aboutsummaryrefslogtreecommitdiffstats
path: root/tools
diff options
context:
space:
mode:
Diffstat (limited to 'tools')
-rw-r--r--tools/bpf/bpf_jit_disasm.c7
-rw-r--r--tools/bpf/bpftool/Makefile2
-rw-r--r--tools/bpf/bpftool/common.c72
-rw-r--r--tools/bpf/bpftool/jit_disasm.c16
-rw-r--r--tools/bpf/bpftool/main.h5
-rw-r--r--tools/bpf/bpftool/map.c8
-rw-r--r--tools/bpf/bpftool/prog.c13
-rw-r--r--tools/build/feature/Makefile2
-rw-r--r--tools/include/uapi/linux/bpf.h16
-rw-r--r--tools/lib/bpf/Makefile20
-rw-r--r--tools/lib/bpf/libbpf.c2
-rw-r--r--tools/objtool/Makefile2
-rw-r--r--tools/objtool/check.c69
-rw-r--r--tools/objtool/check.h2
-rw-r--r--tools/objtool/elf.c4
-rw-r--r--tools/testing/selftests/bpf/.gitignore7
-rw-r--r--tools/testing/selftests/bpf/Makefile3
-rw-r--r--tools/testing/selftests/bpf/sample_map_ret0.c34
-rw-r--r--tools/testing/selftests/bpf/test_lpm_map.c122
-rwxr-xr-xtools/testing/selftests/bpf/test_offload.py206
-rw-r--r--tools/testing/selftests/bpf/test_verifier.c329
-rw-r--r--tools/testing/selftests/x86/Makefile2
-rw-r--r--tools/testing/selftests/x86/test_vsyscall.c500
23 files changed, 1378 insertions, 65 deletions
diff --git a/tools/bpf/bpf_jit_disasm.c b/tools/bpf/bpf_jit_disasm.c
index 30044bc4f389..58c2bab4ef6e 100644
--- a/tools/bpf/bpf_jit_disasm.c
+++ b/tools/bpf/bpf_jit_disasm.c
@@ -172,7 +172,8 @@ static uint8_t *get_last_jit_image(char *haystack, size_t hlen,
{
char *ptr, *pptr, *tmp;
off_t off = 0;
- int ret, flen, proglen, pass, ulen = 0;
+ unsigned int proglen;
+ int ret, flen, pass, ulen = 0;
regmatch_t pmatch[1];
unsigned long base;
regex_t regex;
@@ -199,7 +200,7 @@ static uint8_t *get_last_jit_image(char *haystack, size_t hlen,
}
ptr = haystack + off - (pmatch[0].rm_eo - pmatch[0].rm_so);
- ret = sscanf(ptr, "flen=%d proglen=%d pass=%d image=%lx",
+ ret = sscanf(ptr, "flen=%d proglen=%u pass=%d image=%lx",
&flen, &proglen, &pass, &base);
if (ret != 4) {
regfree(&regex);
@@ -239,7 +240,7 @@ static uint8_t *get_last_jit_image(char *haystack, size_t hlen,
}
assert(ulen == proglen);
- printf("%d bytes emitted from JIT compiler (pass:%d, flen:%d)\n",
+ printf("%u bytes emitted from JIT compiler (pass:%d, flen:%d)\n",
proglen, pass, flen);
printf("%lx + <x>:\n", base);
diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index 2237bc43f71c..26901ec87361 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -39,7 +39,7 @@ CC = gcc
CFLAGS += -O2
CFLAGS += -W -Wall -Wextra -Wno-unused-parameter -Wshadow
-CFLAGS += -D__EXPORTED_HEADERS__ -I$(srctree)/tools/include/uapi -I$(srctree)/tools/include -I$(srctree)/tools/lib/bpf -I$(srctree)/kernel/bpf/
+CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ -I$(srctree)/tools/include/uapi -I$(srctree)/tools/include -I$(srctree)/tools/lib/bpf -I$(srctree)/kernel/bpf/
CFLAGS += -DBPFTOOL_VERSION='"$(BPFTOOL_VERSION)"'
LIBS = -lelf -lbfd -lopcodes $(LIBBPF)
diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index 6601c95a9258..0b482c0070e0 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -34,6 +34,7 @@
/* Author: Jakub Kicinski <kubakici@wp.pl> */
#include <errno.h>
+#include <fcntl.h>
#include <fts.h>
#include <libgen.h>
#include <mntent.h>
@@ -433,6 +434,77 @@ ifindex_to_name_ns(__u32 ifindex, __u32 ns_dev, __u32 ns_ino, char *buf)
return if_indextoname(ifindex, buf);
}
+static int read_sysfs_hex_int(char *path)
+{
+ char vendor_id_buf[8];
+ int len;
+ int fd;
+
+ fd = open(path, O_RDONLY);
+ if (fd < 0) {
+ p_err("Can't open %s: %s", path, strerror(errno));
+ return -1;
+ }
+
+ len = read(fd, vendor_id_buf, sizeof(vendor_id_buf));
+ close(fd);
+ if (len < 0) {
+ p_err("Can't read %s: %s", path, strerror(errno));
+ return -1;
+ }
+ if (len >= (int)sizeof(vendor_id_buf)) {
+ p_err("Value in %s too long", path);
+ return -1;
+ }
+
+ vendor_id_buf[len] = 0;
+
+ return strtol(vendor_id_buf, NULL, 0);
+}
+
+static int read_sysfs_netdev_hex_int(char *devname, const char *entry_name)
+{
+ char full_path[64];
+
+ snprintf(full_path, sizeof(full_path), "/sys/class/net/%s/device/%s",
+ devname, entry_name);
+
+ return read_sysfs_hex_int(full_path);
+}
+
+const char *ifindex_to_bfd_name_ns(__u32 ifindex, __u64 ns_dev, __u64 ns_ino)
+{
+ char devname[IF_NAMESIZE];
+ int vendor_id;
+ int device_id;
+
+ if (!ifindex_to_name_ns(ifindex, ns_dev, ns_ino, devname)) {
+ p_err("Can't get net device name for ifindex %d: %s", ifindex,
+ strerror(errno));
+ return NULL;
+ }
+
+ vendor_id = read_sysfs_netdev_hex_int(devname, "vendor");
+ if (vendor_id < 0) {
+ p_err("Can't get device vendor id for %s", devname);
+ return NULL;
+ }
+
+ switch (vendor_id) {
+ case 0x19ee:
+ device_id = read_sysfs_netdev_hex_int(devname, "device");
+ if (device_id != 0x4000 &&
+ device_id != 0x6000 &&
+ device_id != 0x6003)
+ p_info("Unknown NFP device ID, assuming it is NFP-6xxx arch");
+ return "NFP-6xxx";
+ default:
+ p_err("Can't get bfd arch name for device vendor id 0x%04x",
+ vendor_id);
+ return NULL;
+ }
+}
+
void print_dev_plain(__u32 ifindex, __u64 ns_dev, __u64 ns_inode)
{
char name[IF_NAMESIZE];
diff --git a/tools/bpf/bpftool/jit_disasm.c b/tools/bpf/bpftool/jit_disasm.c
index 57d32e8a1391..87439320ef70 100644
--- a/tools/bpf/bpftool/jit_disasm.c
+++ b/tools/bpf/bpftool/jit_disasm.c
@@ -76,7 +76,8 @@ static int fprintf_json(void *out, const char *fmt, ...)
return 0;
}
-void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes)
+void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes,
+ const char *arch)
{
disassembler_ftype disassemble;
struct disassemble_info info;
@@ -100,6 +101,19 @@ void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes)
else
init_disassemble_info(&info, stdout,
(fprintf_ftype) fprintf);
+
+ /* Update architecture info for offload. */
+ if (arch) {
+ const bfd_arch_info_type *inf = bfd_scan_arch(arch);
+
+ if (inf) {
+ bfdf->arch_info = inf;
+ } else {
+ p_err("No libfd support for %s", arch);
+ return;
+ }
+ }
+
info.arch = bfd_get_arch(bfdf);
info.mach = bfd_get_mach(bfdf);
info.buffer = image;
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 65b526fe6e7e..b8e9584d6246 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -121,7 +121,10 @@ int do_cgroup(int argc, char **arg);
int prog_parse_fd(int *argc, char ***argv);
-void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes);
+void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes,
+ const char *arch);
void print_hex_data_json(uint8_t *data, size_t len);
+const char *ifindex_to_bfd_name_ns(__u32 ifindex, __u64 ns_dev, __u64 ns_ino);
+
#endif
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index 8d7db9d6b9cd..f95fa67bb498 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -66,6 +66,7 @@ static const char * const map_type_name[] = {
[BPF_MAP_TYPE_HASH_OF_MAPS] = "hash_of_maps",
[BPF_MAP_TYPE_DEVMAP] = "devmap",
[BPF_MAP_TYPE_SOCKMAP] = "sockmap",
+ [BPF_MAP_TYPE_CPUMAP] = "cpumap",
};
static unsigned int get_possible_cpus(void)
@@ -428,6 +429,9 @@ static int show_map_close_json(int fd, struct bpf_map_info *info)
jsonw_name(json_wtr, "flags");
jsonw_printf(json_wtr, "%#x", info->map_flags);
+
+ print_dev_json(info->ifindex, info->netns_dev, info->netns_ino);
+
jsonw_uint_field(json_wtr, "bytes_key", info->key_size);
jsonw_uint_field(json_wtr, "bytes_value", info->value_size);
jsonw_uint_field(json_wtr, "max_entries", info->max_entries);
@@ -469,7 +473,9 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info)
if (*info->name)
printf("name %s ", info->name);
- printf("flags 0x%x\n", info->map_flags);
+ printf("flags 0x%x", info->map_flags);
+ print_dev_plain(info->ifindex, info->netns_dev, info->netns_ino);
+ printf("\n");
printf("\tkey %uB value %uB max_entries %u",
info->key_size, info->value_size, info->max_entries);
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index c6a28be4665c..e8e2baaf93c2 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -66,6 +66,7 @@ static const char * const prog_type_name[] = {
[BPF_PROG_TYPE_LWT_XMIT] = "lwt_xmit",
[BPF_PROG_TYPE_SOCK_OPS] = "sock_ops",
[BPF_PROG_TYPE_SK_SKB] = "sk_skb",
+ [BPF_PROG_TYPE_CGROUP_DEVICE] = "cgroup_device",
};
static void print_boot_time(__u64 nsecs, char *buf, unsigned int size)
@@ -775,7 +776,17 @@ static int do_dump(int argc, char **argv)
}
} else {
if (member_len == &info.jited_prog_len) {
- disasm_print_insn(buf, *member_len, opcodes);
+ const char *name = NULL;
+
+ if (info.ifindex) {
+ name = ifindex_to_bfd_name_ns(info.ifindex,
+ info.netns_dev,
+ info.netns_ino);
+ if (!name)
+ goto err_free;
+ }
+
+ disasm_print_insn(buf, *member_len, opcodes, name);
} else {
kernel_syms_load(&dd);
if (json_output)
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index 17f2c73fff8b..bc715f6ac320 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -190,7 +190,7 @@ $(OUTPUT)test-libbfd.bin:
$(BUILD) -DPACKAGE='"perf"' -lbfd -lz -liberty -ldl
$(OUTPUT)test-disassembler-four-args.bin:
- $(BUILD) -lbfd -lopcodes
+ $(BUILD) -DPACKAGE='"perf"' -lbfd -lopcodes
$(OUTPUT)test-liberty.bin:
$(CC) $(CFLAGS) -Wall -Werror -o $@ test-libbfd.c -DPACKAGE='"perf"' $(LDFLAGS) -lbfd -ldl -liberty
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 4e8c60acfa32..af1f49ad8b88 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -245,6 +245,7 @@ union bpf_attr {
* BPF_F_NUMA_NODE is set).
*/
char map_name[BPF_OBJ_NAME_LEN];
+ __u32 map_ifindex; /* ifindex of netdev to create on */
};
struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@@ -899,6 +900,9 @@ struct xdp_md {
__u32 data;
__u32 data_end;
__u32 data_meta;
+ /* Below access go through struct xdp_rxq_info */
+ __u32 ingress_ifindex; /* rxq->dev->ifindex */
+ __u32 rx_queue_index; /* rxq->queue_index */
};
enum sk_action {
@@ -934,6 +938,9 @@ struct bpf_map_info {
__u32 max_entries;
__u32 map_flags;
char name[BPF_OBJ_NAME_LEN];
+ __u32 ifindex;
+ __u64 netns_dev;
+ __u64 netns_ino;
} __attribute__((aligned(8)));
/* User bpf_sock_ops struct to access socket values and specify request ops
@@ -955,6 +962,12 @@ struct bpf_sock_ops {
__u32 local_ip6[4]; /* Stored in network byte order */
__u32 remote_port; /* Stored in network byte order */
__u32 local_port; /* stored in host byte order */
+ __u32 is_fullsock; /* Some TCP fields are only valid if
+ * there is a full socket. If not, the
+ * fields read as zero.
+ */
+ __u32 snd_cwnd;
+ __u32 srtt_us; /* Averaged RTT << 3 in usecs */
};
/* List of known BPF sock_ops operators.
@@ -1009,7 +1022,8 @@ struct bpf_perf_event_value {
#define BPF_DEVCG_DEV_CHAR (1ULL << 1)
struct bpf_cgroup_dev_ctx {
- __u32 access_type; /* (access << 16) | type */
+ /* access_type encoded as (BPF_DEVCG_ACC_* << 16) | BPF_DEVCG_DEV_* */
+ __u32 access_type;
__u32 major;
__u32 minor;
};
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 8ed43ae9db9b..83714ca1f22b 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -93,7 +93,6 @@ export prefix libdir src obj
# Shell quotes
libdir_SQ = $(subst ','\'',$(libdir))
libdir_relative_SQ = $(subst ','\'',$(libdir_relative))
-plugin_dir_SQ = $(subst ','\'',$(plugin_dir))
LIB_FILE = libbpf.a libbpf.so
@@ -150,7 +149,7 @@ CMD_TARGETS = $(LIB_FILE)
TARGETS = $(CMD_TARGETS)
-all: fixdep $(VERSION_FILES) all_cmd
+all: fixdep all_cmd
all_cmd: $(CMD_TARGETS)
@@ -169,21 +168,11 @@ $(OUTPUT)libbpf.so: $(BPF_IN)
$(OUTPUT)libbpf.a: $(BPF_IN)
$(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^
-define update_dir
- (echo $1 > $@.tmp; \
- if [ -r $@ ] && cmp -s $@ $@.tmp; then \
- rm -f $@.tmp; \
- else \
- echo ' UPDATE $@'; \
- mv -f $@.tmp $@; \
- fi);
-endef
-
define do_install
if [ ! -d '$(DESTDIR_SQ)$2' ]; then \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2'; \
fi; \
- $(INSTALL) $1 '$(DESTDIR_SQ)$2'
+ $(INSTALL) $1 $(if $3,-m $3,) '$(DESTDIR_SQ)$2'
endef
install_lib: all_cmd
@@ -192,7 +181,8 @@ install_lib: all_cmd
install_headers:
$(call QUIET_INSTALL, headers) \
- $(call do_install,bpf.h,$(prefix)/include/bpf,644)
+ $(call do_install,bpf.h,$(prefix)/include/bpf,644); \
+ $(call do_install,libbpf.h,$(prefix)/include/bpf,644);
install: install_lib
@@ -203,7 +193,7 @@ config-clean:
$(Q)$(MAKE) -C $(srctree)/tools/build/feature/ clean >/dev/null
clean:
- $(call QUIET_CLEAN, libbpf) $(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d .*.cmd \
+ $(call QUIET_CLEAN, libbpf) $(RM) *.o *~ $(TARGETS) *.a *.so .*.d .*.cmd \
$(RM) LIBBPF-CFLAGS
$(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index e9c4b7cabcf2..30c776375118 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1803,7 +1803,7 @@ BPF_PROG_TYPE_FNS(tracepoint, BPF_PROG_TYPE_TRACEPOINT);
BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP);
BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT);
-#define BPF_PROG_SEC(string, type) { string, sizeof(string), type }
+#define BPF_PROG_SEC(string, type) { string, sizeof(string) - 1, type }
static const struct {
const char *sec;
size_t len;
diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
index ae0272f9a091..e6acc281dd37 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -46,7 +46,7 @@ $(OBJTOOL_IN): fixdep FORCE
@$(MAKE) $(build)=objtool
$(OBJTOOL): $(LIBSUBCMD) $(OBJTOOL_IN)
- @./sync-check.sh
+ @$(CONFIG_SHELL) ./sync-check.sh
$(QUIET_LINK)$(CC) $(OBJTOOL_IN) $(LDFLAGS) -o $@
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 9b341584eb1b..f40d46e24bcc 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -428,6 +428,40 @@ static void add_ignores(struct objtool_file *file)
}
/*
+ * FIXME: For now, just ignore any alternatives which add retpolines. This is
+ * a temporary hack, as it doesn't allow ORC to unwind from inside a retpoline.
+ * But it at least allows objtool to understand the control flow *around* the
+ * retpoline.
+ */
+static int add_nospec_ignores(struct objtool_file *file)
+{
+ struct section *sec;
+ struct rela *rela;
+ struct instruction *insn;
+
+ sec = find_section_by_name(file->elf, ".rela.discard.nospec");
+ if (!sec)
+ return 0;
+
+ list_for_each_entry(rela, &sec->rela_list, list) {
+ if (rela->sym->type != STT_SECTION) {
+ WARN("unexpected relocation symbol type in %s", sec->name);
+ return -1;
+ }
+
+ insn = find_insn(file, rela->sym->sec, rela->addend);
+ if (!insn) {
+ WARN("bad .discard.nospec entry");
+ return -1;
+ }
+
+ insn->ignore_alts = true;
+ }
+
+ return 0;
+}
+
+/*
* Find the destination instructions for all jumps.
*/
static int add_jump_destinations(struct objtool_file *file)
@@ -456,6 +490,13 @@ static int add_jump_destinations(struct objtool_file *file)
} else if (rela->sym->sec->idx) {
dest_sec = rela->sym->sec;
dest_off = rela->sym->sym.st_value + rela->addend + 4;
+ } else if (strstr(rela->sym->name, "_indirect_thunk_")) {
+ /*
+ * Retpoline jumps are really dynamic jumps in
+ * disguise, so convert them accordingly.
+ */
+ insn->type = INSN_JUMP_DYNAMIC;
+ continue;
} else {
/* sibling call */
insn->jump_dest = 0;
@@ -502,11 +543,18 @@ static int add_call_destinations(struct objtool_file *file)
dest_off = insn->offset + insn->len + insn->immediate;
insn->call_dest = find_symbol_by_offset(insn->sec,
dest_off);
+ /*
+ * FIXME: Thanks to retpolines, it's now considered
+ * normal for a function to call within itself. So
+ * disable this warning for now.
+ */
+#if 0
if (!insn->call_dest) {
WARN_FUNC("can't find call dest symbol at offset 0x%lx",
insn->sec, insn->offset, dest_off);
return -1;
}
+#endif
} else if (rela->sym->type == STT_SECTION) {
insn->call_dest = find_symbol_by_offset(rela->sym->sec,
rela->addend+4);
@@ -671,12 +719,6 @@ static int add_special_section_alts(struct objtool_file *file)
return ret;
list_for_each_entry_safe(special_alt, tmp, &special_alts, list) {
- alt = malloc(sizeof(*alt));
- if (!alt) {
- WARN("malloc failed");
- ret = -1;
- goto out;
- }
orig_insn = find_insn(file, special_alt->orig_sec,
special_alt->orig_off);
@@ -687,6 +729,10 @@ static int add_special_section_alts(struct objtool_file *file)
goto out;
}
+ /* Ignore retpoline alternatives. */
+ if (orig_insn->ignore_alts)
+ continue;
+
new_insn = NULL;
if (!special_alt->group || special_alt->new_len) {
new_insn = find_insn(file, special_alt->new_sec,
@@ -712,6 +758,13 @@ static int add_special_section_alts(struct objtool_file *file)
goto out;
}
+ alt = malloc(sizeof(*alt));
+ if (!alt) {
+ WARN("malloc failed");
+ ret = -1;
+ goto out;
+ }
+
alt->insn = new_insn;
list_add_tail(&alt->list, &orig_insn->alts);
@@ -1028,6 +1081,10 @@ static int decode_sections(struct objtool_file *file)
add_ignores(file);
+ ret = add_nospec_ignores(file);
+ if (ret)
+ return ret;
+
ret = add_jump_destinations(file);
if (ret)
return ret;
diff --git a/tools/objtool/check.h b/tools/objtool/check.h
index 47d9ea70a83d..dbadb304a410 100644
--- a/tools/objtool/check.h
+++ b/tools/objtool/check.h
@@ -44,7 +44,7 @@ struct instruction {
unsigned int len;
unsigned char type;
unsigned long immediate;
- bool alt_group, visited, dead_end, ignore, hint, save, restore;
+ bool alt_group, visited, dead_end, ignore, hint, save, restore, ignore_alts;
struct symbol *call_dest;
struct instruction *jump_dest;
struct list_head alts;
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index 24460155c82c..c1c338661699 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -26,6 +26,7 @@
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
+#include <errno.h>
#include "elf.h"
#include "warn.h"
@@ -358,7 +359,8 @@ struct elf *elf_open(const char *name, int flags)
elf->fd = open(name, flags);
if (elf->fd == -1) {
- perror("open");
+ fprintf(stderr, "objtool: Can't open '%s': %s\n",
+ name, strerror(errno));
goto err;
}
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 541d9d7fad5a..1e09d77f1948 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -3,3 +3,10 @@ test_maps
test_lru_map
test_lpm_map
test_tag
+FEATURE-DUMP.libbpf
+fixdep
+test_align
+test_dev_cgroup
+test_progs
+test_verifier_log
+feature
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index a8aa7e251c8e..3a44b655d852 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -19,7 +19,8 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test
TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \
test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o \
sockmap_verdict_prog.o dev_cgroup.o sample_ret0.o test_tracepoint.o \
- test_l4lb_noinline.o test_xdp_noinline.o test_stacktrace_map.o
+ test_l4lb_noinline.o test_xdp_noinline.o test_stacktrace_map.o \
+ sample_map_ret0.o
TEST_PROGS := test_kmod.sh test_xdp_redirect.sh test_xdp_meta.sh \
test_offload.py
diff --git a/tools/testing/selftests/bpf/sample_map_ret0.c b/tools/testing/selftests/bpf/sample_map_ret0.c
new file mode 100644
index 000000000000..0756303676ac
--- /dev/null
+++ b/tools/testing/selftests/bpf/sample_map_ret0.c
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) */
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+
+struct bpf_map_def SEC("maps") htab = {
+ .type = BPF_MAP_TYPE_HASH,
+ .key_size = sizeof(__u32),
+ .value_size = sizeof(long),
+ .max_entries = 2,
+};
+
+struct bpf_map_def SEC("maps") array = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(__u32),
+ .value_size = sizeof(long),
+ .max_entries = 2,
+};
+
+/* Sample program which should always load for testing control paths. */
+SEC(".text") int func()
+{
+ __u64 key64 = 0;
+ __u32 key = 0;
+ long *value;
+
+ value = bpf_map_lookup_elem(&htab, &key);
+ if (!value)
+ return 1;
+ value = bpf_map_lookup_elem(&array, &key64);
+ if (!value)
+ return 1;
+
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/test_lpm_map.c b/tools/testing/selftests/bpf/test_lpm_map.c
index f61480641b6e..081510853c6d 100644
--- a/tools/testing/selftests/bpf/test_lpm_map.c
+++ b/tools/testing/selftests/bpf/test_lpm_map.c
@@ -521,6 +521,126 @@ static void test_lpm_delete(void)
close(map_fd);
}
+static void test_lpm_get_next_key(void)
+{
+ struct bpf_lpm_trie_key *key_p, *next_key_p;
+ size_t key_size;
+ __u32 value = 0;
+ int map_fd;
+
+ key_size = sizeof(*key_p) + sizeof(__u32);
+ key_p = alloca(key_size);
+ next_key_p = alloca(key_size);
+
+ map_fd = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE, key_size, sizeof(value),
+ 100, BPF_F_NO_PREALLOC);
+ assert(map_fd >= 0);
+
+ /* empty tree. get_next_key should return ENOENT */
+ assert(bpf_map_get_next_key(map_fd, NULL, key_p) == -1 &&
+ errno == ENOENT);
+
+ /* get and verify the first key, get the second one should fail. */
+ key_p->prefixlen = 16;
+ inet_pton(AF_INET, "192.168.0.0", key_p->data);
+ assert(bpf_map_update_elem(map_fd, key_p, &value, 0) == 0);
+
+ memset(key_p, 0, key_size);
+ assert(bpf_map_get_next_key(map_fd, NULL, key_p) == 0);
+ assert(key_p->prefixlen == 16 && key_p->data[0] == 192 &&
+ key_p->data[1] == 168);
+
+ assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == -1 &&
+ errno == ENOENT);
+
+ /* no exact matching key should get the first one in post order. */
+ key_p->prefixlen = 8;
+ assert(bpf_map_get_next_key(map_fd, NULL, key_p) == 0);
+ assert(key_p->prefixlen == 16 && key_p->data[0] == 192 &&
+ key_p->data[1] == 168);
+
+ /* add one more element (total two) */
+ key_p->prefixlen = 24;
+ inet_pton(AF_INET, "192.168.0.0", key_p->data);
+ assert(bpf_map_update_elem(map_fd, key_p, &value, 0) == 0);
+
+ memset(key_p, 0, key_size);
+ assert(bpf_map_get_next_key(map_fd, NULL, key_p) == 0);
+ assert(key_p->prefixlen == 24 && key_p->data[0] == 192 &&
+ key_p->data[1] == 168 && key_p->data[2] == 0);
+
+ memset(next_key_p, 0, key_size);
+ assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0);
+ assert(next_key_p->prefixlen == 16 && next_key_p->data[0] == 192 &&
+ next_key_p->data[1] == 168);
+
+ memcpy(key_p, next_key_p, key_size);
+ assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == -1 &&
+ errno == ENOENT);
+
+ /* Add one more element (total three) */
+ key_p->prefixlen = 24;
+ inet_pton(AF_INET, "192.168.128.0", key_p->data);
+ assert(bpf_map_update_elem(map_fd, key_p, &value, 0) == 0);
+
+ memset(key_p, 0, key_size);
+ assert(bpf_map_get_next_key(map_fd, NULL, key_p) == 0);
+ assert(key_p->prefixlen == 24 && key_p->data[0] == 192 &&
+ key_p->data[1] == 168 && key_p->data[2] == 0);
+
+ memset(next_key_p, 0, key_size);
+ assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0);
+ assert(next_key_p->prefixlen == 24 && next_key_p->data[0] == 192 &&
+ next_key_p->data[1] == 168 && next_key_p->data[2] == 128);
+
+ memcpy(key_p, next_key_p, key_size);
+ assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0);
+ assert(next_key_p->prefixlen == 16 && next_key_p->data[0] == 192 &&
+ next_key_p->data[1] == 168);
+
+ memcpy(key_p, next_key_p, key_size);
+ assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == -1 &&
+ errno == ENOENT);
+
+ /* Add one more element (total four) */
+ key_p->prefixlen = 24;
+ inet_pton(AF_INET, "192.168.1.0", key_p->data);
+ assert(bpf_map_update_elem(map_fd, key_p, &value, 0) == 0);
+
+ memset(key_p, 0, key_size);
+ assert(bpf_map_get_next_key(map_fd, NULL, key_p) == 0);
+ assert(key_p->prefixlen == 24 && key_p->data[0] == 192 &&
+ key_p->data[1] == 168 && key_p->data[2] == 0);
+
+ memset(next_key_p, 0, key_size);
+ assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0);
+ assert(next_key_p->prefixlen == 24 && next_key_p->data[0] == 192 &&
+ next_key_p->data[1] == 168 && next_key_p->data[2] == 1);
+
+ memcpy(key_p, next_key_p, key_size);
+ assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0);
+ assert(next_key_p->prefixlen == 24 && next_key_p->data[0] == 192 &&
+ next_key_p->data[1] == 168 && next_key_p->data[2] == 128);
+
+ memcpy(key_p, next_key_p, key_size);
+ assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0);
+ assert(next_key_p->prefixlen == 16 && next_key_p->data[0] == 192 &&
+ next_key_p->data[1] == 168);
+
+ memcpy(key_p, next_key_p, key_size);
+ assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == -1 &&
+ errno == ENOENT);
+
+ /* no exact matching key should return the first one in post order */
+ key_p->prefixlen = 22;
+ inet_pton(AF_INET, "192.168.1.0", key_p->data);
+ assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0);
+ assert(next_key_p->prefixlen == 24 && next_key_p->data[0] == 192 &&
+ next_key_p->data[1] == 168 && next_key_p->data[2] == 0);
+
+ close(map_fd);
+}
+
int main(void)
{
struct rlimit limit = { RLIM_INFINITY, RLIM_INFINITY };
@@ -545,6 +665,8 @@ int main(void)
test_lpm_delete();
+ test_lpm_get_next_key();
+
printf("test_lpm: OK\n");
return 0;
}
diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py
index e3c750f17cb8..833b9c1ec450 100755
--- a/tools/testing/selftests/bpf/test_offload.py
+++ b/tools/testing/selftests/bpf/test_offload.py
@@ -20,6 +20,7 @@ import os
import pprint
import random
import string
+import struct
import subprocess
import time
@@ -156,6 +157,14 @@ def bpftool_prog_list(expected=None, ns=""):
(len(progs), expected))
return progs
+def bpftool_map_list(expected=None, ns=""):
+ _, maps = bpftool("map show", JSON=True, ns=ns, fail=True)
+ if expected is not None:
+ if len(maps) != expected:
+ fail(True, "%d BPF maps loaded, expected %d" %
+ (len(maps), expected))
+ return maps
+
def bpftool_prog_list_wait(expected=0, n_retry=20):
for i in range(n_retry):
nprogs = len(bpftool_prog_list())
@@ -164,6 +173,14 @@ def bpftool_prog_list_wait(expected=0, n_retry=20):
time.sleep(0.05)
raise Exception("Time out waiting for program counts to stabilize want %d, have %d" % (expected, nprogs))
+def bpftool_map_list_wait(expected=0, n_retry=20):
+ for i in range(n_retry):
+ nmaps = len(bpftool_map_list())
+ if nmaps == expected:
+ return
+ time.sleep(0.05)
+ raise Exception("Time out waiting for map counts to stabilize want %d, have %d" % (expected, nmaps))
+
def ip(args, force=False, JSON=True, ns="", fail=True):
if force:
args = "-force " + args
@@ -193,6 +210,26 @@ def mknetns(n_retry=10):
return name
return None
+def int2str(fmt, val):
+ ret = []
+ for b in struct.pack(fmt, val):
+ ret.append(int(b))
+ return " ".join(map(lambda x: str(x), ret))
+
+def str2int(strtab):
+ inttab = []
+ for i in strtab:
+ inttab.append(int(i, 16))
+ ba = bytearray(inttab)
+ if len(strtab) == 4:
+ fmt = "I"
+ elif len(strtab) == 8:
+ fmt = "Q"
+ else:
+ raise Exception("String array of len %d can't be unpacked to an int" %
+ (len(strtab)))
+ return struct.unpack(fmt, ba)[0]
+
class DebugfsDir:
"""
Class for accessing DebugFS directories as a dictionary.
@@ -311,13 +348,13 @@ class NetdevSim:
return ip("link set dev %s mtu %d" % (self.dev["ifname"], mtu),
fail=fail)
- def set_xdp(self, bpf, mode, force=False, fail=True):
+ def set_xdp(self, bpf, mode, force=False, JSON=True, fail=True):
return ip("link set dev %s xdp%s %s" % (self.dev["ifname"], mode, bpf),
- force=force, fail=fail)
+ force=force, JSON=JSON, fail=fail)
- def unset_xdp(self, mode, force=False, fail=True):
+ def unset_xdp(self, mode, force=False, JSON=True, fail=True):
return ip("link set dev %s xdp%s off" % (self.dev["ifname"], mode),
- force=force, fail=fail)
+ force=force, JSON=JSON, fail=fail)
def ip_link_show(self, xdp):
_, link = ip("link show dev %s" % (self['ifname']))
@@ -390,12 +427,16 @@ class NetdevSim:
################################################################################
def clean_up():
+ global files, netns, devs
+
for dev in devs:
dev.remove()
for f in files:
cmd("rm -f %s" % (f))
for ns in netns:
cmd("ip netns delete %s" % (ns))
+ files = []
+ netns = []
def pin_prog(file_name, idx=0):
progs = bpftool_prog_list(expected=(idx + 1))
@@ -405,16 +446,31 @@ def pin_prog(file_name, idx=0):
return file_name, bpf_pinned(file_name)
-def check_dev_info(other_ns, ns, pin_file=None, removed=False):
- if removed:
- bpftool_prog_list(expected=0)
- ret, err = bpftool("prog show pin %s" % (pin_file), fail=False)
- fail(ret == 0, "Showing prog with removed device did not fail")
- fail(err["error"].find("No such device") == -1,
- "Showing prog with removed device expected ENODEV, error is %s" %
- (err["error"]))
- return
- progs = bpftool_prog_list(expected=int(not removed), ns=ns)
+def pin_map(file_name, idx=0, expected=1):
+ maps = bpftool_map_list(expected=expected)
+ m = maps[idx]
+ bpftool("map pin id %d %s" % (m["id"], file_name))
+ files.append(file_name)
+
+ return file_name, bpf_pinned(file_name)
+
+def check_dev_info_removed(prog_file=None, map_file=None):
+ bpftool_prog_list(expected=0)
+ ret, err = bpftool("prog show pin %s" % (prog_file), fail=False)
+ fail(ret == 0, "Showing prog with removed device did not fail")
+ fail(err["error"].find("No such device") == -1,
+ "Showing prog with removed device expected ENODEV, error is %s" %
+ (err["error"]))
+
+ bpftool_map_list(expected=0)
+ ret, err = bpftool("map show pin %s" % (map_file), fail=False)
+ fail(ret == 0, "Showing map with removed device did not fail")
+ fail(err["error"].find("No such device") == -1,
+ "Showing map with removed device expected ENODEV, error is %s" %
+ (err["error"]))
+
+def check_dev_info(other_ns, ns, prog_file=None, map_file=None, removed=False):
+ progs = bpftool_prog_list(expected=1, ns=ns)
prog = progs[0]
fail("dev" not in prog.keys(), "Device parameters not reported")
@@ -423,16 +479,17 @@ def check_dev_info(other_ns, ns, pin_file=None, removed=False):
fail("ns_dev" not in dev.keys(), "Device parameters not reported")
fail("ns_inode" not in dev.keys(), "Device parameters not reported")
- if not removed and not other_ns:
+ if not other_ns:
fail("ifname" not in dev.keys(), "Ifname not reported")
fail(dev["ifname"] != sim["ifname"],
"Ifname incorrect %s vs %s" % (dev["ifname"], sim["ifname"]))
else:
fail("ifname" in dev.keys(), "Ifname is reported for other ns")
- if removed:
- fail(dev["ifindex"] != 0, "Device perameters not zero on removed")
- fail(dev["ns_dev"] != 0, "Device perameters not zero on removed")
- fail(dev["ns_inode"] != 0, "Device perameters not zero on removed")
+
+ maps = bpftool_map_list(expected=2, ns=ns)
+ for m in maps:
+ fail("dev" not in m.keys(), "Device parameters not reported")
+ fail(dev != m["dev"], "Map's device different than program's")
# Parse command line
parser = argparse.ArgumentParser()
@@ -464,7 +521,7 @@ if out.find("/sys/kernel/debug type debugfs") == -1:
cmd("mount -t debugfs none /sys/kernel/debug")
# Check samples are compiled
-samples = ["sample_ret0.o"]
+samples = ["sample_ret0.o", "sample_map_ret0.o"]
for s in samples:
ret, out = cmd("ls %s/%s" % (bpf_test_dir, s), fail=False)
skip(ret != 0, "sample %s/%s not found, please compile it" %
@@ -739,8 +796,9 @@ try:
bpftool_prog_list_wait(expected=0)
sim = NetdevSim()
- sim.set_ethtool_tc_offloads(True)
- sim.set_xdp(obj, "offload")
+ map_obj = bpf_obj("sample_map_ret0.o")
+ start_test("Test loading program with maps...")
+ sim.set_xdp(map_obj, "offload", JSON=False) # map fixup msg breaks JSON
start_test("Test bpftool bound info reporting (own ns)...")
check_dev_info(False, "")
@@ -757,11 +815,111 @@ try:
sim.set_ns("")
check_dev_info(False, "")
- pin_file, _ = pin_prog("/sys/fs/bpf/tmp")
+ prog_file, _ = pin_prog("/sys/fs/bpf/tmp_prog")
+ map_file, _ = pin_map("/sys/fs/bpf/tmp_map", idx=1, expected=2)
sim.remove()
start_test("Test bpftool bound info reporting (removed dev)...")
- check_dev_info(True, "", pin_file=pin_file, removed=True)
+ check_dev_info_removed(prog_file=prog_file, map_file=map_file)
+
+ # Remove all pinned files and reinstantiate the netdev
+ clean_up()
+ bpftool_prog_list_wait(expected=0)
+
+ sim = NetdevSim()
+
+ start_test("Test map update (no flags)...")
+ sim.set_xdp(map_obj, "offload", JSON=False) # map fixup msg breaks JSON
+ maps = bpftool_map_list(expected=2)
+ array = maps[0] if maps[0]["type"] == "array" else maps[1]
+ htab = maps[0] if maps[0]["type"] == "hash" else maps[1]
+ for m in maps:
+ for i in range(2):
+ bpftool("map update id %d key %s value %s" %
+ (m["id"], int2str("I", i), int2str("Q", i * 3)))
+
+ for m in maps:
+ ret, _ = bpftool("map update id %d key %s value %s" %
+ (m["id"], int2str("I", 3), int2str("Q", 3 * 3)),
+ fail=False)
+ fail(ret == 0, "added too many entries")
+
+ start_test("Test map update (exists)...")
+ for m in maps:
+ for i in range(2):
+ bpftool("map update id %d key %s value %s exist" %
+ (m["id"], int2str("I", i), int2str("Q", i * 3)))
+
+ for m in maps:
+ ret, err = bpftool("map update id %d key %s value %s exist" %
+ (m["id"], int2str("I", 3), int2str("Q", 3 * 3)),
+ fail=False)
+ fail(ret == 0, "updated non-existing key")
+ fail(err["error"].find("No such file or directory") == -1,
+ "expected ENOENT, error is '%s'" % (err["error"]))
+
+ start_test("Test map update (noexist)...")
+ for m in maps:
+ for i in range(2):
+ ret, err = bpftool("map update id %d key %s value %s noexist" %
+ (m["id"], int2str("I", i), int2str("Q", i * 3)),
+ fail=False)
+ fail(ret == 0, "updated existing key")
+ fail(err["error"].find("File exists") == -1,
+ "expected EEXIST, error is '%s'" % (err["error"]))
+
+ start_test("Test map dump...")
+ for m in maps:
+ _, entries = bpftool("map dump id %d" % (m["id"]))
+ for i in range(2):
+ key = str2int(entries[i]["key"])
+ fail(key != i, "expected key %d, got %d" % (key, i))
+ val = str2int(entries[i]["value"])
+ fail(val != i * 3, "expected value %d, got %d" % (val, i * 3))
+
+ start_test("Test map getnext...")
+ for m in maps:
+ _, entry = bpftool("map getnext id %d" % (m["id"]))
+ key = str2int(entry["next_key"])
+ fail(key != 0, "next key %d, expected %d" % (key, 0))
+ _, entry = bpftool("map getnext id %d key %s" %
+ (m["id"], int2str("I", 0)))
+ key = str2int(entry["next_key"])
+ fail(key != 1, "next key %d, expected %d" % (key, 1))
+ ret, err = bpftool("map getnext id %d key %s" %
+ (m["id"], int2str("I", 1)), fail=False)
+ fail(ret == 0, "got next key past the end of map")
+ fail(err["error"].find("No such file or directory") == -1,
+ "expected ENOENT, error is '%s'" % (err["error"]))
+
+ start_test("Test map delete (htab)...")
+ for i in range(2):
+ bpftool("map delete id %d key %s" % (htab["id"], int2str("I", i)))
+
+ start_test("Test map delete (array)...")
+ for i in range(2):
+ ret, err = bpftool("map delete id %d key %s" %
+ (htab["id"], int2str("I", i)), fail=False)
+ fail(ret == 0, "removed entry from an array")
+ fail(err["error"].find("No such file or directory") == -1,
+ "expected ENOENT, error is '%s'" % (err["error"]))
+
+ start_test("Test map remove...")
+ sim.unset_xdp("offload")
+ bpftool_map_list_wait(expected=0)
+ sim.remove()
+
+ sim = NetdevSim()
+ sim.set_xdp(map_obj, "offload", JSON=False) # map fixup msg breaks JSON
+ sim.remove()
+ bpftool_map_list_wait(expected=0)
+
+ start_test("Test map creation fail path...")
+ sim = NetdevSim()
+ sim.dfs["bpf_map_accept"] = "N"
+ ret, _ = sim.set_xdp(map_obj, "offload", JSON=False, fail=False)
+ fail(ret == 0,
+ "netdevsim didn't refuse to create a map with offload disabled")
print("%s: OK" % (os.path.basename(__file__)))
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 543847957fdd..fb82d29ee863 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -29,6 +29,7 @@
#include <linux/filter.h>
#include <linux/bpf_perf_event.h>
#include <linux/bpf.h>
+#include <linux/if_ether.h>
#include <bpf/bpf.h>
@@ -49,6 +50,8 @@
#define MAX_INSNS 512
#define MAX_FIXUPS 8
#define MAX_NR_MAPS 4
+#define POINTER_VALUE 0xcafe4all
+#define TEST_DATA_LEN 64
#define F_NEEDS_EFFICIENT_UNALIGNED_ACCESS (1 << 0)
#define F_LOAD_WITH_STRICT_ALIGNMENT (1 << 1)
@@ -62,6 +65,7 @@ struct bpf_test {
int fixup_map_in_map[MAX_FIXUPS];
const char *errstr;
const char *errstr_unpriv;
+ uint32_t retval;
enum {
UNDEF,
ACCEPT,
@@ -95,6 +99,94 @@ static struct bpf_test tests[] = {
BPF_EXIT_INSN(),
},
.result = ACCEPT,
+ .retval = -3,
+ },
+ {
+ "DIV32 by 0, zero check 1",
+ .insns = {
+ BPF_MOV32_IMM(BPF_REG_0, 42),
+ BPF_MOV32_IMM(BPF_REG_1, 0),
+ BPF_MOV32_IMM(BPF_REG_2, 1),
+ BPF_ALU32_REG(BPF_DIV, BPF_REG_2, BPF_REG_1),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .retval = 0,
+ },
+ {
+ "DIV32 by 0, zero check 2",
+ .insns = {
+ BPF_MOV32_IMM(BPF_REG_0, 42),
+ BPF_LD_IMM64(BPF_REG_1, 0xffffffff00000000LL),
+ BPF_MOV32_IMM(BPF_REG_2, 1),
+ BPF_ALU32_REG(BPF_DIV, BPF_REG_2, BPF_REG_1),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .retval = 0,
+ },
+ {
+ "DIV64 by 0, zero check",
+ .insns = {
+ BPF_MOV32_IMM(BPF_REG_0, 42),
+ BPF_MOV32_IMM(BPF_REG_1, 0),
+ BPF_MOV32_IMM(BPF_REG_2, 1),
+ BPF_ALU64_REG(BPF_DIV, BPF_REG_2, BPF_REG_1),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .retval = 0,
+ },
+ {
+ "MOD32 by 0, zero check 1",
+ .insns = {
+ BPF_MOV32_IMM(BPF_REG_0, 42),
+ BPF_MOV32_IMM(BPF_REG_1, 0),
+ BPF_MOV32_IMM(BPF_REG_2, 1),
+ BPF_ALU32_REG(BPF_MOD, BPF_REG_2, BPF_REG_1),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .retval = 0,
+ },
+ {
+ "MOD32 by 0, zero check 2",
+ .insns = {
+ BPF_MOV32_IMM(BPF_REG_0, 42),
+ BPF_LD_IMM64(BPF_REG_1, 0xffffffff00000000LL),
+ BPF_MOV32_IMM(BPF_REG_2, 1),
+ BPF_ALU32_REG(BPF_MOD, BPF_REG_2, BPF_REG_1),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .retval = 0,
+ },
+ {
+ "MOD64 by 0, zero check",
+ .insns = {
+ BPF_MOV32_IMM(BPF_REG_0, 42),
+ BPF_MOV32_IMM(BPF_REG_1, 0),
+ BPF_MOV32_IMM(BPF_REG_2, 1),
+ BPF_ALU64_REG(BPF_MOD, BPF_REG_2, BPF_REG_1),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .retval = 0,
+ },
+ {
+ "empty prog",
+ .insns = {
+ },
+ .errstr = "last insn is not an exit or jmp",
+ .result = REJECT,
+ },
+ {
+ "only exit insn",
+ .insns = {
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "R0 !read_ok",
+ .result = REJECT,
},
{
"unreachable",
@@ -210,6 +302,7 @@ static struct bpf_test tests[] = {
BPF_EXIT_INSN(),
},
.result = ACCEPT,
+ .retval = 1,
},
{
"test8 ld_imm64",
@@ -274,6 +367,46 @@ static struct bpf_test tests[] = {
.result = REJECT,
},
{
+ "arsh32 on imm",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_ALU32_IMM(BPF_ARSH, BPF_REG_0, 5),
+ BPF_EXIT_INSN(),
+ },
+ .result = REJECT,
+ .errstr = "BPF_ARSH not supported for 32 bit ALU",
+ },
+ {
+ "arsh32 on reg",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_MOV64_IMM(BPF_REG_1, 5),
+ BPF_ALU32_REG(BPF_ARSH, BPF_REG_0, BPF_REG_1),
+ BPF_EXIT_INSN(),
+ },
+ .result = REJECT,
+ .errstr = "BPF_ARSH not supported for 32 bit ALU",
+ },
+ {
+ "arsh64 on imm",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_ALU64_IMM(BPF_ARSH, BPF_REG_0, 5),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ },
+ {
+ "arsh64 on reg",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_MOV64_IMM(BPF_REG_1, 5),
+ BPF_ALU64_REG(BPF_ARSH, BPF_REG_0, BPF_REG_1),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ },
+ {
"no bpf_exit",
.insns = {
BPF_ALU64_REG(BPF_MOV, BPF_REG_0, BPF_REG_2),
@@ -477,6 +610,7 @@ static struct bpf_test tests[] = {
.errstr_unpriv = "R0 leaks addr",
.result = ACCEPT,
.result_unpriv = REJECT,
+ .retval = POINTER_VALUE,
},
{
"check valid spill/fill, skb mark",
@@ -763,6 +897,7 @@ static struct bpf_test tests[] = {
.errstr_unpriv = "R1 pointer comparison",
.result_unpriv = REJECT,
.result = ACCEPT,
+ .retval = -ENOENT,
},
{
"jump test 4",
@@ -1783,6 +1918,7 @@ static struct bpf_test tests[] = {
BPF_EXIT_INSN(),
},
.result = ACCEPT,
+ .retval = 0xfaceb00c,
},
{
"PTR_TO_STACK store/load - bad alignment on off",
@@ -1841,6 +1977,7 @@ static struct bpf_test tests[] = {
.result = ACCEPT,
.result_unpriv = REJECT,
.errstr_unpriv = "R0 leaks addr",
+ .retval = POINTER_VALUE,
},
{
"unpriv: add const to pointer",
@@ -2014,6 +2151,7 @@ static struct bpf_test tests[] = {
BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, 0),
BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
BPF_FUNC_get_hash_recalc),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
.result = ACCEPT,
@@ -2554,6 +2692,29 @@ static struct bpf_test tests[] = {
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
},
{
+ "context stores via ST",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_ST_MEM(BPF_DW, BPF_REG_1, offsetof(struct __sk_buff, mark), 0),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "BPF_ST stores into R1 context is not allowed",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ },
+ {
+ "context stores via XADD",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_W, BPF_REG_1,
+ BPF_REG_0, offsetof(struct __sk_buff, mark), 0),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "BPF_XADD stores into R1 context is not allowed",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ },
+ {
"direct packet access: test1",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
@@ -2778,6 +2939,7 @@ static struct bpf_test tests[] = {
},
.result = ACCEPT,
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .retval = 1,
},
{
"direct packet access: test12 (and, good access)",
@@ -2802,6 +2964,7 @@ static struct bpf_test tests[] = {
},
.result = ACCEPT,
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .retval = 1,
},
{
"direct packet access: test13 (branches, good access)",
@@ -2832,6 +2995,7 @@ static struct bpf_test tests[] = {
},
.result = ACCEPT,
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .retval = 1,
},
{
"direct packet access: test14 (pkt_ptr += 0, CONST_IMM, good access)",
@@ -2855,6 +3019,7 @@ static struct bpf_test tests[] = {
},
.result = ACCEPT,
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .retval = 1,
},
{
"direct packet access: test15 (spill with xadd)",
@@ -3141,6 +3306,7 @@ static struct bpf_test tests[] = {
},
.result = ACCEPT,
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .retval = 1,
},
{
"direct packet access: test28 (marking on <=, bad access)",
@@ -4273,7 +4439,8 @@ static struct bpf_test tests[] = {
.fixup_map1 = { 2 },
.errstr_unpriv = "R2 leaks addr into mem",
.result_unpriv = REJECT,
- .result = ACCEPT,
+ .result = REJECT,
+ .errstr = "BPF_XADD stores into R1 context is not allowed",
},
{
"leak pointer into ctx 2",
@@ -4287,7 +4454,8 @@ static struct bpf_test tests[] = {
},
.errstr_unpriv = "R10 leaks addr into mem",
.result_unpriv = REJECT,
- .result = ACCEPT,
+ .result = REJECT,
+ .errstr = "BPF_XADD stores into R1 context is not allowed",
},
{
"leak pointer into ctx 3",
@@ -5758,6 +5926,7 @@ static struct bpf_test tests[] = {
},
.result = ACCEPT,
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .retval = 0 /* csum_diff of 64-byte packet */,
},
{
"helper access to variable memory: size = 0 not allowed on NULL (!ARG_PTR_TO_MEM_OR_NULL)",
@@ -6126,6 +6295,7 @@ static struct bpf_test tests[] = {
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.result = ACCEPT,
+ .retval = 42 /* ultimate return value */,
},
{
"ld_ind: check calling conv, r1",
@@ -6197,6 +6367,7 @@ static struct bpf_test tests[] = {
BPF_EXIT_INSN(),
},
.result = ACCEPT,
+ .retval = 1,
},
{
"check bpf_perf_event_data->sample_period byte load permitted",
@@ -6668,7 +6839,7 @@ static struct bpf_test tests[] = {
BPF_JMP_IMM(BPF_JA, 0, 0, -7),
},
.fixup_map1 = { 4 },
- .errstr = "unbounded min value",
+ .errstr = "R0 invalid mem access 'inv'",
.result = REJECT,
},
{
@@ -7184,6 +7355,7 @@ static struct bpf_test tests[] = {
},
.fixup_map1 = { 3 },
.result = ACCEPT,
+ .retval = POINTER_VALUE,
.result_unpriv = REJECT,
.errstr_unpriv = "R0 leaks addr as return value"
},
@@ -7204,6 +7376,7 @@ static struct bpf_test tests[] = {
},
.fixup_map1 = { 3 },
.result = ACCEPT,
+ .retval = POINTER_VALUE,
.result_unpriv = REJECT,
.errstr_unpriv = "R0 leaks addr as return value"
},
@@ -7645,6 +7818,7 @@ static struct bpf_test tests[] = {
BPF_EXIT_INSN(),
},
.result = ACCEPT,
+ .retval = TEST_DATA_LEN,
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
},
{
@@ -8570,6 +8744,127 @@ static struct bpf_test tests[] = {
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
+ "check deducing bounds from const, 1",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_JMP_IMM(BPF_JSGE, BPF_REG_0, 1, 0),
+ BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
+ BPF_EXIT_INSN(),
+ },
+ .result = REJECT,
+ .errstr = "R0 tried to subtract pointer from scalar",
+ },
+ {
+ "check deducing bounds from const, 2",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_JMP_IMM(BPF_JSGE, BPF_REG_0, 1, 1),
+ BPF_EXIT_INSN(),
+ BPF_JMP_IMM(BPF_JSLE, BPF_REG_0, 1, 1),
+ BPF_EXIT_INSN(),
+ BPF_ALU64_REG(BPF_SUB, BPF_REG_1, BPF_REG_0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ },
+ {
+ "check deducing bounds from const, 3",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JSLE, BPF_REG_0, 0, 0),
+ BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
+ BPF_EXIT_INSN(),
+ },
+ .result = REJECT,
+ .errstr = "R0 tried to subtract pointer from scalar",
+ },
+ {
+ "check deducing bounds from const, 4",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JSLE, BPF_REG_0, 0, 1),
+ BPF_EXIT_INSN(),
+ BPF_JMP_IMM(BPF_JSGE, BPF_REG_0, 0, 1),
+ BPF_EXIT_INSN(),
+ BPF_ALU64_REG(BPF_SUB, BPF_REG_1, BPF_REG_0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ },
+ {
+ "check deducing bounds from const, 5",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JSGE, BPF_REG_0, 0, 1),
+ BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
+ BPF_EXIT_INSN(),
+ },
+ .result = REJECT,
+ .errstr = "R0 tried to subtract pointer from scalar",
+ },
+ {
+ "check deducing bounds from const, 6",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JSGE, BPF_REG_0, 0, 1),
+ BPF_EXIT_INSN(),
+ BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
+ BPF_EXIT_INSN(),
+ },
+ .result = REJECT,
+ .errstr = "R0 tried to subtract pointer from scalar",
+ },
+ {
+ "check deducing bounds from const, 7",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, ~0),
+ BPF_JMP_IMM(BPF_JSGE, BPF_REG_0, 0, 0),
+ BPF_ALU64_REG(BPF_SUB, BPF_REG_1, BPF_REG_0),
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, mark)),
+ BPF_EXIT_INSN(),
+ },
+ .result = REJECT,
+ .errstr = "dereference of modified ctx ptr",
+ },
+ {
+ "check deducing bounds from const, 8",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, ~0),
+ BPF_JMP_IMM(BPF_JSGE, BPF_REG_0, 0, 1),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, mark)),
+ BPF_EXIT_INSN(),
+ },
+ .result = REJECT,
+ .errstr = "dereference of modified ctx ptr",
+ },
+ {
+ "check deducing bounds from const, 9",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JSGE, BPF_REG_0, 0, 0),
+ BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
+ BPF_EXIT_INSN(),
+ },
+ .result = REJECT,
+ .errstr = "R0 tried to subtract pointer from scalar",
+ },
+ {
+ "check deducing bounds from const, 10",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JSLE, BPF_REG_0, 0, 0),
+ /* Marks reg as unknown. */
+ BPF_ALU64_IMM(BPF_NEG, BPF_REG_0, 0),
+ BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
+ BPF_EXIT_INSN(),
+ },
+ .result = REJECT,
+ .errstr = "math between ctx pointer and register with unbounded min value is not allowed",
+ },
+ {
"bpf_exit with invalid return code. test1",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
@@ -8665,6 +8960,7 @@ static struct bpf_test tests[] = {
.errstr_unpriv = "function calls to other bpf functions are allowed for root only",
.result_unpriv = REJECT,
.result = ACCEPT,
+ .retval = 1,
},
{
"calls: overlapping caller/callee",
@@ -8860,6 +9156,7 @@ static struct bpf_test tests[] = {
},
.prog_type = BPF_PROG_TYPE_SCHED_ACT,
.result = ACCEPT,
+ .retval = TEST_DATA_LEN,
},
{
"calls: callee using args1",
@@ -8872,6 +9169,7 @@ static struct bpf_test tests[] = {
.errstr_unpriv = "allowed for root only",
.result_unpriv = REJECT,
.result = ACCEPT,
+ .retval = POINTER_VALUE,
},
{
"calls: callee using wrong args2",
@@ -8902,6 +9200,7 @@ static struct bpf_test tests[] = {
.errstr_unpriv = "allowed for root only",
.result_unpriv = REJECT,
.result = ACCEPT,
+ .retval = TEST_DATA_LEN + TEST_DATA_LEN - ETH_HLEN - ETH_HLEN,
},
{
"calls: callee changing pkt pointers",
@@ -8950,6 +9249,7 @@ static struct bpf_test tests[] = {
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.result = ACCEPT,
+ .retval = TEST_DATA_LEN + TEST_DATA_LEN,
},
{
"calls: calls with stack arith",
@@ -8968,6 +9268,7 @@ static struct bpf_test tests[] = {
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.result = ACCEPT,
+ .retval = 42,
},
{
"calls: calls with misaligned stack access",
@@ -9001,6 +9302,7 @@ static struct bpf_test tests[] = {
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.result = ACCEPT,
+ .retval = 43,
},
{
"calls: calls control flow, jump test 2",
@@ -9493,6 +9795,7 @@ static struct bpf_test tests[] = {
},
.prog_type = BPF_PROG_TYPE_XDP,
.result = ACCEPT,
+ .retval = 42,
},
{
"calls: write into callee stack frame",
@@ -10104,6 +10407,7 @@ static struct bpf_test tests[] = {
},
.result = ACCEPT,
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .retval = POINTER_VALUE,
},
{
"calls: pkt_ptr spill into caller stack 2",
@@ -10169,6 +10473,7 @@ static struct bpf_test tests[] = {
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.result = ACCEPT,
+ .retval = 1,
},
{
"calls: pkt_ptr spill into caller stack 4",
@@ -10202,6 +10507,7 @@ static struct bpf_test tests[] = {
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.result = ACCEPT,
+ .retval = 1,
},
{
"calls: pkt_ptr spill into caller stack 5",
@@ -10610,10 +10916,12 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
int fd_prog, expected_ret, reject_from_alignment;
struct bpf_insn *prog = test->insns;
int prog_len = probe_filter_length(prog);
+ char data_in[TEST_DATA_LEN] = {};
int prog_type = test->prog_type;
int map_fds[MAX_NR_MAPS];
const char *expected_err;
- int i;
+ uint32_t retval;
+ int i, err;
for (i = 0; i < MAX_NR_MAPS; i++)
map_fds[i] = -1;
@@ -10656,6 +10964,19 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
}
}
+ if (fd_prog >= 0) {
+ err = bpf_prog_test_run(fd_prog, 1, data_in, sizeof(data_in),
+ NULL, NULL, &retval, NULL);
+ if (err && errno != 524/*ENOTSUPP*/ && errno != EPERM) {
+ printf("Unexpected bpf_prog_test_run error\n");
+ goto fail_log;
+ }
+ if (!err && retval != test->retval &&
+ test->retval != POINTER_VALUE) {
+ printf("FAIL retval %d != %d\n", retval, test->retval);
+ goto fail_log;
+ }
+ }
(*passes)++;
printf("OK%s\n", reject_from_alignment ?
" (NOTE: reject due to unknown alignment)" : "");
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index 939a337128db..5d4f10ac2af2 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -7,7 +7,7 @@ include ../lib.mk
TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_syscall test_mremap_vdso \
check_initial_reg_state sigreturn ldt_gdt iopl mpx-mini-test ioperm \
- protection_keys test_vdso
+ protection_keys test_vdso test_vsyscall
TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault test_syscall_vdso unwind_vdso \
test_FCMOV test_FCOMI test_FISTTP \
vdso_restorer
diff --git a/tools/testing/selftests/x86/test_vsyscall.c b/tools/testing/selftests/x86/test_vsyscall.c
new file mode 100644
index 000000000000..7a744fa7b786
--- /dev/null
+++ b/tools/testing/selftests/x86/test_vsyscall.c
@@ -0,0 +1,500 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#define _GNU_SOURCE
+
+#include <stdio.h>
+#include <sys/time.h>
+#include <time.h>
+#include <stdlib.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+#include <dlfcn.h>
+#include <string.h>
+#include <inttypes.h>
+#include <signal.h>
+#include <sys/ucontext.h>
+#include <errno.h>
+#include <err.h>
+#include <sched.h>
+#include <stdbool.h>
+#include <setjmp.h>
+
+#ifdef __x86_64__
+# define VSYS(x) (x)
+#else
+# define VSYS(x) 0
+#endif
+
+#ifndef SYS_getcpu
+# ifdef __x86_64__
+# define SYS_getcpu 309
+# else
+# define SYS_getcpu 318
+# endif
+#endif
+
+static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
+ int flags)
+{
+ struct sigaction sa;
+ memset(&sa, 0, sizeof(sa));
+ sa.sa_sigaction = handler;
+ sa.sa_flags = SA_SIGINFO | flags;
+ sigemptyset(&sa.sa_mask);
+ if (sigaction(sig, &sa, 0))
+ err(1, "sigaction");
+}
+
+/* vsyscalls and vDSO */
+bool should_read_vsyscall = false;
+
+typedef long (*gtod_t)(struct timeval *tv, struct timezone *tz);
+gtod_t vgtod = (gtod_t)VSYS(0xffffffffff600000);
+gtod_t vdso_gtod;
+
+typedef int (*vgettime_t)(clockid_t, struct timespec *);
+vgettime_t vdso_gettime;
+
+typedef long (*time_func_t)(time_t *t);
+time_func_t vtime = (time_func_t)VSYS(0xffffffffff600400);
+time_func_t vdso_time;
+
+typedef long (*getcpu_t)(unsigned *, unsigned *, void *);
+getcpu_t vgetcpu = (getcpu_t)VSYS(0xffffffffff600800);
+getcpu_t vdso_getcpu;
+
+static void init_vdso(void)
+{
+ void *vdso = dlopen("linux-vdso.so.1", RTLD_LAZY | RTLD_LOCAL | RTLD_NOLOAD);
+ if (!vdso)
+ vdso = dlopen("linux-gate.so.1", RTLD_LAZY | RTLD_LOCAL | RTLD_NOLOAD);
+ if (!vdso) {
+ printf("[WARN]\tfailed to find vDSO\n");
+ return;
+ }
+
+ vdso_gtod = (gtod_t)dlsym(vdso, "__vdso_gettimeofday");
+ if (!vdso_gtod)
+ printf("[WARN]\tfailed to find gettimeofday in vDSO\n");
+
+ vdso_gettime = (vgettime_t)dlsym(vdso, "__vdso_clock_gettime");
+ if (!vdso_gettime)
+ printf("[WARN]\tfailed to find clock_gettime in vDSO\n");
+
+ vdso_time = (time_func_t)dlsym(vdso, "__vdso_time");
+ if (!vdso_time)
+ printf("[WARN]\tfailed to find time in vDSO\n");
+
+ vdso_getcpu = (getcpu_t)dlsym(vdso, "__vdso_getcpu");
+ if (!vdso_getcpu) {
+ /* getcpu() was never wired up in the 32-bit vDSO. */
+ printf("[%s]\tfailed to find getcpu in vDSO\n",
+ sizeof(long) == 8 ? "WARN" : "NOTE");
+ }
+}
+
+static int init_vsys(void)
+{
+#ifdef __x86_64__
+ int nerrs = 0;
+ FILE *maps;
+ char line[128];
+ bool found = false;
+
+ maps = fopen("/proc/self/maps", "r");
+ if (!maps) {
+ printf("[WARN]\tCould not open /proc/self/maps -- assuming vsyscall is r-x\n");
+ should_read_vsyscall = true;
+ return 0;
+ }
+
+ while (fgets(line, sizeof(line), maps)) {
+ char r, x;
+ void *start, *end;
+ char name[128];
+ if (sscanf(line, "%p-%p %c-%cp %*x %*x:%*x %*u %s",
+ &start, &end, &r, &x, name) != 5)
+ continue;
+
+ if (strcmp(name, "[vsyscall]"))
+ continue;
+
+ printf("\tvsyscall map: %s", line);
+
+ if (start != (void *)0xffffffffff600000 ||
+ end != (void *)0xffffffffff601000) {
+ printf("[FAIL]\taddress range is nonsense\n");
+ nerrs++;
+ }
+
+ printf("\tvsyscall permissions are %c-%c\n", r, x);
+ should_read_vsyscall = (r == 'r');
+ if (x != 'x') {
+ vgtod = NULL;
+ vtime = NULL;
+ vgetcpu = NULL;
+ }
+
+ found = true;
+ break;
+ }
+
+ fclose(maps);
+
+ if (!found) {
+ printf("\tno vsyscall map in /proc/self/maps\n");
+ should_read_vsyscall = false;
+ vgtod = NULL;
+ vtime = NULL;
+ vgetcpu = NULL;
+ }
+
+ return nerrs;
+#else
+ return 0;
+#endif
+}
+
+/* syscalls */
+static inline long sys_gtod(struct timeval *tv, struct timezone *tz)
+{
+ return syscall(SYS_gettimeofday, tv, tz);
+}
+
+static inline int sys_clock_gettime(clockid_t id, struct timespec *ts)
+{
+ return syscall(SYS_clock_gettime, id, ts);
+}
+
+static inline long sys_time(time_t *t)
+{
+ return syscall(SYS_time, t);
+}
+
+static inline long sys_getcpu(unsigned * cpu, unsigned * node,
+ void* cache)
+{
+ return syscall(SYS_getcpu, cpu, node, cache);
+}
+
+static jmp_buf jmpbuf;
+
+static void sigsegv(int sig, siginfo_t *info, void *ctx_void)
+{
+ siglongjmp(jmpbuf, 1);
+}
+
+static double tv_diff(const struct timeval *a, const struct timeval *b)
+{
+ return (double)(a->tv_sec - b->tv_sec) +
+ (double)((int)a->tv_usec - (int)b->tv_usec) * 1e-6;
+}
+
+static int check_gtod(const struct timeval *tv_sys1,
+ const struct timeval *tv_sys2,
+ const struct timezone *tz_sys,
+ const char *which,
+ const struct timeval *tv_other,
+ const struct timezone *tz_other)
+{
+ int nerrs = 0;
+ double d1, d2;
+
+ if (tz_other && (tz_sys->tz_minuteswest != tz_other->tz_minuteswest || tz_sys->tz_dsttime != tz_other->tz_dsttime)) {
+ printf("[FAIL] %s tz mismatch\n", which);
+ nerrs++;
+ }
+
+ d1 = tv_diff(tv_other, tv_sys1);
+ d2 = tv_diff(tv_sys2, tv_other);
+ printf("\t%s time offsets: %lf %lf\n", which, d1, d2);
+
+ if (d1 < 0 || d2 < 0) {
+ printf("[FAIL]\t%s time was inconsistent with the syscall\n", which);
+ nerrs++;
+ } else {
+ printf("[OK]\t%s gettimeofday()'s timeval was okay\n", which);
+ }
+
+ return nerrs;
+}
+
+static int test_gtod(void)
+{
+ struct timeval tv_sys1, tv_sys2, tv_vdso, tv_vsys;
+ struct timezone tz_sys, tz_vdso, tz_vsys;
+ long ret_vdso = -1;
+ long ret_vsys = -1;
+ int nerrs = 0;
+
+ printf("[RUN]\ttest gettimeofday()\n");
+
+ if (sys_gtod(&tv_sys1, &tz_sys) != 0)
+ err(1, "syscall gettimeofday");
+ if (vdso_gtod)
+ ret_vdso = vdso_gtod(&tv_vdso, &tz_vdso);
+ if (vgtod)
+ ret_vsys = vgtod(&tv_vsys, &tz_vsys);
+ if (sys_gtod(&tv_sys2, &tz_sys) != 0)
+ err(1, "syscall gettimeofday");
+
+ if (vdso_gtod) {
+ if (ret_vdso == 0) {
+ nerrs += check_gtod(&tv_sys1, &tv_sys2, &tz_sys, "vDSO", &tv_vdso, &tz_vdso);
+ } else {
+ printf("[FAIL]\tvDSO gettimeofday() failed: %ld\n", ret_vdso);
+ nerrs++;
+ }
+ }
+
+ if (vgtod) {
+ if (ret_vsys == 0) {
+ nerrs += check_gtod(&tv_sys1, &tv_sys2, &tz_sys, "vsyscall", &tv_vsys, &tz_vsys);
+ } else {
+ printf("[FAIL]\tvsys gettimeofday() failed: %ld\n", ret_vsys);
+ nerrs++;
+ }
+ }
+
+ return nerrs;
+}
+
+static int test_time(void) {
+ int nerrs = 0;
+
+ printf("[RUN]\ttest time()\n");
+ long t_sys1, t_sys2, t_vdso = 0, t_vsys = 0;
+ long t2_sys1 = -1, t2_sys2 = -1, t2_vdso = -1, t2_vsys = -1;
+ t_sys1 = sys_time(&t2_sys1);
+ if (vdso_time)
+ t_vdso = vdso_time(&t2_vdso);
+ if (vtime)
+ t_vsys = vtime(&t2_vsys);
+ t_sys2 = sys_time(&t2_sys2);
+ if (t_sys1 < 0 || t_sys1 != t2_sys1 || t_sys2 < 0 || t_sys2 != t2_sys2) {
+ printf("[FAIL]\tsyscall failed (ret1:%ld output1:%ld ret2:%ld output2:%ld)\n", t_sys1, t2_sys1, t_sys2, t2_sys2);
+ nerrs++;
+ return nerrs;
+ }
+
+ if (vdso_time) {
+ if (t_vdso < 0 || t_vdso != t2_vdso) {
+ printf("[FAIL]\tvDSO failed (ret:%ld output:%ld)\n", t_vdso, t2_vdso);
+ nerrs++;
+ } else if (t_vdso < t_sys1 || t_vdso > t_sys2) {
+ printf("[FAIL]\tvDSO returned the wrong time (%ld %ld %ld)\n", t_sys1, t_vdso, t_sys2);
+ nerrs++;
+ } else {
+ printf("[OK]\tvDSO time() is okay\n");
+ }
+ }
+
+ if (vtime) {
+ if (t_vsys < 0 || t_vsys != t2_vsys) {
+ printf("[FAIL]\tvsyscall failed (ret:%ld output:%ld)\n", t_vsys, t2_vsys);
+ nerrs++;
+ } else if (t_vsys < t_sys1 || t_vsys > t_sys2) {
+ printf("[FAIL]\tvsyscall returned the wrong time (%ld %ld %ld)\n", t_sys1, t_vsys, t_sys2);
+ nerrs++;
+ } else {
+ printf("[OK]\tvsyscall time() is okay\n");
+ }
+ }
+
+ return nerrs;
+}
+
+static int test_getcpu(int cpu)
+{
+ int nerrs = 0;
+ long ret_sys, ret_vdso = -1, ret_vsys = -1;
+
+ printf("[RUN]\tgetcpu() on CPU %d\n", cpu);
+
+ cpu_set_t cpuset;
+ CPU_ZERO(&cpuset);
+ CPU_SET(cpu, &cpuset);
+ if (sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0) {
+ printf("[SKIP]\tfailed to force CPU %d\n", cpu);
+ return nerrs;
+ }
+
+ unsigned cpu_sys, cpu_vdso, cpu_vsys, node_sys, node_vdso, node_vsys;
+ unsigned node = 0;
+ bool have_node = false;
+ ret_sys = sys_getcpu(&cpu_sys, &node_sys, 0);
+ if (vdso_getcpu)
+ ret_vdso = vdso_getcpu(&cpu_vdso, &node_vdso, 0);
+ if (vgetcpu)
+ ret_vsys = vgetcpu(&cpu_vsys, &node_vsys, 0);
+
+ if (ret_sys == 0) {
+ if (cpu_sys != cpu) {
+ printf("[FAIL]\tsyscall reported CPU %hu but should be %d\n", cpu_sys, cpu);
+ nerrs++;
+ }
+
+ have_node = true;
+ node = node_sys;
+ }
+
+ if (vdso_getcpu) {
+ if (ret_vdso) {
+ printf("[FAIL]\tvDSO getcpu() failed\n");
+ nerrs++;
+ } else {
+ if (!have_node) {
+ have_node = true;
+ node = node_vdso;
+ }
+
+ if (cpu_vdso != cpu) {
+ printf("[FAIL]\tvDSO reported CPU %hu but should be %d\n", cpu_vdso, cpu);
+ nerrs++;
+ } else {
+ printf("[OK]\tvDSO reported correct CPU\n");
+ }
+
+ if (node_vdso != node) {
+ printf("[FAIL]\tvDSO reported node %hu but should be %hu\n", node_vdso, node);
+ nerrs++;
+ } else {
+ printf("[OK]\tvDSO reported correct node\n");
+ }
+ }
+ }
+
+ if (vgetcpu) {
+ if (ret_vsys) {
+ printf("[FAIL]\tvsyscall getcpu() failed\n");
+ nerrs++;
+ } else {
+ if (!have_node) {
+ have_node = true;
+ node = node_vsys;
+ }
+
+ if (cpu_vsys != cpu) {
+ printf("[FAIL]\tvsyscall reported CPU %hu but should be %d\n", cpu_vsys, cpu);
+ nerrs++;
+ } else {
+ printf("[OK]\tvsyscall reported correct CPU\n");
+ }
+
+ if (node_vsys != node) {
+ printf("[FAIL]\tvsyscall reported node %hu but should be %hu\n", node_vsys, node);
+ nerrs++;
+ } else {
+ printf("[OK]\tvsyscall reported correct node\n");
+ }
+ }
+ }
+
+ return nerrs;
+}
+
+static int test_vsys_r(void)
+{
+#ifdef __x86_64__
+ printf("[RUN]\tChecking read access to the vsyscall page\n");
+ bool can_read;
+ if (sigsetjmp(jmpbuf, 1) == 0) {
+ *(volatile int *)0xffffffffff600000;
+ can_read = true;
+ } else {
+ can_read = false;
+ }
+
+ if (can_read && !should_read_vsyscall) {
+ printf("[FAIL]\tWe have read access, but we shouldn't\n");
+ return 1;
+ } else if (!can_read && should_read_vsyscall) {
+ printf("[FAIL]\tWe don't have read access, but we should\n");
+ return 1;
+ } else {
+ printf("[OK]\tgot expected result\n");
+ }
+#endif
+
+ return 0;
+}
+
+
+#ifdef __x86_64__
+#define X86_EFLAGS_TF (1UL << 8)
+static volatile sig_atomic_t num_vsyscall_traps;
+
+static unsigned long get_eflags(void)
+{
+ unsigned long eflags;
+ asm volatile ("pushfq\n\tpopq %0" : "=rm" (eflags));
+ return eflags;
+}
+
+static void set_eflags(unsigned long eflags)
+{
+ asm volatile ("pushq %0\n\tpopfq" : : "rm" (eflags) : "flags");
+}
+
+static void sigtrap(int sig, siginfo_t *info, void *ctx_void)
+{
+ ucontext_t *ctx = (ucontext_t *)ctx_void;
+ unsigned long ip = ctx->uc_mcontext.gregs[REG_RIP];
+
+ if (((ip ^ 0xffffffffff600000UL) & ~0xfffUL) == 0)
+ num_vsyscall_traps++;
+}
+
+static int test_native_vsyscall(void)
+{
+ time_t tmp;
+ bool is_native;
+
+ if (!vtime)
+ return 0;
+
+ printf("[RUN]\tchecking for native vsyscall\n");
+ sethandler(SIGTRAP, sigtrap, 0);
+ set_eflags(get_eflags() | X86_EFLAGS_TF);
+ vtime(&tmp);
+ set_eflags(get_eflags() & ~X86_EFLAGS_TF);
+
+ /*
+ * If vsyscalls are emulated, we expect a single trap in the
+ * vsyscall page -- the call instruction will trap with RIP
+ * pointing to the entry point before emulation takes over.
+ * In native mode, we expect two traps, since whatever code
+ * the vsyscall page contains will be more than just a ret
+ * instruction.
+ */
+ is_native = (num_vsyscall_traps > 1);
+
+ printf("\tvsyscalls are %s (%d instructions in vsyscall page)\n",
+ (is_native ? "native" : "emulated"),
+ (int)num_vsyscall_traps);
+
+ return 0;
+}
+#endif
+
+int main(int argc, char **argv)
+{
+ int nerrs = 0;
+
+ init_vdso();
+ nerrs += init_vsys();
+
+ nerrs += test_gtod();
+ nerrs += test_time();
+ nerrs += test_getcpu(0);
+ nerrs += test_getcpu(1);
+
+ sethandler(SIGSEGV, sigsegv, 0);
+ nerrs += test_vsys_r();
+
+#ifdef __x86_64__
+ nerrs += test_native_vsyscall();
+#endif
+
+ return nerrs ? 1 : 0;
+}
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.