negop->icversion_data[j].major == fw_major && + negop->icversion_data[j].minor == fw_minor) { + icframe_major = negop->icversion_data[j].major; + icframe_minor = negop->icversion_data[j].minor; + found_match = true; + break; + } + } + + if (found_match) + break; + } + + if (!found_match) + goto fw_error; + + found_match = false; + + for (i = 0; i < srv_vercnt; i++) { + srv_major = (srv_version[i] >> 16); + srv_minor = (srv_version[i] & 0xFFFF); + + for (j = negop->icframe_vercnt; + (j < negop->icframe_vercnt + negop->icmsg_vercnt); + j++) { + if (negop->icversion_data[j].major == srv_major && + negop->icversion_data[j].minor == srv_minor) { + icmsg_major = negop->icversion_data[j].major; + icmsg_minor = negop->icversion_data[j].minor; + found_match = true; + break; + } + } + + if (found_match) + break; + } + + /* + * Respond with the framework and service + * version numbers we can support. + */ +fw_error: + if (!found_match) { + negop->icframe_vercnt = 0; + negop->icmsg_vercnt = 0; + } else { + negop->icframe_vercnt = 1; + negop->icmsg_vercnt = 1; + } + + if (nego_fw_version) + *nego_fw_version = (icframe_major << 16) | icframe_minor; + + if (nego_srv_version) + *nego_srv_version = (icmsg_major << 16) | icmsg_minor; + + negop->icversion_data[0].major = icframe_major; + negop->icversion_data[0].minor = icframe_minor; + negop->icversion_data[1].major = icmsg_major; + negop->icversion_data[1].minor = icmsg_minor; + + return found_match; +} + +static void wcstoutf8(char *dest, const __u16 *src, size_t dest_size) +{ + size_t len = 0; + + while (len < dest_size) { + if (src[len] < 0x80) + dest[len++] = (char)(*src++); + else + dest[len++] = 'X'; + } + + dest[len] = '\0'; +} + +static int hv_fcopy_start(struct hv_start_fcopy *smsg_in) +{ + setlocale(LC_ALL, "en_US.utf8"); + size_t file_size, path_size; + char *file_name, *path_name; + char *in_file_name = (char *)smsg_in->file_name; + char *in_path_name = (char *)smsg_in->path_name; + + file_size = wcstombs(NULL, (const wchar_t *restrict)in_file_name, 0) + 1; + path_size = wcstombs(NULL, (const wchar_t *restrict)in_path_name, 0) + 1; + + file_name = (char *)malloc(file_size * sizeof(char)); + path_name = (char *)malloc(path_size * sizeof(char)); + + wcstoutf8(file_name, (__u16 *)in_file_name, file_size); + wcstoutf8(path_name, (__u16 *)in_path_name, path_size); + + return hv_fcopy_create_file(file_name, path_name, smsg_in->copy_flags); +} + +static int hv_fcopy_send_data(struct hv_fcopy_hdr *fcopy_msg, int recvlen) +{ + int operation = fcopy_msg->operation; + + /* + * The strings sent from the host are encoded in + * utf16; convert it to utf8 strings. + * The host assures us that the utf16 strings will not exceed + * the max lengths specified. We will however, reserve room + * for the string terminating character - in the utf16s_utf8s() + * function we limit the size of the buffer where the converted + * string is placed to W_MAX_PATH -1 to guarantee + * that the strings can be properly terminated! + */ + + switch (operation) { + case START_FILE_COPY: + return hv_fcopy_start((struct hv_start_fcopy *)fcopy_msg); + case WRITE_TO_FILE: + return hv_copy_data((struct hv_do_fcopy *)fcopy_msg); + case COMPLETE_FCOPY: + return hv_copy_finished(); + } + + return HV_E_FAIL; +} + +/* process the packet recv from host */ +static int fcopy_pkt_process(struct vmbus_br *txbr) +{ + int ret, offset, pktlen; + int fcopy_srv_version; + const struct vmbus_chanpkt_hdr *pkt; + struct hv_fcopy_hdr *fcopy_msg; + struct icmsg_hdr *icmsghdr; + + pkt = (const struct vmbus_chanpkt_hdr *)desc; + offset = pkt->hlen << 3; + pktlen = (pkt->tlen << 3) - offset; + icmsghdr = (struct icmsg_hdr *)&desc[offset + sizeof(struct vmbuspipe_hdr)]; + icmsghdr->status = HV_E_FAIL; + + if (icmsghdr->icmsgtype == ICMSGTYPE_NEGOTIATE) { + if (vmbus_prep_negotiate_resp(icmsghdr, desc + offset, pktlen, fw_versions, + FW_VER_COUNT, fcopy_versions, FCOPY_VER_COUNT, + NULL, &fcopy_srv_version)) { + syslog(LOG_INFO, "FCopy IC version %d.%d", + fcopy_srv_version >> 16, fcopy_srv_version & 0xFFFF); + icmsghdr->status = 0; + } + } else if (icmsghdr->icmsgtype == ICMSGTYPE_FCOPY) { + /* Ensure recvlen is big enough to contain hv_fcopy_hdr */ + if (pktlen < ICMSG_HDR + sizeof(struct hv_fcopy_hdr)) { + syslog(LOG_ERR, "Invalid Fcopy hdr. Packet length too small: %u", + pktlen); + return -ENOBUFS; + } + + fcopy_msg = (struct hv_fcopy_hdr *)&desc[offset + ICMSG_HDR]; + icmsghdr->status = hv_fcopy_send_data(fcopy_msg, pktlen); + } + + icmsghdr->icflags = ICMSGHDRFLAG_TRANSACTION | ICMSGHDRFLAG_RESPONSE; + ret = rte_vmbus_chan_send(txbr, 0x6, desc + offset, pktlen, 0); + if (ret) { + syslog(LOG_ERR, "Write to ringbuffer failed err: %d", ret); + return ret; + } + + return 0; +} + +static void fcopy_get_first_folder(char *path, char *chan_no) +{ + DIR *dir = opendir(path); + struct dirent *entry; + + if (!dir) { + syslog(LOG_ERR, "Failed to open directory (errno=%s).\n", strerror(errno)); + return; + } + + while ((entry = readdir(dir)) != NULL) { + if (entry->d_type == DT_DIR && strcmp(entry->d_name, ".") != 0 && + strcmp(entry->d_name, "..") != 0) { + strcpy(chan_no, entry->d_name); + break; + } + } + + closedir(dir); +} + +int main(int argc, char *argv[]) +{ + int fcopy_fd = -1, tmp = 1; + int daemonize = 1, long_index = 0, opt, ret = -EINVAL; + struct vmbus_br txbr, rxbr; + void *ring; + uint32_t len = HV_RING_SIZE; + char uio_name[MAX_FOLDER_NAME] = {0}; + char uio_dev_path[MAX_PATH_LEN] = {0}; + + static struct option long_options[] = { + {"help", no_argument, 0, 'h' }, + {"no-daemon", no_argument, 0, 'n' }, + {0, 0, 0, 0 } + }; + + while ((opt = getopt_long(argc, argv, "hn", long_options, + &long_index)) != -1) { + switch (opt) { + case 'n': + daemonize = 0; + break; + case 'h': + default: + print_usage(argv); + goto exit; + } + } + + if (daemonize && daemon(1, 0)) { + syslog(LOG_ERR, "daemon() failed; error: %s", strerror(errno)); + goto exit; + } + + openlog("HV_UIO_FCOPY", 0, LOG_USER); + syslog(LOG_INFO, "starting; pid is:%d", getpid()); + + fcopy_get_first_folder(FCOPY_UIO, uio_name); + snprintf(uio_dev_path, sizeof(uio_dev_path), "/dev/%s", uio_name); + fcopy_fd = open(uio_dev_path, O_RDWR); + + if (fcopy_fd < 0) { + syslog(LOG_ERR, "open %s failed; error: %d %s", + uio_dev_path, errno, strerror(errno)); + ret = fcopy_fd; + goto exit; + } + + ring = vmbus_uio_map(&fcopy_fd, HV_RING_SIZE); + if (!ring) { + ret = errno; + syslog(LOG_ERR, "mmap ringbuffer failed; error: %d %s", ret, strerror(ret)); + goto close; + } + vmbus_br_setup(&txbr, ring, HV_RING_SIZE); + vmbus_br_setup(&rxbr, (char *)ring + HV_RING_SIZE, HV_RING_SIZE); + + rxbr.vbr->imask = 0; + + while (1) { + /* + * In this loop we process fcopy messages after the + * handshake is complete. + */ + ret = pread(fcopy_fd, &tmp, sizeof(int), 0); + if (ret < 0) { + syslog(LOG_ERR, "pread failed: %s", strerror(errno)); + continue; + } + + len = HV_RING_SIZE; + ret = rte_vmbus_chan_recv_raw(&rxbr, desc, &len); + if (unlikely(ret <= 0)) { + /* This indicates a failure to communicate (or worse) */ + syslog(LOG_ERR, "VMBus channel recv error: %d", ret); + } else { + ret = fcopy_pkt_process(&txbr); + if (ret < 0) + goto close; + + /* Signal host */ + if ((write(fcopy_fd, &tmp, sizeof(int))) != sizeof(int)) { + ret = errno; + syslog(LOG_ERR, "Signal to host failed: %s\n", strerror(ret)); + goto close; + } + } + } +close: + close(fcopy_fd); +exit: + return ret; +} diff --git a/tools/hv/vmbus_bufring.c b/tools/hv/vmbus_bufring.c new file mode 100644 index 000000000000..bac32c1109df --- /dev/null +++ b/tools/hv/vmbus_bufring.c @@ -0,0 +1,318 @@ +// SPDX-License-Identifier: BSD-3-Clause +/* + * Copyright (c) 2009-2012,2016,2023 Microsoft Corp. + * Copyright (c) 2012 NetApp Inc. + * Copyright (c) 2012 Citrix Inc. + * All rights reserved. + */ + +#include <errno.h> +#include <fcntl.h> +#include <emmintrin.h> +#include <linux/limits.h> +#include <stdbool.h> +#include <stdint.h> +#include <stdio.h> +#include <string.h> +#include <sys/mman.h> +#include <sys/uio.h> +#include <unistd.h> +#include "vmbus_bufring.h" + +/** + * Compiler barrier. + * + * Guarantees that operation reordering does not occur at compile time + * for operations directly before and after the barrier. + */ +#define rte_compiler_barrier() ({ asm volatile ("" : : : "memory"); }) + +#define VMBUS_RQST_ERROR 0xFFFFFFFFFFFFFFFF +#define ALIGN(val, align) ((typeof(val))((val) & (~((typeof(val))((align) - 1))))) + +void *vmbus_uio_map(int *fd, int size) +{ + void *map; + + map = mmap(NULL, 2 * size, PROT_READ | PROT_WRITE, MAP_SHARED, *fd, 0); + if (map == MAP_FAILED) + return NULL; + + return map; +} + +/* Increase bufring index by inc with wraparound */ +static inline uint32_t vmbus_br_idxinc(uint32_t idx, uint32_t inc, uint32_t sz) +{ + idx += inc; + if (idx >= sz) + idx -= sz; + + return idx; +} + +void vmbus_br_setup(struct vmbus_br *br, void *buf, unsigned int blen) +{ + br->vbr = buf; + br->windex = br->vbr->windex; + br->dsize = blen - sizeof(struct vmbus_bufring); +} + +static inline __always_inline void +rte_smp_mb(void) +{ + asm volatile("lock addl $0, -128(%%rsp); " ::: "memory"); +} + +static inline int +rte_atomic32_cmpset(volatile uint32_t *dst, uint32_t exp, uint32_t src) +{ + uint8_t res; + + asm volatile("lock ; " + "cmpxchgl %[src], %[dst];" + "sete %[res];" + : [res] "=a" (res), /* output */ + [dst] "=m" (*dst) + : [src] "r" (src), /* input */ + "a" (exp), + "m" (*dst) + : "memory"); /* no-clobber list */ + return res; +} + +static inline uint32_t +vmbus_txbr_copyto(const struct vmbus_br *tbr, uint32_t windex, + const void *src0, uint32_t cplen) +{ + uint8_t *br_data = tbr->vbr->data; + uint32_t br_dsize = tbr->dsize; + const uint8_t *src = src0; + + /* XXX use double mapping like Linux kernel? */ + if (cplen > br_dsize - windex) { + uint32_t fraglen = br_dsize - windex; + + /* Wrap-around detected */ + memcpy(br_data + windex, src, fraglen); + memcpy(br_data, src + fraglen, cplen - fraglen); + } else { + memcpy(br_data + windex, src, cplen); + } + + return vmbus_br_idxinc(windex, cplen, br_dsize); +} + +/* + * Write scattered channel packet to TX bufring. + * + * The offset of this channel packet is written as a 64bits value + * immediately after this channel packet. + * + * The write goes through three stages: + * 1. Reserve space in ring buffer for the new data. + * Writer atomically moves priv_write_index. + * 2. Copy the new data into the ring. + * 3. Update the tail of the ring (visible to host) that indicates + * next read location. Writer updates write_index + */ +static int +vmbus_txbr_write(struct vmbus_br *tbr, const struct iovec iov[], int iovlen) +{ + struct vmbus_bufring *vbr = tbr->vbr; + uint32_t ring_size = tbr->dsize; + uint32_t old_windex, next_windex, windex, total; + uint64_t save_windex; + int i; + + total = 0; + for (i = 0; i < iovlen; i++) + total += iov[i].iov_len; + total += sizeof(save_windex); + + /* Reserve space in ring */ + do { + uint32_t avail; + + /* Get current free location */ + old_windex = tbr->windex; + + /* Prevent compiler reordering this with calculation */ + rte_compiler_barrier(); + + avail = vmbus_br_availwrite(tbr, old_windex); + + /* If not enough space in ring, then tell caller. */ + if (avail <= total) + return -EAGAIN; + + next_windex = vmbus_br_idxinc(old_windex, total, ring_size); + + /* Atomic update of next write_index for other threads */ + } while (!rte_atomic32_cmpset(&tbr->windex, old_windex, next_windex)); + + /* Space from old..new is now reserved */ + windex = old_windex; + for (i = 0; i < iovlen; i++) + windex = vmbus_txbr_copyto(tbr, windex, iov[i].iov_base, iov[i].iov_len); + + /* Set the offset of the current channel packet. */ + save_windex = ((uint64_t)old_windex) << 32; + windex = vmbus_txbr_copyto(tbr, windex, &save_windex, + sizeof(save_windex)); + + /* The region reserved should match region used */ + if (windex != next_windex) + return -EINVAL; + + /* Ensure that data is available before updating host index */ + rte_compiler_barrier(); + + /* Checkin for our reservation. wait for our turn to update host */ + while (!rte_atomic32_cmpset(&vbr->windex, old_windex, next_windex)) + _mm_pause(); + + return 0; +} + +int rte_vmbus_chan_send(struct vmbus_br *txbr, uint16_t type, void *data, + uint32_t dlen, uint32_t flags) +{ + struct vmbus_chanpkt pkt; + unsigned int pktlen, pad_pktlen; + const uint32_t hlen = sizeof(pkt); + uint64_t pad = 0; + struct iovec iov[3]; + int error; + + pktlen = hlen + dlen; + pad_pktlen = ALIGN(pktlen, sizeof(uint64_t)); + + pkt.hdr.type = type; + pkt.hdr.flags = flags; + pkt.hdr.hlen = hlen >> VMBUS_CHANPKT_SIZE_SHIFT; + pkt.hdr.tlen = pad_pktlen >> VMBUS_CHANPKT_SIZE_SHIFT; + pkt.hdr.xactid = VMBUS_RQST_ERROR; + + iov[0].iov_base = &pkt; + iov[0].iov_len = hlen; + iov[1].iov_base = data; + iov[1].iov_len = dlen; + iov[2].iov_base = &pad; + iov[2].iov_len = pad_pktlen - pktlen; + + error = vmbus_txbr_write(txbr, iov, 3); + + return error; +} + +static inline uint32_t +vmbus_rxbr_copyfrom(const struct vmbus_br *rbr, uint32_t rindex, + void *dst0, size_t cplen) +{ + const uint8_t *br_data = rbr->vbr->data; + uint32_t br_dsize = rbr->dsize; + uint8_t *dst = dst0; + + if (cplen > br_dsize - rindex) { + uint32_t fraglen = br_dsize - rindex; + + /* Wrap-around detected. */ + memcpy(dst, br_data + rindex, fraglen); + memcpy(dst + fraglen, br_data, cplen - fraglen); + } else { + memcpy(dst, br_data + rindex, cplen); + } + + return vmbus_br_idxinc(rindex, cplen, br_dsize); +} + +/* Copy data from receive ring but don't change index */ +static int +vmbus_rxbr_peek(const struct vmbus_br *rbr, void *data, size_t dlen) +{ + uint32_t avail; + + /* + * The requested data and the 64bits channel packet + * offset should be there at least. + */ + avail = vmbus_br_availread(rbr); + if (avail < dlen + sizeof(uint64_t)) + return -EAGAIN; + + vmbus_rxbr_copyfrom(rbr, rbr->vbr->rindex, data, dlen); + return 0; +} + +/* + * Copy data from receive ring and change index + * NOTE: + * We assume (dlen + skip) == sizeof(channel packet). + */ +static int +vmbus_rxbr_read(struct vmbus_br *rbr, void *data, size_t dlen, size_t skip) +{ + struct vmbus_bufring *vbr = rbr->vbr; + uint32_t br_dsize = rbr->dsize; + uint32_t rindex; + + if (vmbus_br_availread(rbr) < dlen + skip + sizeof(uint64_t)) + return -EAGAIN; + + /* Record where host was when we started read (for debug) */ + rbr->windex = rbr->vbr->windex; + + /* + * Copy channel packet from RX bufring. + */ + rindex = vmbus_br_idxinc(rbr->vbr->rindex, skip, br_dsize); + rindex = vmbus_rxbr_copyfrom(rbr, rindex, data, dlen); + + /* + * Discard this channel packet's 64bits offset, which is useless to us. + */ + rindex = vmbus_br_idxinc(rindex, sizeof(uint64_t), br_dsize); + + /* Update the read index _after_ the channel packet is fetched. */ + rte_compiler_barrier(); + + vbr->rindex = rindex; + + return 0; +} + +int rte_vmbus_chan_recv_raw(struct vmbus_br *rxbr, + void *data, uint32_t *len) +{ + struct vmbus_chanpkt_hdr pkt; + uint32_t dlen, bufferlen = *len; + int error; + + error = vmbus_rxbr_peek(rxbr, &pkt, sizeof(pkt)); + if (error) + return error; + + if (unlikely(pkt.hlen < VMBUS_CHANPKT_HLEN_MIN)) + /* XXX this channel is dead actually. */ + return -EIO; + + if (unlikely(pkt.hlen > pkt.tlen)) + return -EIO; + + /* Length are in quad words */ + dlen = pkt.tlen << VMBUS_CHANPKT_SIZE_SHIFT; + *len = dlen; + + /* If caller buffer is not large enough */ + if (unlikely(dlen > bufferlen)) + return -ENOBUFS; + + /* Read data and skip packet header */ + error = vmbus_rxbr_read(rxbr, data, dlen, 0); + if (error) + return error; + + /* Return the number of bytes read */ + return dlen + sizeof(uint64_t); +} diff --git a/tools/hv/vmbus_bufring.h b/tools/hv/vmbus_bufring.h new file mode 100644 index 000000000000..6e7caacfff57 --- /dev/null +++ b/tools/hv/vmbus_bufring.h @@ -0,0 +1,158 @@ +/* SPDX-License-Identifier: BSD-3-Clause */ + +#ifndef _VMBUS_BUF_H_ +#define _VMBUS_BUF_H_ + +#include <stdbool.h> +#include <stdint.h> + +#define __packed __attribute__((__packed__)) +#define unlikely(x) __builtin_expect(!!(x), 0) + +#define ICMSGHDRFLAG_TRANSACTION 1 +#define ICMSGHDRFLAG_REQUEST 2 +#define ICMSGHDRFLAG_RESPONSE 4 + +#define IC_VERSION_NEGOTIATION_MAX_VER_COUNT 100 +#define ICMSG_HDR (sizeof(struct vmbuspipe_hdr) + sizeof(struct icmsg_hdr)) +#define ICMSG_NEGOTIATE_PKT_SIZE(icframe_vercnt, icmsg_vercnt) \ + (ICMSG_HDR + sizeof(struct icmsg_negotiate) + \ + (((icframe_vercnt) + (icmsg_vercnt)) * sizeof(struct ic_version))) + +/* + * Channel packets + */ + +/* Channel packet flags */ +#define VMBUS_CHANPKT_TYPE_INBAND 0x0006 +#define VMBUS_CHANPKT_TYPE_RXBUF 0x0007 +#define VMBUS_CHANPKT_TYPE_GPA 0x0009 +#define VMBUS_CHANPKT_TYPE_COMP 0x000b + +#define VMBUS_CHANPKT_FLAG_NONE 0 +#define VMBUS_CHANPKT_FLAG_RC 0x0001 /* report completion */ + +#define VMBUS_CHANPKT_SIZE_SHIFT 3 +#define VMBUS_CHANPKT_SIZE_ALIGN BIT(VMBUS_CHANPKT_SIZE_SHIFT) +#define VMBUS_CHANPKT_HLEN_MIN \ + (sizeof(struct vmbus_chanpkt_hdr) >> VMBUS_CHANPKT_SIZE_SHIFT) + +/* + * Buffer ring + */ +struct vmbus_bufring { + volatile uint32_t windex; + volatile uint32_t rindex; + + /* + * Interrupt mask {0,1} + * + * For TX bufring, host set this to 1, when it is processing + * the TX bufring, so that we can safely skip the TX event + * notification to host. + * + * For RX bufring, once this is set to 1 by us, host will not + * further dispatch interrupts to us, even if there are data + * pending on the RX bufring. This effectively disables the + * interrupt of the channel to which this RX bufring is attached. + */ + volatile uint32_t imask; + + /* + * Win8 uses some of the reserved bits to implement + * interrupt driven flow management. On the send side + * we can request that the receiver interrupt the sender + * when the ring transitions from being full to being able + * to handle a message of size "pending_send_sz". + * + * Add necessary state for this enhancement. + */ + volatile uint32_t pending_send; + uint32_t reserved1[12]; + + union { + struct { + uint32_t feat_pending_send_sz:1; + }; + uint32_t value; + } feature_bits; + + /* Pad it to rte_mem_page_size() so that data starts on page boundary */ + uint8_t reserved2[4028]; + + /* + * Ring data starts here + RingDataStartOffset + * !!! DO NOT place any fields below this !!! + */ + uint8_t data[]; +} __packed; + +struct vmbus_br { + struct vmbus_bufring *vbr; + uint32_t dsize; + uint32_t windex; /* next available location */ +}; + +struct vmbus_chanpkt_hdr { + uint16_t type; /* VMBUS_CHANPKT_TYPE_ */ + uint16_t hlen; /* header len, in 8 bytes */ + uint16_t tlen; /* total len, in 8 bytes */ + uint16_t flags; /* VMBUS_CHANPKT_FLAG_ */ + uint64_t xactid; +} __packed; + +struct vmbus_chanpkt { + struct vmbus_chanpkt_hdr hdr; +} __packed; + +struct vmbuspipe_hdr { + unsigned int flags; + unsigned int msgsize; +} __packed; + +struct ic_version { + unsigned short major; + unsigned short minor; +} __packed; + +struct icmsg_negotiate { + unsigned short icframe_vercnt; + unsigned short icmsg_vercnt; + unsigned int reserved; + struct ic_version icversion_data[]; /* any size array */ +} __packed; + +struct icmsg_hdr { + struct ic_version icverframe; + unsigned short icmsgtype; + struct ic_version icvermsg; + unsigned short icmsgsize; + unsigned int status; + unsigned char ictransaction_id; + unsigned char icflags; + unsigned char reserved[2]; +} __packed; + +int rte_vmbus_chan_recv_raw(struct vmbus_br *rxbr, void *data, uint32_t *len); +int rte_vmbus_chan_send(struct vmbus_br *txbr, uint16_t type, void *data, + uint32_t dlen, uint32_t flags); +void vmbus_br_setup(struct vmbus_br *br, void *buf, unsigned int blen); +void *vmbus_uio_map(int *fd, int size); + +/* Amount of space available for write */ +static inline uint32_t vmbus_br_availwrite(const struct vmbus_br *br, uint32_t windex) +{ + uint32_t rindex = br->vbr->rindex; + + if (windex >= rindex) + return br->dsize - (windex - rindex); + else + return rindex - windex; +} + +static inline uint32_t vmbus_br_availread(const struct vmbus_br *br) +{ + return br->dsize - vmbus_br_availwrite(br, br->vbr->windex); +} + +#endif /* !_VMBUS_BUF_H_ */ diff --git a/tools/testing/selftests/drivers/net/stats.py b/tools/testing/selftests/drivers/net/stats.py index 7a7b16b180e2..820b8e0a22c6 100755 --- a/tools/testing/selftests/drivers/net/stats.py +++ b/tools/testing/selftests/drivers/net/stats.py @@ -69,7 +69,7 @@ def pkt_byte_sum(cfg) -> None: return 0 for _ in range(10): - rtstat = rtnl.getlink({"ifi-index": cfg.ifindex})['stats'] + rtstat = rtnl.getlink({"ifi-index": cfg.ifindex})['stats64'] if stat_cmp(rtstat, qstat) < 0: raise Exception("RTNL stats are lower, fetched later") qstat = get_qstat(cfg) diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 3c8f2965c285..b634969cbb6f 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -1216,7 +1216,7 @@ void __run_test(struct __fixture_metadata *f, struct __test_metadata *t) { struct __test_xfail *xfail; - char *test_name; + char test_name[1024]; const char *diagnostic; /* reset test struct */ @@ -1227,12 +1227,8 @@ void __run_test(struct __fixture_metadata *f, memset(t->env, 0, sizeof(t->env)); memset(t->results->reason, 0, sizeof(t->results->reason)); - if (asprintf(&test_name, "%s%s%s.%s", f->name, - variant->name[0] ? "." : "", variant->name, t->name) == -1) { - ksft_print_msg("ERROR ALLOCATING MEMORY\n"); - t->exit_code = KSFT_FAIL; - _exit(t->exit_code); - } + snprintf(test_name, sizeof(test_name), "%s%s%s.%s", + f->name, variant->name[0] ? "." : "", variant->name, t->name); ksft_print_msg(" RUN %s ...\n", test_name); @@ -1270,7 +1266,6 @@ void __run_test(struct __fixture_metadata *f, ksft_test_result_code(t->exit_code, test_name, diagnostic ? "%s" : NULL, diagnostic); - free(test_name); } static int test_harness_run(int argc, char **argv) diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore index d26e962f2ac4..0b9ab987601c 100644 --- a/tools/testing/selftests/mm/.gitignore +++ b/tools/testing/selftests/mm/.gitignore @@ -47,3 +47,5 @@ mkdirty va_high_addr_switch hugetlb_fault_after_madv hugetlb_madv_vs_map +mseal_test +seal_elf diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 60b8feb6a5ec..3b49bc3d0a3b 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -59,6 +59,8 @@ TEST_GEN_FILES += mlock2-tests TEST_GEN_FILES += mrelease_test TEST_GEN_FILES += mremap_dontunmap TEST_GEN_FILES += mremap_test +TEST_GEN_FILES += mseal_test +TEST_GEN_FILES += seal_elf TEST_GEN_FILES += on-fault-limit TEST_GEN_FILES += pagemap_ioctl TEST_GEN_FILES += thuge-gen diff --git a/tools/testing/selftests/mm/compaction_test.c b/tools/testing/selftests/mm/compaction_test.c index 4f42eb7d7636..e140558e6f53 100644 --- a/tools/testing/selftests/mm/compaction_test.c +++ b/tools/testing/selftests/mm/compaction_test.c @@ -82,12 +82,16 @@ int prereq(void) return -1; } -int check_compaction(unsigned long mem_free, unsigned int hugepage_size) +int check_compaction(unsigned long mem_free, unsigned long hugepage_size, + unsigned long initial_nr_hugepages) { + unsigned long nr_hugepages_ul; int fd, ret = -1; int compaction_index = 0; - char initial_nr_hugepages[10] = {0}; - char nr_hugepages[10] = {0}; + char nr_hugepages[20] = {0}; + char init_nr_hugepages[20] = {0}; + + sprintf(init_nr_hugepages, "%lu", initial_nr_hugepages); /* We want to test with 80% of available memory. Else, OOM killer comes in to play */ @@ -101,21 +105,6 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size) goto out; } - if (read(fd, initial_nr_hugepages, sizeof(initial_nr_hugepages)) <= 0) { - ksft_print_msg("Failed to read from /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); - goto close_fd; - } - - /* Start with the initial condition of 0 huge pages*/ - if (write(fd, "0", sizeof(char)) != sizeof(char)) { - ksft_print_msg("Failed to write 0 to /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); - goto close_fd; - } - - lseek(fd, 0, SEEK_SET); - /* Request a large number of huge pages. The Kernel will allocate as much as it can */ if (write(fd, "100000", (6*sizeof(char))) != (6*sizeof(char))) { @@ -134,22 +123,27 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size) /* We should have been able to request at least 1/3 rd of the memory in huge pages */ - compaction_index = mem_free/(atoi(nr_hugepages) * hugepage_size); + nr_hugepages_ul = strtoul(nr_hugepages, NULL, 10); + if (!nr_hugepages_ul) { + ksft_print_msg("ERROR: No memory is available as huge pages\n"); + goto close_fd; + } + compaction_index = mem_free/(nr_hugepages_ul * hugepage_size); lseek(fd, 0, SEEK_SET); - if (write(fd, initial_nr_hugepages, strlen(initial_nr_hugepages)) - != strlen(initial_nr_hugepages)) { + if (write(fd, init_nr_hugepages, strlen(init_nr_hugepages)) + != strlen(init_nr_hugepages)) { ksft_print_msg("Failed to write value to /proc/sys/vm/nr_hugepages: %s\n", strerror(errno)); goto close_fd; } - ksft_print_msg("Number of huge pages allocated = %d\n", - atoi(nr_hugepages)); + ksft_print_msg("Number of huge pages allocated = %lu\n", + nr_hugepages_ul); if (compaction_index > 3) { - ksft_print_msg("ERROR: Less that 1/%d of memory is available\n" + ksft_print_msg("ERROR: Less than 1/%d of memory is available\n" "as huge pages\n", compaction_index); goto close_fd; } @@ -163,6 +157,41 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size) return ret; } +int set_zero_hugepages(unsigned long *initial_nr_hugepages) +{ + int fd, ret = -1; + char nr_hugepages[20] = {0}; + + fd = open("/proc/sys/vm/nr_hugepages", O_RDWR | O_NONBLOCK); + if (fd < 0) { + ksft_print_msg("Failed to open /proc/sys/vm/nr_hugepages: %s\n", + strerror(errno)); + goto out; + } + if (read(fd, nr_hugepages, sizeof(nr_hugepages)) <= 0) { + ksft_print_msg("Failed to read from /proc/sys/vm/nr_hugepages: %s\n", + strerror(errno)); + goto close_fd; + } + + lseek(fd, 0, SEEK_SET); + + /* Start with the initial condition of 0 huge pages */ + if (write(fd, "0", sizeof(char)) != sizeof(char)) { + ksft_print_msg("Failed to write 0 to /proc/sys/vm/nr_hugepages: %s\n", + strerror(errno)); + goto close_fd; + } + + *initial_nr_hugepages = strtoul(nr_hugepages, NULL, 10); + ret = 0; + + close_fd: + close(fd); + + out: + return ret; +} int main(int argc, char **argv) { @@ -173,6 +202,7 @@ int main(int argc, char **argv) unsigned long mem_free = 0; unsigned long hugepage_size = 0; long mem_fragmentable_MB = 0; + unsigned long initial_nr_hugepages; ksft_print_header(); @@ -181,6 +211,10 @@ int main(int argc, char **argv) ksft_set_plan(1); + /* Start the test without hugepages reducing mem_free */ + if (set_zero_hugepages(&initial_nr_hugepages)) + ksft_exit_fail(); + lim.rlim_cur = RLIM_INFINITY; lim.rlim_max = RLIM_INFINITY; if (setrlimit(RLIMIT_MEMLOCK, &lim)) @@ -224,7 +258,8 @@ int main(int argc, char **argv) entry = entry->next; } - if (check_compaction(mem_free, hugepage_size) == 0) + if (check_compaction(mem_free, hugepage_size, + initial_nr_hugepages) == 0) ksft_exit_pass(); ksft_exit_fail(); diff --git a/tools/testing/selftests/mm/gup_test.c b/tools/testing/selftests/mm/gup_test.c index bd335cf9bc0e..bdeaac67ff9a 100644 --- a/tools/testing/selftests/mm/gup_test.c +++ b/tools/testing/selftests/mm/gup_test.c @@ -1,3 +1,4 @@ +#define __SANE_USERSPACE_TYPES__ // Use ll64 #include <fcntl.h> #include <errno.h> #include <stdio.h> diff --git a/tools/testing/selftests/mm/mdwe_test.c b/tools/testing/selftests/mm/mdwe_test.c index 1e01d3ddc11c..200bedcdc32e 100644 --- a/tools/testing/selftests/mm/mdwe_test.c +++ b/tools/testing/selftests/mm/mdwe_test.c @@ -7,7 +7,6 @@ #include <linux/mman.h> #include <linux/prctl.h> -#define _GNU_SOURCE #include <stdio.h> #include <stdlib.h> #include <sys/auxv.h> diff --git a/tools/testing/selftests/mm/mseal_test.c b/tools/testing/selftests/mm/mseal_test.c new file mode 100644 index 000000000000..41998cf1dcf5 --- /dev/null +++ b/tools/testing/selftests/mm/mseal_test.c @@ -0,0 +1,1894 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#include <linux/mman.h> +#include <sys/mman.h> +#include <stdint.h> +#include <unistd.h> +#include <string.h> +#include <sys/time.h> +#include <sys/resource.h> +#include <stdbool.h> +#include "../kselftest.h" +#include <syscall.h> +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <fcntl.h> +#include <sys/ioctl.h> +#include <sys/vfs.h> +#include <sys/stat.h> + +/* + * need those definition for manually build using gcc. + * gcc -I ../../../../usr/include -DDEBUG -O3 -DDEBUG -O3 mseal_test.c -o mseal_test + */ +#ifndef PKEY_DISABLE_ACCESS +# define PKEY_DISABLE_ACCESS 0x1 +#endif + +#ifndef PKEY_DISABLE_WRITE +# define PKEY_DISABLE_WRITE 0x2 +#endif + +#ifndef PKEY_BITS_PER_PKEY +#define PKEY_BITS_PER_PKEY 2 +#endif + +#ifndef PKEY_MASK +#define PKEY_MASK (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE) +#endif + +#define FAIL_TEST_IF_FALSE(c) do {\ + if (!(c)) {\ + ksft_test_result_fail("%s, line:%d\n", __func__, __LINE__);\ + goto test_end;\ + } \ + } \ + while (0) + +#define SKIP_TEST_IF_FALSE(c) do {\ + if (!(c)) {\ + ksft_test_result_skip("%s, line:%d\n", __func__, __LINE__);\ + goto test_end;\ + } \ + } \ + while (0) + + +#define TEST_END_CHECK() {\ + ksft_test_result_pass("%s\n", __func__);\ + return;\ +test_end:\ + return;\ +} + +#ifndef u64 +#define u64 unsigned long long +#endif + +static unsigned long get_vma_size(void *addr, int *prot) +{ + FILE *maps; + char line[256]; + int size = 0; + uintptr_t addr_start, addr_end; + char protstr[5]; + *prot = 0; + + maps = fopen("/proc/self/maps", "r"); + if (!maps) + return 0; + + while (fgets(line, sizeof(line), maps)) { + if (sscanf(line, "%lx-%lx %4s", &addr_start, &addr_end, protstr) == 3) { + if (addr_start == (uintptr_t) addr) { + size = addr_end - addr_start; + if (protstr[0] == 'r') + *prot |= 0x4; + if (protstr[1] == 'w') + *prot |= 0x2; + if (protstr[2] == 'x') + *prot |= 0x1; + break; + } + } + } + fclose(maps); + return size; +} + +/* + * define sys_xyx to call syscall directly. + */ +static int sys_mseal(void *start, size_t len) +{ + int sret; + + errno = 0; + sret = syscall(__NR_mseal, start, len, 0); + return sret; +} + +static int sys_mprotect(void *ptr, size_t size, unsigned long prot) +{ + int sret; + + errno = 0; + sret = syscall(__NR_mprotect, ptr, size, prot); + return sret; +} + +static int sys_mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot, + unsigned long pkey) +{ + int sret; + + errno = 0; + sret = syscall(__NR_pkey_mprotect, ptr, size, orig_prot, pkey); + return sret; +} + +static void *sys_mmap(void *addr, unsigned long len, unsigned long prot, + unsigned long flags, unsigned long fd, unsigned long offset) +{ + void *sret; + + errno = 0; + sret = (void *) syscall(__NR_mmap, addr, len, prot, + flags, fd, offset); + return sret; +} + +static int sys_munmap(void *ptr, size_t size) +{ + int sret; + + errno = 0; + sret = syscall(__NR_munmap, ptr, size); + return sret; +} + +static int sys_madvise(void *start, size_t len, int types) +{ + int sret; + + errno = 0; + sret = syscall(__NR_madvise, start, len, types); + return sret; +} + +static int sys_pkey_alloc(unsigned long flags, unsigned long init_val) +{ + int ret = syscall(__NR_pkey_alloc, flags, init_val); + + return ret; +} + +static unsigned int __read_pkey_reg(void) +{ + unsigned int pkey_reg = 0; +#if defined(__i386__) || defined(__x86_64__) /* arch */ + unsigned int eax, edx; + unsigned int ecx = 0; + + asm volatile(".byte 0x0f,0x01,0xee\n\t" + : "=a" (eax), "=d" (edx) + : "c" (ecx)); + pkey_reg = eax; +#endif + return pkey_reg; +} + +static void __write_pkey_reg(u64 pkey_reg) +{ +#if defined(__i386__) || defined(__x86_64__) /* arch */ + unsigned int eax = pkey_reg; + unsigned int ecx = 0; + unsigned int edx = 0; + + asm volatile(".byte 0x0f,0x01,0xef\n\t" + : : "a" (eax), "c" (ecx), "d" (edx)); +#endif +} + +static unsigned long pkey_bit_position(int pkey) +{ + return pkey * PKEY_BITS_PER_PKEY; +} + +static u64 set_pkey_bits(u64 reg, int pkey, u64 flags) +{ + unsigned long shift = pkey_bit_position(pkey); + + /* mask out bits from pkey in old value */ + reg &= ~((u64)PKEY_MASK << shift); + /* OR in new bits for pkey */ + reg |= (flags & PKEY_MASK) << shift; + return reg; +} + +static void set_pkey(int pkey, unsigned long pkey_value) +{ + u64 new_pkey_reg; + + new_pkey_reg = set_pkey_bits(__read_pkey_reg(), pkey, pkey_value); + __write_pkey_reg(new_pkey_reg); +} + +static void setup_single_address(int size, void **ptrOut) +{ + void *ptr; + + ptr = sys_mmap(NULL, size, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + *ptrOut = ptr; +} + +static void setup_single_address_rw(int size, void **ptrOut) +{ + void *ptr; + unsigned long mapflags = MAP_ANONYMOUS | MAP_PRIVATE; + + ptr = sys_mmap(NULL, size, PROT_READ | PROT_WRITE, mapflags, -1, 0); + *ptrOut = ptr; +} + +static int clean_single_address(void *ptr, int size) +{ + int ret; + ret = munmap(ptr, size); + return ret; +} + +static int seal_single_address(void *ptr, int size) +{ + int ret; + ret = sys_mseal(ptr, size); + return ret; +} + +bool seal_support(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + + ptr = sys_mmap(NULL, page_size, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + if (ptr == (void *) -1) + return false; + + ret = sys_mseal(ptr, page_size); + if (ret < 0) + return false; + + return true; +} + +bool pkey_supported(void) +{ +#if defined(__i386__) || defined(__x86_64__) /* arch */ + int pkey = sys_pkey_alloc(0, 0); + + if (pkey > 0) + return true; +#endif + return false; +} + +static void test_seal_addseal(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_unmapped_start(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* munmap 2 pages from ptr. */ + ret = sys_munmap(ptr, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + /* mprotect will fail because 2 pages from ptr are unmapped. */ + ret = sys_mprotect(ptr, size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(ret < 0); + + /* mseal will fail because 2 pages from ptr are unmapped. */ + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(ret < 0); + + ret = sys_mseal(ptr + 2 * page_size, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_unmapped_middle(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* munmap 2 pages from ptr + page. */ + ret = sys_munmap(ptr + page_size, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + /* mprotect will fail, since middle 2 pages are unmapped. */ + ret = sys_mprotect(ptr, size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(ret < 0); + + /* mseal will fail as well. */ + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(ret < 0); + + /* we still can add seal to the first page and last page*/ + ret = sys_mseal(ptr, page_size); + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_mseal(ptr + 3 * page_size, page_size); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_unmapped_end(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* unmap last 2 pages. */ + ret = sys_munmap(ptr + 2 * page_size, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + /* mprotect will fail since last 2 pages are unmapped. */ + ret = sys_mprotect(ptr, size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(ret < 0); + + /* mseal will fail as well. */ + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(ret < 0); + + /* The first 2 pages is not sealed, and can add seals */ + ret = sys_mseal(ptr, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_multiple_vmas(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect to split the vma into 3. */ + ret = sys_mprotect(ptr + page_size, 2 * page_size, + PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* mprotect will get applied to all 4 pages - 3 VMAs. */ + ret = sys_mprotect(ptr, size, PROT_READ); + FAIL_TEST_IF_FALSE(!ret); + + /* use mprotect to split the vma into 3. */ + ret = sys_mprotect(ptr + page_size, 2 * page_size, + PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* mseal get applied to all 4 pages - 3 VMAs. */ + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_split_start(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect to split at middle */ + ret = sys_mprotect(ptr, 2 * page_size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* seal the first page, this will split the VMA */ + ret = sys_mseal(ptr, page_size); + FAIL_TEST_IF_FALSE(!ret); + + /* add seal to the remain 3 pages */ + ret = sys_mseal(ptr + page_size, 3 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_split_end(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect to split at middle */ + ret = sys_mprotect(ptr, 2 * page_size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* seal the last page */ + ret = sys_mseal(ptr + 3 * page_size, page_size); + FAIL_TEST_IF_FALSE(!ret); + + /* Adding seals to the first 3 pages */ + ret = sys_mseal(ptr, 3 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_invalid_input(void) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(8 * page_size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + ret = clean_single_address(ptr + 4 * page_size, 4 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + /* invalid flag */ + ret = syscall(__NR_mseal, ptr, size, 0x20); + FAIL_TEST_IF_FALSE(ret < 0); + + /* unaligned address */ + ret = sys_mseal(ptr + 1, 2 * page_size); + FAIL_TEST_IF_FALSE(ret < 0); + + /* length too big */ + ret = sys_mseal(ptr, 5 * page_size); + FAIL_TEST_IF_FALSE(ret < 0); + + /* length overflow */ + ret = sys_mseal(ptr, UINT64_MAX/page_size); + FAIL_TEST_IF_FALSE(ret < 0); + + /* start is not in a valid VMA */ + ret = sys_mseal(ptr - page_size, 5 * page_size); + FAIL_TEST_IF_FALSE(ret < 0); + + TEST_END_CHECK(); +} + +static void test_seal_zero_length(void) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + ret = sys_mprotect(ptr, 0, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* seal 0 length will be OK, same as mprotect */ + ret = sys_mseal(ptr, 0); + FAIL_TEST_IF_FALSE(!ret); + + /* verify the 4 pages are not sealed by previous call. */ + ret = sys_mprotect(ptr, size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_zero_address(void) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + int prot; + + /* use mmap to change protection. */ + ptr = sys_mmap(0, size, PROT_NONE, + MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0); + FAIL_TEST_IF_FALSE(ptr == 0); + + size = get_vma_size(ptr, &prot); + FAIL_TEST_IF_FALSE(size == 4 * page_size); + + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + + /* verify the 4 pages are sealed by previous call. */ + ret = sys_mprotect(ptr, size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(ret); + + TEST_END_CHECK(); +} + +static void test_seal_twice(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + + /* apply the same seal will be OK. idempotent. */ + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_mprotect(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = seal_single_address(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + ret = sys_mprotect(ptr, size, PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_start_mprotect(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = seal_single_address(ptr, page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* the first page is sealed. */ + ret = sys_mprotect(ptr, page_size, PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + /* pages after the first page is not sealed. */ + ret = sys_mprotect(ptr + page_size, page_size * 3, + PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_end_mprotect(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = seal_single_address(ptr + page_size, 3 * page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* first page is not sealed */ + ret = sys_mprotect(ptr, page_size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* last 3 page are sealed */ + ret = sys_mprotect(ptr + page_size, page_size * 3, + PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_mprotect_unalign_len(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = seal_single_address(ptr, page_size * 2 - 1); + FAIL_TEST_IF_FALSE(!ret); + } + + /* 2 pages are sealed. */ + ret = sys_mprotect(ptr, page_size * 2, PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_mprotect(ptr + page_size * 2, page_size, + PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_mprotect_unalign_len_variant_2(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + if (seal) { + ret = seal_single_address(ptr, page_size * 2 + 1); + FAIL_TEST_IF_FALSE(!ret); + } + + /* 3 pages are sealed. */ + ret = sys_mprotect(ptr, page_size * 3, PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_mprotect(ptr + page_size * 3, page_size, + PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_mprotect_two_vma(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect to split */ + ret = sys_mprotect(ptr, page_size * 2, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + if (seal) { + ret = seal_single_address(ptr, page_size * 4); + FAIL_TEST_IF_FALSE(!ret); + } + + ret = sys_mprotect(ptr, page_size * 2, PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_mprotect(ptr + page_size * 2, page_size * 2, + PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_mprotect_two_vma_with_split(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect to split as two vma. */ + ret = sys_mprotect(ptr, page_size * 2, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* mseal can apply across 2 vma, also split them. */ + if (seal) { + ret = seal_single_address(ptr + page_size, page_size * 2); + FAIL_TEST_IF_FALSE(!ret); + } + + /* the first page is not sealed. */ + ret = sys_mprotect(ptr, page_size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* the second page is sealed. */ + ret = sys_mprotect(ptr + page_size, page_size, PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + /* the third page is sealed. */ + ret = sys_mprotect(ptr + 2 * page_size, page_size, + PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + /* the fouth page is not sealed. */ + ret = sys_mprotect(ptr + 3 * page_size, page_size, + PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_mprotect_partial_mprotect(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* seal one page. */ + if (seal) { + ret = seal_single_address(ptr, page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* mprotect first 2 page will fail, since the first page are sealed. */ + ret = sys_mprotect(ptr, 2 * page_size, PROT_READ | PROT_WRITE); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_mprotect_two_vma_with_gap(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect to split. */ + ret = sys_mprotect(ptr, page_size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* use mprotect to split. */ + ret = sys_mprotect(ptr + 3 * page_size, page_size, + PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* use munmap to free two pages in the middle */ + ret = sys_munmap(ptr + page_size, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + /* mprotect will fail, because there is a gap in the address. */ + /* notes, internally mprotect still updated the first page. */ + ret = sys_mprotect(ptr, 4 * page_size, PROT_READ); + FAIL_TEST_IF_FALSE(ret < 0); + + /* mseal will fail as well. */ + ret = sys_mseal(ptr, 4 * page_size); + FAIL_TEST_IF_FALSE(ret < 0); + + /* the first page is not sealed. */ + ret = sys_mprotect(ptr, page_size, PROT_READ); + FAIL_TEST_IF_FALSE(ret == 0); + + /* the last page is not sealed. */ + ret = sys_mprotect(ptr + 3 * page_size, page_size, PROT_READ); + FAIL_TEST_IF_FALSE(ret == 0); + + TEST_END_CHECK(); +} + +static void test_seal_mprotect_split(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect to split. */ + ret = sys_mprotect(ptr, page_size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* seal all 4 pages. */ + if (seal) { + ret = sys_mseal(ptr, 4 * page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* mprotect is sealed. */ + ret = sys_mprotect(ptr, 2 * page_size, PROT_READ); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + + ret = sys_mprotect(ptr + 2 * page_size, 2 * page_size, PROT_READ); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_mprotect_merge(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect to split one page. */ + ret = sys_mprotect(ptr, page_size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + /* seal first two pages. */ + if (seal) { + ret = sys_mseal(ptr, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* 2 pages are sealed. */ + ret = sys_mprotect(ptr, 2 * page_size, PROT_READ); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + /* last 2 pages are not sealed. */ + ret = sys_mprotect(ptr + 2 * page_size, 2 * page_size, PROT_READ); + FAIL_TEST_IF_FALSE(ret == 0); + + TEST_END_CHECK(); +} + +static void test_seal_munmap(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* 4 pages are sealed. */ + ret = sys_munmap(ptr, size); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +/* + * allocate 4 pages, + * use mprotect to split it as two VMAs + * seal the whole range + * munmap will fail on both + */ +static void test_seal_munmap_two_vma(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect to split */ + ret = sys_mprotect(ptr, page_size * 2, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + ret = sys_munmap(ptr, page_size * 2); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_munmap(ptr + page_size, page_size * 2); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +/* + * allocate a VMA with 4 pages. + * munmap the middle 2 pages. + * seal the whole 4 pages, will fail. + * munmap the first page will be OK. + * munmap the last page will be OK. + */ +static void test_seal_munmap_vma_with_gap(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + ret = sys_munmap(ptr + page_size, page_size * 2); + FAIL_TEST_IF_FALSE(!ret); + + if (seal) { + /* can't have gap in the middle. */ + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(ret < 0); + } + + ret = sys_munmap(ptr, page_size); + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_munmap(ptr + page_size * 2, page_size); + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_munmap(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_munmap_start_freed(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + int prot; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* unmap the first page. */ + ret = sys_munmap(ptr, page_size); + FAIL_TEST_IF_FALSE(!ret); + + /* seal the last 3 pages. */ + if (seal) { + ret = sys_mseal(ptr + page_size, 3 * page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* unmap from the first page. */ + ret = sys_munmap(ptr, size); + if (seal) { + FAIL_TEST_IF_FALSE(ret < 0); + + size = get_vma_size(ptr + page_size, &prot); + FAIL_TEST_IF_FALSE(size == page_size * 3); + } else { + /* note: this will be OK, even the first page is */ + /* already unmapped. */ + FAIL_TEST_IF_FALSE(!ret); + + size = get_vma_size(ptr + page_size, &prot); + FAIL_TEST_IF_FALSE(size == 0); + } + + TEST_END_CHECK(); +} + +static void test_munmap_end_freed(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* unmap last page. */ + ret = sys_munmap(ptr + page_size * 3, page_size); + FAIL_TEST_IF_FALSE(!ret); + + /* seal the first 3 pages. */ + if (seal) { + ret = sys_mseal(ptr, 3 * page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* unmap all pages. */ + ret = sys_munmap(ptr, size); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_munmap_middle_freed(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + int prot; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* unmap 2 pages in the middle. */ + ret = sys_munmap(ptr + page_size, page_size * 2); + FAIL_TEST_IF_FALSE(!ret); + + /* seal the first page. */ + if (seal) { + ret = sys_mseal(ptr, page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* munmap all 4 pages. */ + ret = sys_munmap(ptr, size); + if (seal) { + FAIL_TEST_IF_FALSE(ret < 0); + + size = get_vma_size(ptr, &prot); + FAIL_TEST_IF_FALSE(size == page_size); + + size = get_vma_size(ptr + page_size * 3, &prot); + FAIL_TEST_IF_FALSE(size == page_size); + } else { + FAIL_TEST_IF_FALSE(!ret); + + size = get_vma_size(ptr, &prot); + FAIL_TEST_IF_FALSE(size == 0); + + size = get_vma_size(ptr + page_size * 3, &prot); + FAIL_TEST_IF_FALSE(size == 0); + } + + TEST_END_CHECK(); +} + +static void test_seal_mremap_shrink(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* shrink from 4 pages to 2 pages. */ + ret2 = mremap(ptr, size, 2 * page_size, 0, 0); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else { + FAIL_TEST_IF_FALSE(ret2 != MAP_FAILED); + + } + + TEST_END_CHECK(); +} + +static void test_seal_mremap_expand(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + /* ummap last 2 pages. */ + ret = sys_munmap(ptr + 2 * page_size, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + if (seal) { + ret = sys_mseal(ptr, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* expand from 2 page to 4 pages. */ + ret2 = mremap(ptr, 2 * page_size, 4 * page_size, 0, 0); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else { + FAIL_TEST_IF_FALSE(ret2 == ptr); + + } + + TEST_END_CHECK(); +} + +static void test_seal_mremap_move(bool seal) +{ + void *ptr, *newPtr; + unsigned long page_size = getpagesize(); + unsigned long size = page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + setup_single_address(size, &newPtr); + FAIL_TEST_IF_FALSE(newPtr != (void *)-1); + ret = clean_single_address(newPtr, size); + FAIL_TEST_IF_FALSE(!ret); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* move from ptr to fixed address. */ + ret2 = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_FIXED, newPtr); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else { + FAIL_TEST_IF_FALSE(ret2 != MAP_FAILED); + + } + + TEST_END_CHECK(); +} + +static void test_seal_mmap_overwrite_prot(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* use mmap to change protection. */ + ret2 = sys_mmap(ptr, size, PROT_NONE, + MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else + FAIL_TEST_IF_FALSE(ret2 == ptr); + + TEST_END_CHECK(); +} + +static void test_seal_mmap_expand(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 12 * page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + /* ummap last 4 pages. */ + ret = sys_munmap(ptr + 8 * page_size, 4 * page_size); + FAIL_TEST_IF_FALSE(!ret); + + if (seal) { + ret = sys_mseal(ptr, 8 * page_size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* use mmap to expand. */ + ret2 = sys_mmap(ptr, size, PROT_READ, + MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else + FAIL_TEST_IF_FALSE(ret2 == ptr); + + TEST_END_CHECK(); +} + +static void test_seal_mmap_shrink(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 12 * page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* use mmap to shrink. */ + ret2 = sys_mmap(ptr, 8 * page_size, PROT_READ, + MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else + FAIL_TEST_IF_FALSE(ret2 == ptr); + + TEST_END_CHECK(); +} + +static void test_seal_mremap_shrink_fixed(bool seal) +{ + void *ptr; + void *newAddr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + setup_single_address(size, &newAddr); + FAIL_TEST_IF_FALSE(newAddr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* mremap to move and shrink to fixed address */ + ret2 = mremap(ptr, size, 2 * page_size, MREMAP_MAYMOVE | MREMAP_FIXED, + newAddr); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else + FAIL_TEST_IF_FALSE(ret2 == newAddr); + + TEST_END_CHECK(); +} + +static void test_seal_mremap_expand_fixed(bool seal) +{ + void *ptr; + void *newAddr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + void *ret2; + + setup_single_address(page_size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + setup_single_address(size, &newAddr); + FAIL_TEST_IF_FALSE(newAddr != (void *)-1); + + if (seal) { + ret = sys_mseal(newAddr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* mremap to move and expand to fixed address */ + ret2 = mremap(ptr, page_size, size, MREMAP_MAYMOVE | MREMAP_FIXED, + newAddr); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else + FAIL_TEST_IF_FALSE(ret2 == newAddr); + + TEST_END_CHECK(); +} + +static void test_seal_mremap_move_fixed(bool seal) +{ + void *ptr; + void *newAddr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + setup_single_address(size, &newAddr); + FAIL_TEST_IF_FALSE(newAddr != (void *)-1); + + if (seal) { + ret = sys_mseal(newAddr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* mremap to move to fixed address */ + ret2 = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_FIXED, newAddr); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else + FAIL_TEST_IF_FALSE(ret2 == newAddr); + + TEST_END_CHECK(); +} + +static void test_seal_mremap_move_fixed_zero(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* + * MREMAP_FIXED can move the mapping to zero address + */ + ret2 = mremap(ptr, size, 2 * page_size, MREMAP_MAYMOVE | MREMAP_FIXED, + 0); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else { + FAIL_TEST_IF_FALSE(ret2 == 0); + + } + + TEST_END_CHECK(); +} + +static void test_seal_mremap_move_dontunmap(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* mremap to move, and don't unmap src addr. */ + ret2 = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_DONTUNMAP, 0); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else { + FAIL_TEST_IF_FALSE(ret2 != MAP_FAILED); + + } + + TEST_END_CHECK(); +} + +static void test_seal_mremap_move_dontunmap_anyaddr(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + void *ret2; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* + * The 0xdeaddead should not have effect on dest addr + * when MREMAP_DONTUNMAP is set. + */ + ret2 = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_DONTUNMAP, + 0xdeaddead); + if (seal) { + FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(errno == EPERM); + } else { + FAIL_TEST_IF_FALSE(ret2 != MAP_FAILED); + FAIL_TEST_IF_FALSE((long)ret2 != 0xdeaddead); + + } + + TEST_END_CHECK(); +} + + +static void test_seal_merge_and_split(void) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size; + int ret; + int prot; + + /* (24 RO) */ + setup_single_address(24 * page_size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + /* use mprotect(NONE) to set out boundary */ + /* (1 NONE) (22 RO) (1 NONE) */ + ret = sys_mprotect(ptr, page_size, PROT_NONE); + FAIL_TEST_IF_FALSE(!ret); + ret = sys_mprotect(ptr + 23 * page_size, page_size, PROT_NONE); + FAIL_TEST_IF_FALSE(!ret); + size = get_vma_size(ptr + page_size, &prot); + FAIL_TEST_IF_FALSE(size == 22 * page_size); + FAIL_TEST_IF_FALSE(prot == 4); + + /* use mseal to split from beginning */ + /* (1 NONE) (1 RO_SEAL) (21 RO) (1 NONE) */ + ret = sys_mseal(ptr + page_size, page_size); + FAIL_TEST_IF_FALSE(!ret); + size = get_vma_size(ptr + page_size, &prot); + FAIL_TEST_IF_FALSE(size == page_size); + FAIL_TEST_IF_FALSE(prot == 0x4); + size = get_vma_size(ptr + 2 * page_size, &prot); + FAIL_TEST_IF_FALSE(size == 21 * page_size); + FAIL_TEST_IF_FALSE(prot == 0x4); + + /* use mseal to split from the end. */ + /* (1 NONE) (1 RO_SEAL) (20 RO) (1 RO_SEAL) (1 NONE) */ + ret = sys_mseal(ptr + 22 * page_size, page_size); + FAIL_TEST_IF_FALSE(!ret); + size = get_vma_size(ptr + 22 * page_size, &prot); + FAIL_TEST_IF_FALSE(size == page_size); + FAIL_TEST_IF_FALSE(prot == 0x4); + size = get_vma_size(ptr + 2 * page_size, &prot); + FAIL_TEST_IF_FALSE(size == 20 * page_size); + FAIL_TEST_IF_FALSE(prot == 0x4); + + /* merge with prev. */ + /* (1 NONE) (2 RO_SEAL) (19 RO) (1 RO_SEAL) (1 NONE) */ + ret = sys_mseal(ptr + 2 * page_size, page_size); + FAIL_TEST_IF_FALSE(!ret); + size = get_vma_size(ptr + page_size, &prot); + FAIL_TEST_IF_FALSE(size == 2 * page_size); + FAIL_TEST_IF_FALSE(prot == 0x4); + + /* merge with after. */ + /* (1 NONE) (2 RO_SEAL) (18 RO) (2 RO_SEALS) (1 NONE) */ + ret = sys_mseal(ptr + 21 * page_size, page_size); + FAIL_TEST_IF_FALSE(!ret); + size = get_vma_size(ptr + 21 * page_size, &prot); + FAIL_TEST_IF_FALSE(size == 2 * page_size); + FAIL_TEST_IF_FALSE(prot == 0x4); + + /* split and merge from prev */ + /* (1 NONE) (3 RO_SEAL) (17 RO) (2 RO_SEALS) (1 NONE) */ + ret = sys_mseal(ptr + 2 * page_size, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + size = get_vma_size(ptr + 1 * page_size, &prot); + FAIL_TEST_IF_FALSE(size == 3 * page_size); + FAIL_TEST_IF_FALSE(prot == 0x4); + ret = sys_munmap(ptr + page_size, page_size); + FAIL_TEST_IF_FALSE(ret < 0); + ret = sys_mprotect(ptr + 2 * page_size, page_size, PROT_NONE); + FAIL_TEST_IF_FALSE(ret < 0); + + /* split and merge from next */ + /* (1 NONE) (3 RO_SEAL) (16 RO) (3 RO_SEALS) (1 NONE) */ + ret = sys_mseal(ptr + 20 * page_size, 2 * page_size); + FAIL_TEST_IF_FALSE(!ret); + FAIL_TEST_IF_FALSE(prot == 0x4); + size = get_vma_size(ptr + 20 * page_size, &prot); + FAIL_TEST_IF_FALSE(size == 3 * page_size); + FAIL_TEST_IF_FALSE(prot == 0x4); + + /* merge from middle of prev and middle of next. */ + /* (1 NONE) (22 RO_SEAL) (1 NONE) */ + ret = sys_mseal(ptr + 2 * page_size, 20 * page_size); + FAIL_TEST_IF_FALSE(!ret); + size = get_vma_size(ptr + page_size, &prot); + FAIL_TEST_IF_FALSE(size == 22 * page_size); + FAIL_TEST_IF_FALSE(prot == 0x4); + + TEST_END_CHECK(); +} + +static void test_seal_discard_ro_anon_on_rw(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address_rw(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* sealing doesn't take effect on RW memory. */ + ret = sys_madvise(ptr, size, MADV_DONTNEED); + FAIL_TEST_IF_FALSE(!ret); + + /* base seal still apply. */ + ret = sys_munmap(ptr, size); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_discard_ro_anon_on_pkey(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + int pkey; + + SKIP_TEST_IF_FALSE(pkey_supported()); + + setup_single_address_rw(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + pkey = sys_pkey_alloc(0, 0); + FAIL_TEST_IF_FALSE(pkey > 0); + + ret = sys_mprotect_pkey((void *)ptr, size, PROT_READ | PROT_WRITE, pkey); + FAIL_TEST_IF_FALSE(!ret); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* sealing doesn't take effect if PKRU allow write. */ + set_pkey(pkey, 0); + ret = sys_madvise(ptr, size, MADV_DONTNEED); + FAIL_TEST_IF_FALSE(!ret); + + /* sealing will take effect if PKRU deny write. */ + set_pkey(pkey, PKEY_DISABLE_WRITE); + ret = sys_madvise(ptr, size, MADV_DONTNEED); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + /* base seal still apply. */ + ret = sys_munmap(ptr, size); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_discard_ro_anon_on_filebacked(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + int fd; + unsigned long mapflags = MAP_PRIVATE; + + fd = memfd_create("test", 0); + FAIL_TEST_IF_FALSE(fd > 0); + + ret = fallocate(fd, 0, 0, size); + FAIL_TEST_IF_FALSE(!ret); + + ptr = sys_mmap(NULL, size, PROT_READ, mapflags, fd, 0); + FAIL_TEST_IF_FALSE(ptr != MAP_FAILED); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* sealing doesn't apply for file backed mapping. */ + ret = sys_madvise(ptr, size, MADV_DONTNEED); + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_munmap(ptr, size); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + close(fd); + + TEST_END_CHECK(); +} + +static void test_seal_discard_ro_anon_on_shared(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + unsigned long mapflags = MAP_ANONYMOUS | MAP_SHARED; + + ptr = sys_mmap(NULL, size, PROT_READ, mapflags, -1, 0); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = sys_mseal(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + /* sealing doesn't apply for shared mapping. */ + ret = sys_madvise(ptr, size, MADV_DONTNEED); + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_munmap(ptr, size); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +static void test_seal_discard_ro_anon(bool seal) +{ + void *ptr; + unsigned long page_size = getpagesize(); + unsigned long size = 4 * page_size; + int ret; + + setup_single_address(size, &ptr); + FAIL_TEST_IF_FALSE(ptr != (void *)-1); + + if (seal) { + ret = seal_single_address(ptr, size); + FAIL_TEST_IF_FALSE(!ret); + } + + ret = sys_madvise(ptr, size, MADV_DONTNEED); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + ret = sys_munmap(ptr, size); + if (seal) + FAIL_TEST_IF_FALSE(ret < 0); + else + FAIL_TEST_IF_FALSE(!ret); + + TEST_END_CHECK(); +} + +int main(int argc, char **argv) +{ + bool test_seal = seal_support(); + + ksft_print_header(); + + if (!test_seal) + ksft_exit_skip("sealing not supported, check CONFIG_64BIT\n"); + + if (!pkey_supported()) + ksft_print_msg("PKEY not supported\n"); + + ksft_set_plan(80); + + test_seal_addseal(); + test_seal_unmapped_start(); + test_seal_unmapped_middle(); + test_seal_unmapped_end(); + test_seal_multiple_vmas(); + test_seal_split_start(); + test_seal_split_end(); + test_seal_invalid_input(); + test_seal_zero_length(); + test_seal_twice(); + + test_seal_mprotect(false); + test_seal_mprotect(true); + + test_seal_start_mprotect(false); + test_seal_start_mprotect(true); + + test_seal_end_mprotect(false); + test_seal_end_mprotect(true); + + test_seal_mprotect_unalign_len(false); + test_seal_mprotect_unalign_len(true); + + test_seal_mprotect_unalign_len_variant_2(false); + test_seal_mprotect_unalign_len_variant_2(true); + + test_seal_mprotect_two_vma(false); + test_seal_mprotect_two_vma(true); + + test_seal_mprotect_two_vma_with_split(false); + test_seal_mprotect_two_vma_with_split(true); + + test_seal_mprotect_partial_mprotect(false); + test_seal_mprotect_partial_mprotect(true); + + test_seal_mprotect_two_vma_with_gap(false); + test_seal_mprotect_two_vma_with_gap(true); + + test_seal_mprotect_merge(false); + test_seal_mprotect_merge(true); + + test_seal_mprotect_split(false); + test_seal_mprotect_split(true); + + test_seal_munmap(false); + test_seal_munmap(true); + test_seal_munmap_two_vma(false); + test_seal_munmap_two_vma(true); + test_seal_munmap_vma_with_gap(false); + test_seal_munmap_vma_with_gap(true); + + test_munmap_start_freed(false); + test_munmap_start_freed(true); + test_munmap_middle_freed(false); + test_munmap_middle_freed(true); + test_munmap_end_freed(false); + test_munmap_end_freed(true); + + test_seal_mremap_shrink(false); + test_seal_mremap_shrink(true); + test_seal_mremap_expand(false); + test_seal_mremap_expand(true); + test_seal_mremap_move(false); + test_seal_mremap_move(true); + + test_seal_mremap_shrink_fixed(false); + test_seal_mremap_shrink_fixed(true); + test_seal_mremap_expand_fixed(false); + test_seal_mremap_expand_fixed(true); + test_seal_mremap_move_fixed(false); + test_seal_mremap_move_fixed(true); + test_seal_mremap_move_dontunmap(false); + test_seal_mremap_move_dontunmap(true); + test_seal_mremap_move_fixed_zero(false); + test_seal_mremap_move_fixed_zero(true); + test_seal_mremap_move_dontunmap_anyaddr(false); + test_seal_mremap_move_dontunmap_anyaddr(true); + test_seal_discard_ro_anon(false); + test_seal_discard_ro_anon(true); + test_seal_discard_ro_anon_on_rw(false); + test_seal_discard_ro_anon_on_rw(true); + test_seal_discard_ro_anon_on_shared(false); + test_seal_discard_ro_anon_on_shared(true); + test_seal_discard_ro_anon_on_filebacked(false); + test_seal_discard_ro_anon_on_filebacked(true); + test_seal_mmap_overwrite_prot(false); + test_seal_mmap_overwrite_prot(true); + test_seal_mmap_expand(false); + test_seal_mmap_expand(true); + test_seal_mmap_shrink(false); + test_seal_mmap_shrink(true); + + test_seal_merge_and_split(); + test_seal_zero_address(); + + test_seal_discard_ro_anon_on_pkey(false); + test_seal_discard_ro_anon_on_pkey(true); + + ksft_finished(); +} diff --git a/tools/testing/selftests/mm/seal_elf.c b/tools/testing/selftests/mm/seal_elf.c new file mode 100644 index 000000000000..f2babec79bb6 --- /dev/null +++ b/tools/testing/selftests/mm/seal_elf.c @@ -0,0 +1,179 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#include <sys/mman.h> +#include <stdint.h> +#include <unistd.h> +#include <string.h> +#include <sys/time.h> +#include <sys/resource.h> +#include <stdbool.h> +#include "../kselftest.h" +#include <syscall.h> +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <fcntl.h> +#include <sys/ioctl.h> +#include <sys/vfs.h> +#include <sys/stat.h> + +/* + * need those definition for manually build using gcc. + * gcc -I ../../../../usr/include -DDEBUG -O3 -DDEBUG -O3 seal_elf.c -o seal_elf + */ +#define FAIL_TEST_IF_FALSE(c) do {\ + if (!(c)) {\ + ksft_test_result_fail("%s, line:%d\n", __func__, __LINE__);\ + goto test_end;\ + } \ + } \ + while (0) + +#define SKIP_TEST_IF_FALSE(c) do {\ + if (!(c)) {\ + ksft_test_result_skip("%s, line:%d\n", __func__, __LINE__);\ + goto test_end;\ + } \ + } \ + while (0) + + +#define TEST_END_CHECK() {\ + ksft_test_result_pass("%s\n", __func__);\ + return;\ +test_end:\ + return;\ +} + +#ifndef u64 +#define u64 unsigned long long +#endif + +/* + * define sys_xyx to call syscall directly. + */ +static int sys_mseal(void *start, size_t len) +{ + int sret; + + errno = 0; + sret = syscall(__NR_mseal, start, len, 0); + return sret; +} + +static void *sys_mmap(void *addr, unsigned long len, unsigned long prot, + unsigned long flags, unsigned long fd, unsigned long offset) +{ + void *sret; + + errno = 0; + sret = (void *) syscall(__NR_mmap, addr, len, prot, + flags, fd, offset); + return sret; +} + +static inline int sys_mprotect(void *ptr, size_t size, unsigned long prot) +{ + int sret; + + errno = 0; + sret = syscall(__NR_mprotect, ptr, size, prot); + return sret; +} + +static bool seal_support(void) +{ + int ret; + void *ptr; + unsigned long page_size = getpagesize(); + + ptr = sys_mmap(NULL, page_size, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + if (ptr == (void *) -1) + return false; + + ret = sys_mseal(ptr, page_size); + if (ret < 0) + return false; + + return true; +} + +const char somestr[4096] = {"READONLY"}; + +static void test_seal_elf(void) +{ + int ret; + FILE *maps; + char line[512]; + uintptr_t addr_start, addr_end; + char prot[5]; + char filename[256]; + unsigned long page_size = getpagesize(); + unsigned long long ptr = (unsigned long long) somestr; + char *somestr2 = (char *)somestr; + + /* + * Modify the protection of readonly somestr + */ + if (((unsigned long long)ptr % page_size) != 0) + ptr = (unsigned long long)ptr & ~(page_size - 1); + + ksft_print_msg("somestr = %s\n", somestr); + ksft_print_msg("change protection to rw\n"); + ret = sys_mprotect((void *)ptr, page_size, PROT_READ|PROT_WRITE); + FAIL_TEST_IF_FALSE(!ret); + *somestr2 = 'A'; + ksft_print_msg("somestr is modified to: %s\n", somestr); + ret = sys_mprotect((void *)ptr, page_size, PROT_READ); + FAIL_TEST_IF_FALSE(!ret); + + maps = fopen("/proc/self/maps", "r"); + FAIL_TEST_IF_FALSE(maps); + + /* + * apply sealing to elf binary + */ + while (fgets(line, sizeof(line), maps)) { + if (sscanf(line, "%lx-%lx %4s %*x %*x:%*x %*u %255[^\n]", + &addr_start, &addr_end, prot, filename) == 4) { + if (strlen(filename)) { + /* + * seal the mapping if read only. + */ + if (strstr(prot, "r-")) { + ret = sys_mseal((void *)addr_start, addr_end - addr_start); + FAIL_TEST_IF_FALSE(!ret); + ksft_print_msg("sealed: %lx-%lx %s %s\n", + addr_start, addr_end, prot, filename); + if ((uintptr_t) somestr >= addr_start && + (uintptr_t) somestr <= addr_end) + ksft_print_msg("mapping for somestr found\n"); + } + } + } + } + fclose(maps); + + ret = sys_mprotect((void *)ptr, page_size, PROT_READ | PROT_WRITE); + FAIL_TEST_IF_FALSE(ret < 0); + ksft_print_msg("somestr is sealed, mprotect is rejected\n"); + + TEST_END_CHECK(); +} + +int main(int argc, char **argv) +{ + bool test_seal = seal_support(); + + ksft_print_header(); + ksft_print_msg("pid=%d\n", getpid()); + + if (!test_seal) + ksft_exit_skip("sealing not supported, check CONFIG_64BIT\n"); + + ksft_set_plan(1); + + test_seal_elf(); + + ksft_finished(); +} diff --git a/tools/testing/selftests/mm/uffd-common.h b/tools/testing/selftests/mm/uffd-common.h index cc5629c3d2aa..a70ae10b5f62 100644 --- a/tools/testing/selftests/mm/uffd-common.h +++ b/tools/testing/selftests/mm/uffd-common.h @@ -8,6 +8,7 @@ #define __UFFD_COMMON_H__ #define _GNU_SOURCE +#define __SANE_USERSPACE_TYPES__ // Use ll64 #include <stdio.h> #include <errno.h> #include <unistd.h> diff --git a/tools/testing/selftests/net/af_unix/scm_rights.c b/tools/testing/selftests/net/af_unix/scm_rights.c index bab606c9f1eb..2bfed46e0b19 100644 --- a/tools/testing/selftests/net/af_unix/scm_rights.c +++ b/tools/testing/selftests/net/af_unix/scm_rights.c @@ -197,8 +197,8 @@ void __send_fd(struct __test_metadata *_metadata, const FIXTURE_VARIANT(scm_rights) *variant, int inflight, int receiver) { -#define MSG "nop" -#define MSGLEN 3 +#define MSG "x" +#define MSGLEN 1 struct { struct cmsghdr cmsghdr; int fd[2]; diff --git a/tools/testing/selftests/net/amt.sh b/tools/testing/selftests/net/amt.sh index 5175a42cbe8a..7e7ed6c558da 100755 --- a/tools/testing/selftests/net/amt.sh +++ b/tools/testing/selftests/net/amt.sh @@ -77,6 +77,7 @@ readonly LISTENER=$(mktemp -u listener-XXXXXXXX) readonly GATEWAY=$(mktemp -u gateway-XXXXXXXX) readonly RELAY=$(mktemp -u relay-XXXXXXXX) readonly SOURCE=$(mktemp -u source-XXXXXXXX) +readonly SMCROUTEDIR="$(mktemp -d)" ERR=4 err=0 @@ -85,6 +86,11 @@ exit_cleanup() for ns in "$@"; do ip netns delete "${ns}" 2>/dev/null || true done + if [ -f "$SMCROUTEDIR/amt.pid" ]; then + smcpid=$(< $SMCROUTEDIR/amt.pid) + kill $smcpid + fi + rm -rf $SMCROUTEDIR exit $ERR } @@ -167,7 +173,7 @@ setup_iptables() setup_mcast_routing() { - ip netns exec "${RELAY}" smcrouted + ip netns exec "${RELAY}" smcrouted -P $SMCROUTEDIR/amt.pid ip netns exec "${RELAY}" smcroutectl a relay_src \ 172.17.0.2 239.0.0.1 amtr ip netns exec "${RELAY}" smcroutectl a relay_src \ diff --git a/tools/testing/selftests/net/arp_ndisc_untracked_subnets.sh b/tools/testing/selftests/net/arp_ndisc_untracked_subnets.sh index a40c0e9bd023..eef5cbf6eecc 100755 --- a/tools/testing/selftests/net/arp_ndisc_untracked_subnets.sh +++ b/tools/testing/selftests/net/arp_ndisc_untracked_subnets.sh @@ -73,25 +73,19 @@ setup_v6() { # namespaces. veth0 is veth-router, veth1 is veth-host. # first, set up the inteface's link to the namespace # then, set the interface "up" - ip -6 -netns ${ROUTER_NS_V6} link add name ${ROUTER_INTF} \ - type veth peer name ${HOST_INTF} - - ip -6 -netns ${ROUTER_NS_V6} link set dev ${ROUTER_INTF} up - ip -6 -netns ${ROUTER_NS_V6} link set dev ${HOST_INTF} netns \ - ${HOST_NS_V6} + ip -n ${ROUTER_NS_V6} link add name ${ROUTER_INTF} \ + type veth peer name ${HOST_INTF} netns ${HOST_NS_V6} - ip -6 -netns ${HOST_NS_V6} link set dev ${HOST_INTF} up - ip -6 -netns ${ROUTER_NS_V6} addr add \ - ${ROUTER_ADDR_V6}/${PREFIX_WIDTH_V6} dev ${ROUTER_INTF} nodad + # Add tc rule to filter out host na message + tc -n ${ROUTER_NS_V6} qdisc add dev ${ROUTER_INTF} clsact + tc -n ${ROUTER_NS_V6} filter add dev ${ROUTER_INTF} \ + ingress protocol ipv6 pref 1 handle 101 \ + flower src_ip ${HOST_ADDR_V6} ip_proto icmpv6 type 136 skip_hw action pass HOST_CONF=net.ipv6.conf.${HOST_INTF} ip netns exec ${HOST_NS_V6} sysctl -qw ${HOST_CONF}.ndisc_notify=1 ip netns exec ${HOST_NS_V6} sysctl -qw ${HOST_CONF}.disable_ipv6=0 - ip -6 -netns ${HOST_NS_V6} addr add ${HOST_ADDR_V6}/${PREFIX_WIDTH_V6} \ - dev ${HOST_INTF} - ROUTER_CONF=net.ipv6.conf.${ROUTER_INTF} - ip netns exec ${ROUTER_NS_V6} sysctl -w \ ${ROUTER_CONF}.forwarding=1 >/dev/null 2>&1 ip netns exec ${ROUTER_NS_V6} sysctl -w \ @@ -99,6 +93,13 @@ setup_v6() { ip netns exec ${ROUTER_NS_V6} sysctl -w \ ${ROUTER_CONF}.accept_untracked_na=${accept_untracked_na} \ >/dev/null 2>&1 + + ip -n ${ROUTER_NS_V6} link set dev ${ROUTER_INTF} up + ip -n ${HOST_NS_V6} link set dev ${HOST_INTF} up + ip -n ${ROUTER_NS_V6} addr add ${ROUTER_ADDR_V6}/${PREFIX_WIDTH_V6} \ + dev ${ROUTER_INTF} nodad + ip -n ${HOST_NS_V6} addr add ${HOST_ADDR_V6}/${PREFIX_WIDTH_V6} \ + dev ${HOST_INTF} set +e } @@ -162,26 +163,6 @@ arp_test_gratuitous_combinations() { arp_test_gratuitous 2 1 } -cleanup_tcpdump() { - set -e - [[ ! -z ${tcpdump_stdout} ]] && rm -f ${tcpdump_stdout} - [[ ! -z ${tcpdump_stderr} ]] && rm -f ${tcpdump_stderr} - tcpdump_stdout= - tcpdump_stderr= - set +e -} - -start_tcpdump() { - set -e - tcpdump_stdout=`mktemp` - tcpdump_stderr=`mktemp` - ip netns exec ${ROUTER_NS_V6} timeout 15s \ - tcpdump --immediate-mode -tpni ${ROUTER_INTF} -c 1 \ - "icmp6 && icmp6[0] == 136 && src ${HOST_ADDR_V6}" \ - > ${tcpdump_stdout} 2> /dev/null - set +e -} - verify_ndisc() { local accept_untracked_na=$1 local same_subnet=$2 @@ -222,8 +203,9 @@ ndisc_test_untracked_advertisements() { HOST_ADDR_V6=2001:db8:abcd:0012::3 fi fi - setup_v6 $1 $2 - start_tcpdump + setup_v6 $1 + slowwait_for_counter 15 1 \ + tc_rule_handle_stats_get "dev ${ROUTER_INTF} ingress" 101 ".packets" "-n ${ROUTER_NS_V6}" if verify_ndisc $1 $2; then printf " TEST: %-60s [ OK ]\n" "${test_msg[*]}" @@ -231,7 +213,6 @@ ndisc_test_untracked_advertisements() { printf " TEST: %-60s [FAIL]\n" "${test_msg[*]}" fi - cleanup_tcpdump cleanup_v6 set +e } diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 112c85c35092..eabbdf00d8ca 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -129,14 +129,6 @@ fi source "$net_forwarding_dir/../lib.sh" -# timeout in seconds -slowwait() -{ - local timeout_sec=$1; shift - - loopy_wait "sleep 0.1" "$((timeout_sec * 1000))" "$@" -} - ############################################################################## # Sanity checks @@ -678,33 +670,6 @@ wait_for_trap() "$@" | grep -q trap } -until_counter_is() -{ - local expr=$1; shift - local current=$("$@") - - echo $((current)) - ((current $expr)) -} - -busywait_for_counter() -{ - local timeout=$1; shift - local delta=$1; shift - - local base=$("$@") - busywait "$timeout" until_counter_is ">= $((base + delta))" "$@" -} - -slowwait_for_counter() -{ - local timeout=$1; shift - local delta=$1; shift - - local base=$("$@") - slowwait "$timeout" until_counter_is ">= $((base + delta))" "$@" -} - setup_wait_dev() { local dev=$1; shift @@ -1023,29 +988,6 @@ link_stats_rx_errors_get() link_stats_get $1 rx errors } -tc_rule_stats_get() -{ - local dev=$1; shift - local pref=$1; shift - local dir=$1; shift - local selector=${1:-.packets}; shift - - tc -j -s filter show dev $dev ${dir:-ingress} pref $pref \ - | jq ".[1].options.actions[].stats$selector" -} - -tc_rule_handle_stats_get() -{ - local id=$1; shift - local handle=$1; shift - local selector=${1:-.packets}; shift - local netns=${1:-""}; shift - - tc $netns -j -s filter show $id \ - | jq ".[] | select(.options.handle == $handle) | \ - .options.actions[0].stats$selector" -} - ethtool_stats_get() { local dev=$1; shift diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 72b191e4e064..edc030e81a46 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -91,6 +91,41 @@ busywait() loopy_wait : "$timeout_ms" "$@" } +# timeout in seconds +slowwait() +{ + local timeout_sec=$1; shift + + loopy_wait "sleep 0.1" "$((timeout_sec * 1000))" "$@" +} + +until_counter_is() +{ + local expr=$1; shift + local current=$("$@") + + echo $((current)) + ((current $expr)) +} + +busywait_for_counter() +{ + local timeout=$1; shift + local delta=$1; shift + + local base=$("$@") + busywait "$timeout" until_counter_is ">= $((base + delta))" "$@" +} + +slowwait_for_counter() +{ + local timeout=$1; shift + local delta=$1; shift + + local base=$("$@") + slowwait "$timeout" until_counter_is ">= $((base + delta))" "$@" +} + cleanup_ns() { local ns="" @@ -150,3 +185,26 @@ setup_ns() done NS_LIST="$NS_LIST $ns_list" } + +tc_rule_stats_get() +{ + local dev=$1; shift + local pref=$1; shift + local dir=$1; shift + local selector=${1:-.packets}; shift + + tc -j -s filter show dev $dev ${dir:-ingress} pref $pref \ + | jq ".[1].options.actions[].stats$selector" +} + +tc_rule_handle_stats_get() +{ + local id=$1; shift + local handle=$1; shift + local selector=${1:-.packets}; shift + local netns=${1:-""}; shift + + tc $netns -j -s filter show $id \ + | jq ".[] | select(.options.handle == $handle) | \ + .options.actions[0].stats$selector" +} diff --git a/tools/testing/selftests/riscv/Makefile b/tools/testing/selftests/riscv/Makefile index 4a9ff515a3a0..7ce03d832b64 100644 --- a/tools/testing/selftests/riscv/Makefile +++ b/tools/testing/selftests/riscv/Makefile @@ -5,7 +5,7 @@ ARCH ?= $(shell uname -m 2>/dev/null || echo not) ifneq (,$(filter $(ARCH),riscv)) -RISCV_SUBTARGETS ?= hwprobe vector mm +RISCV_SUBTARGETS ?= hwprobe vector mm sigreturn else RISCV_SUBTARGETS := endif diff --git a/tools/testing/selftests/riscv/hwprobe/.gitignore b/tools/testing/selftests/riscv/hwprobe/.gitignore index 8113dc3bdd03..6e384e80ea1a 100644 --- a/tools/testing/selftests/riscv/hwprobe/.gitignore +++ b/tools/testing/selftests/riscv/hwprobe/.gitignore @@ -1 +1,3 @@ hwprobe +cbo +which-cpus diff --git a/tools/testing/selftests/riscv/sigreturn/.gitignore b/tools/testing/selftests/riscv/sigreturn/.gitignore new file mode 100644 index 000000000000..35002b8ae780 --- /dev/null +++ b/tools/testing/selftests/riscv/sigreturn/.gitignore @@ -0,0 +1 @@ +sigreturn diff --git a/tools/testing/selftests/riscv/sigreturn/Makefile b/tools/testing/selftests/riscv/sigreturn/Makefile new file mode 100644 index 000000000000..eb8bac9279a8 --- /dev/null +++ b/tools/testing/selftests/riscv/sigreturn/Makefile @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: GPL-2.0 +# Copyright (C) 2021 ARM Limited +# Originally tools/testing/arm64/abi/Makefile + +CFLAGS += -I$(top_srcdir)/tools/include + +TEST_GEN_PROGS := sigreturn + +include ../../lib.mk + +$(OUTPUT)/sigreturn: sigreturn.c + $(CC) -static -o$@ $(CFLAGS) $(LDFLAGS) $^ diff --git a/tools/testing/selftests/riscv/sigreturn/sigreturn.c b/tools/testing/selftests/riscv/sigreturn/sigreturn.c new file mode 100644 index 000000000000..62397d5934f1 --- /dev/null +++ b/tools/testing/selftests/riscv/sigreturn/sigreturn.c @@ -0,0 +1,82 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <ucontext.h> +#include <linux/ptrace.h> +#include "../../kselftest_harness.h" + +#define RISCV_V_MAGIC 0x53465457 +#define DEFAULT_VALUE 2 +#define SIGNAL_HANDLER_OVERRIDE 3 + +static void simple_handle(int sig_no, siginfo_t *info, void *vcontext) +{ + ucontext_t *context = vcontext; + + context->uc_mcontext.__gregs[REG_PC] = context->uc_mcontext.__gregs[REG_PC] + 4; +} + +static void vector_override(int sig_no, siginfo_t *info, void *vcontext) +{ + ucontext_t *context = vcontext; + + // vector state + struct __riscv_extra_ext_header *ext; + struct __riscv_v_ext_state *v_ext_state; + + /* Find the vector context. */ + ext = (void *)(&context->uc_mcontext.__fpregs); + if (ext->hdr.magic != RISCV_V_MAGIC) { + fprintf(stderr, "bad vector magic: %x\n", ext->hdr.magic); + abort(); + } + + v_ext_state = (void *)((char *)(ext) + sizeof(*ext)); + + *(int *)v_ext_state->datap = SIGNAL_HANDLER_OVERRIDE; + + context->uc_mcontext.__gregs[REG_PC] = context->uc_mcontext.__gregs[REG_PC] + 4; +} + +static int vector_sigreturn(int data, void (*handler)(int, siginfo_t *, void *)) +{ + int after_sigreturn; + struct sigaction sig_action = { + .sa_sigaction = handler, + .sa_flags = SA_SIGINFO + }; + + sigaction(SIGSEGV, &sig_action, 0); + + asm(".option push \n\ + .option arch, +v \n\ + vsetivli x0, 1, e32, ta, ma \n\ + vmv.s.x v0, %1 \n\ + # Generate SIGSEGV \n\ + lw a0, 0(x0) \n\ + vmv.x.s %0, v0 \n\ + .option pop" : "=r" (after_sigreturn) : "r" (data)); + + return after_sigreturn; +} + +TEST(vector_restore) +{ + int result; + + result = vector_sigreturn(DEFAULT_VALUE, &simple_handle); + + EXPECT_EQ(DEFAULT_VALUE, result); +} + +TEST(vector_restore_signal_handler_override) +{ + int result; + + result = vector_sigreturn(DEFAULT_VALUE, &vector_override); + + EXPECT_EQ(SIGNAL_HANDLER_OVERRIDE, result); +} + +TEST_HARNESS_MAIN diff --git a/tools/tracing/latency/latency-collector.c b/tools/tracing/latency/latency-collector.c index 0fd9c747d396..cf263fe9deaf 100644 --- a/tools/tracing/latency/latency-collector.c +++ b/tools/tracing/latency/latency-collector.c @@ -935,12 +935,12 @@ static void show_available(void) } if (!tracers) { - warnx(no_tracer_msg); + warnx("%s", no_tracer_msg); return; } if (!found) { - warnx(no_latency_tr_msg); + warnx("%s", no_latency_tr_msg); tracefs_list_free(tracers); return; } @@ -983,7 +983,7 @@ static const char *find_default_tracer(void) for (i = 0; relevant_tracers[i]; i++) { valid = tracer_valid(relevant_tracers[i], ¬racer); if (notracer) - errx(EXIT_FAILURE, no_tracer_msg); + errx(EXIT_FAILURE, "%s", no_tracer_msg); if (valid) return relevant_tracers[i]; } @@ -1878,7 +1878,7 @@ static void scan_arguments(int argc, char *argv[]) } valid = tracer_valid(current_tracer, ¬racer); if (notracer) - errx(EXIT_FAILURE, no_tracer_msg); + errx(EXIT_FAILURE, "%s", no_tracer_msg); if (!valid) errx(EXIT_FAILURE, "The tracer %s is not supported by your kernel!\n", current_tracer); |