diff options
Diffstat (limited to 'tools')
26 files changed, 3454 insertions, 567 deletions
diff --git a/tools/hv/bondvf.sh b/tools/hv/bondvf.sh deleted file mode 100755 index 89b25068cd98..000000000000 --- a/tools/hv/bondvf.sh +++ /dev/null @@ -1,232 +0,0 @@ -#!/bin/bash - -# This example script creates bonding network devices based on synthetic NIC -# (the virtual network adapter usually provided by Hyper-V) and the matching -# VF NIC (SRIOV virtual function). So the synthetic NIC and VF NIC can -# function as one network device, and fail over to the synthetic NIC if VF is -# down. -# -# Usage: -# - After configured vSwitch and vNIC with SRIOV, start Linux virtual -# machine (VM) -# - Run this scripts on the VM. It will create configuration files in -# distro specific directory. -# - Reboot the VM, so that the bonding config are enabled. -# -# The config files are DHCP by default. You may edit them if you need to change -# to Static IP or change other settings. -# - -sysdir=/sys/class/net -netvsc_cls={f8615163-df3e-46c5-913f-f2d2f965ed0e} -bondcnt=0 - -# Detect Distro -if [ -f /etc/redhat-release ]; -then - cfgdir=/etc/sysconfig/network-scripts - distro=redhat -elif grep -q 'Ubuntu' /etc/issue -then - cfgdir=/etc/network - distro=ubuntu -elif grep -q 'SUSE' /etc/issue -then - cfgdir=/etc/sysconfig/network - distro=suse -else - echo "Unsupported Distro" - exit 1 -fi - -echo Detected Distro: $distro, or compatible - -# Get a list of ethernet names -list_eth=(`cd $sysdir && ls -d */ | cut -d/ -f1 | grep -v bond`) -eth_cnt=${#list_eth[@]} - -echo List of net devices: - -# Get the MAC addresses -for (( i=0; i < $eth_cnt; i++ )) -do - list_mac[$i]=`cat $sysdir/${list_eth[$i]}/address` - echo ${list_eth[$i]}, ${list_mac[$i]} -done - -# Find NIC with matching MAC -for (( i=0; i < $eth_cnt-1; i++ )) -do - for (( j=i+1; j < $eth_cnt; j++ )) - do - if [ "${list_mac[$i]}" = "${list_mac[$j]}" ] - then - list_match[$i]=${list_eth[$j]} - break - fi - done -done - -function create_eth_cfg_redhat { - local fn=$cfgdir/ifcfg-$1 - - rm -f $fn - echo DEVICE=$1 >>$fn - echo TYPE=Ethernet >>$fn - echo BOOTPROTO=none >>$fn - echo UUID=`uuidgen` >>$fn - echo ONBOOT=yes >>$fn - echo PEERDNS=yes >>$fn - echo IPV6INIT=yes >>$fn - echo MASTER=$2 >>$fn - echo SLAVE=yes >>$fn -} - -function create_eth_cfg_pri_redhat { - create_eth_cfg_redhat $1 $2 -} - -function create_bond_cfg_redhat { - local fn=$cfgdir/ifcfg-$1 - - rm -f $fn - echo DEVICE=$1 >>$fn - echo TYPE=Bond >>$fn - echo BOOTPROTO=dhcp >>$fn - echo UUID=`uuidgen` >>$fn - echo ONBOOT=yes >>$fn - echo PEERDNS=yes >>$fn - echo IPV6INIT=yes >>$fn - echo BONDING_MASTER=yes >>$fn - echo BONDING_OPTS=\"mode=active-backup miimon=100 primary=$2\" >>$fn -} - -function del_eth_cfg_ubuntu { - local mainfn=$cfgdir/interfaces - local fnlist=( $mainfn ) - - local dirlist=(`awk '/^[ \t]*source/{print $2}' $mainfn`) - - local i - for i in "${dirlist[@]}" - do - fnlist+=(`ls $i 2>/dev/null`) - done - - local tmpfl=$(mktemp) - - local nic_start='^[ \t]*(auto|iface|mapping|allow-.*)[ \t]+'$1 - local nic_end='^[ \t]*(auto|iface|mapping|allow-.*|source)' - - local fn - for fn in "${fnlist[@]}" - do - awk "/$nic_end/{x=0} x{next} /$nic_start/{x=1;next} 1" \ - $fn >$tmpfl - - cp $tmpfl $fn - done - - rm $tmpfl -} - -function create_eth_cfg_ubuntu { - local fn=$cfgdir/interfaces - - del_eth_cfg_ubuntu $1 - echo $'\n'auto $1 >>$fn - echo iface $1 inet manual >>$fn - echo bond-master $2 >>$fn -} - -function create_eth_cfg_pri_ubuntu { - local fn=$cfgdir/interfaces - - del_eth_cfg_ubuntu $1 - echo $'\n'allow-hotplug $1 >>$fn - echo iface $1 inet manual >>$fn - echo bond-master $2 >>$fn - echo bond-primary $1 >>$fn -} - -function create_bond_cfg_ubuntu { - local fn=$cfgdir/interfaces - - del_eth_cfg_ubuntu $1 - - echo $'\n'auto $1 >>$fn - echo iface $1 inet dhcp >>$fn - echo bond-mode active-backup >>$fn - echo bond-miimon 100 >>$fn - echo bond-slaves none >>$fn -} - -function create_eth_cfg_suse { - local fn=$cfgdir/ifcfg-$1 - - rm -f $fn - echo BOOTPROTO=none >>$fn - echo STARTMODE=auto >>$fn -} - -function create_eth_cfg_pri_suse { - local fn=$cfgdir/ifcfg-$1 - - rm -f $fn - echo BOOTPROTO=none >>$fn - echo STARTMODE=hotplug >>$fn -} - -function create_bond_cfg_suse { - local fn=$cfgdir/ifcfg-$1 - - rm -f $fn - echo BOOTPROTO=dhcp >>$fn - echo STARTMODE=auto >>$fn - echo BONDING_MASTER=yes >>$fn - echo BONDING_SLAVE_0=$2 >>$fn - echo BONDING_SLAVE_1=$3 >>$fn - echo BONDING_MODULE_OPTS=\'mode=active-backup miimon=100 primary=$2\' >>$fn -} - -function create_bond { - local bondname=bond$bondcnt - local primary - local secondary - - local class_id1=`cat $sysdir/$1/device/class_id 2>/dev/null` - local class_id2=`cat $sysdir/$2/device/class_id 2>/dev/null` - - if [ "$class_id1" = "$netvsc_cls" ] - then - primary=$2 - secondary=$1 - elif [ "$class_id2" = "$netvsc_cls" ] - then - primary=$1 - secondary=$2 - else - return 0 - fi - - echo $'\nBond name:' $bondname - - echo configuring $primary - create_eth_cfg_pri_$distro $primary $bondname - - echo configuring $secondary - create_eth_cfg_$distro $secondary $bondname - - echo creating: $bondname with primary slave: $primary - create_bond_cfg_$distro $bondname $primary $secondary - - let bondcnt=bondcnt+1 -} - -for (( i=0; i < $eth_cnt-1; i++ )) -do - if [ -n "${list_match[$i]}" ] - then - create_bond ${list_eth[$i]} ${list_match[$i]} - fi -done diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index e99e3e6f8b37..461811e57140 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -30,9 +30,14 @@ #define BPF_FROM_LE BPF_TO_LE #define BPF_FROM_BE BPF_TO_BE +/* jmp encodings */ #define BPF_JNE 0x50 /* jump != */ +#define BPF_JLT 0xa0 /* LT is unsigned, '<' */ +#define BPF_JLE 0xb0 /* LE is unsigned, '<=' */ #define BPF_JSGT 0x60 /* SGT is signed '>', GT in x86 */ #define BPF_JSGE 0x70 /* SGE is signed '>=', GE in x86 */ +#define BPF_JSLT 0xc0 /* SLT is signed, '<' */ +#define BPF_JSLE 0xd0 /* SLE is signed, '<=' */ #define BPF_CALL 0x80 /* function call */ #define BPF_EXIT 0x90 /* function return */ @@ -104,6 +109,8 @@ enum bpf_map_type { BPF_MAP_TYPE_LPM_TRIE, BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_HASH_OF_MAPS, + BPF_MAP_TYPE_DEVMAP, + BPF_MAP_TYPE_SOCKMAP, }; enum bpf_prog_type { @@ -121,6 +128,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_LWT_OUT, BPF_PROG_TYPE_LWT_XMIT, BPF_PROG_TYPE_SOCK_OPS, + BPF_PROG_TYPE_SK_SKB, }; enum bpf_attach_type { @@ -128,11 +136,19 @@ enum bpf_attach_type { BPF_CGROUP_INET_EGRESS, BPF_CGROUP_INET_SOCK_CREATE, BPF_CGROUP_SOCK_OPS, + BPF_SK_SKB_STREAM_PARSER, + BPF_SK_SKB_STREAM_VERDICT, __MAX_BPF_ATTACH_TYPE }; #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE +enum bpf_sockmap_flags { + BPF_SOCKMAP_UNSPEC, + BPF_SOCKMAP_STRPARSER, + __MAX_BPF_SOCKMAP_FLAG +}; + /* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command * to the given target_fd cgroup the descendent cgroup will be able to * override effective bpf program that was inherited from this cgroup @@ -153,6 +169,7 @@ enum bpf_attach_type { #define BPF_NOEXIST 1 /* create new element if it didn't exist */ #define BPF_EXIST 2 /* update existing element */ +/* flags for BPF_MAP_CREATE command */ #define BPF_F_NO_PREALLOC (1U << 0) /* Instead of having one common LRU list in the * BPF_MAP_TYPE_LRU_[PERCPU_]HASH map, use a percpu LRU list @@ -161,6 +178,8 @@ enum bpf_attach_type { * across different LRU lists. */ #define BPF_F_NO_COMMON_LRU (1U << 1) +/* Specify numa node during map creation */ +#define BPF_F_NUMA_NODE (1U << 2) union bpf_attr { struct { /* anonymous struct used by BPF_MAP_CREATE command */ @@ -168,8 +187,13 @@ union bpf_attr { __u32 key_size; /* size of key in bytes */ __u32 value_size; /* size of value in bytes */ __u32 max_entries; /* max number of entries in a map */ - __u32 map_flags; /* prealloc or not */ + __u32 map_flags; /* BPF_MAP_CREATE related + * flags defined above. + */ __u32 inner_map_fd; /* fd pointing to the inner map */ + __u32 numa_node; /* numa node (effective only if + * BPF_F_NUMA_NODE is set). + */ }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -539,6 +563,20 @@ union bpf_attr { * @mode: operation mode (enum bpf_adj_room_mode) * @flags: reserved for future use * Return: 0 on success or negative error code + * + * int bpf_sk_redirect_map(map, key, flags) + * Redirect skb to a sock in map using key as a lookup key for the + * sock in map. + * @map: pointer to sockmap + * @key: key to lookup sock in map + * @flags: reserved for future use + * Return: SK_REDIRECT + * + * int bpf_sock_map_update(skops, map, key, flags) + * @skops: pointer to bpf_sock_ops + * @map: pointer to sockmap to update + * @key: key to insert/update sock in map + * @flags: same flags as map update elem */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -591,7 +629,10 @@ union bpf_attr { FN(get_socket_uid), \ FN(set_hash), \ FN(setsockopt), \ - FN(skb_adjust_room), + FN(skb_adjust_room), \ + FN(redirect_map), \ + FN(sk_redirect_map), \ + FN(sock_map_update), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -668,6 +709,15 @@ struct __sk_buff { __u32 data; __u32 data_end; __u32 napi_id; + + /* accessed by BPF_PROG_TYPE_sk_skb types */ + __u32 family; + __u32 remote_ip4; /* Stored in network byte order */ + __u32 local_ip4; /* Stored in network byte order */ + __u32 remote_ip6[4]; /* Stored in network byte order */ + __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 */ }; struct bpf_tunnel_key { @@ -727,6 +777,12 @@ struct xdp_md { __u32 data_end; }; +enum sk_action { + SK_ABORTED = 0, + SK_DROP, + SK_REDIRECT, +}; + #define BPF_TAG_SIZE 8 struct bpf_prog_info { diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index 4ed0257dc1f3..d2441db34740 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -189,6 +189,10 @@ install_lib: all_cmd $(call QUIET_INSTALL, $(LIB_FILE)) \ $(call do_install,$(LIB_FILE),$(libdir_SQ)) +install_headers: + $(call QUIET_INSTALL, headers) \ + $(call do_install,bpf.h,$(prefix)/include/bpf,644) + install: install_lib ### Cleaning rules diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index e5bbb090bf88..1d6907d379c9 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -57,8 +57,9 @@ static inline int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr, return syscall(__NR_bpf, cmd, attr, size); } -int bpf_create_map(enum bpf_map_type map_type, int key_size, - int value_size, int max_entries, __u32 map_flags) +int bpf_create_map_node(enum bpf_map_type map_type, int key_size, + int value_size, int max_entries, __u32 map_flags, + int node) { union bpf_attr attr; @@ -69,12 +70,24 @@ int bpf_create_map(enum bpf_map_type map_type, int key_size, attr.value_size = value_size; attr.max_entries = max_entries; attr.map_flags = map_flags; + if (node >= 0) { + attr.map_flags |= BPF_F_NUMA_NODE; + attr.numa_node = node; + } return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr)); } -int bpf_create_map_in_map(enum bpf_map_type map_type, int key_size, - int inner_map_fd, int max_entries, __u32 map_flags) +int bpf_create_map(enum bpf_map_type map_type, int key_size, + int value_size, int max_entries, __u32 map_flags) +{ + return bpf_create_map_node(map_type, key_size, value_size, + max_entries, map_flags, -1); +} + +int bpf_create_map_in_map_node(enum bpf_map_type map_type, int key_size, + int inner_map_fd, int max_entries, + __u32 map_flags, int node) { union bpf_attr attr; @@ -86,10 +99,21 @@ int bpf_create_map_in_map(enum bpf_map_type map_type, int key_size, attr.inner_map_fd = inner_map_fd; attr.max_entries = max_entries; attr.map_flags = map_flags; + if (node >= 0) { + attr.map_flags |= BPF_F_NUMA_NODE; + attr.numa_node = node; + } return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr)); } +int bpf_create_map_in_map(enum bpf_map_type map_type, int key_size, + int inner_map_fd, int max_entries, __u32 map_flags) +{ + return bpf_create_map_in_map_node(map_type, key_size, inner_map_fd, + max_entries, map_flags, -1); +} + int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, size_t insns_cnt, const char *license, __u32 kern_version, char *log_buf, size_t log_buf_sz) diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 418c86e69bcb..b8ea5843c39e 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -24,8 +24,14 @@ #include <linux/bpf.h> #include <stddef.h> +int bpf_create_map_node(enum bpf_map_type map_type, int key_size, + int value_size, int max_entries, __u32 map_flags, + int node); int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size, int max_entries, __u32 map_flags); +int bpf_create_map_in_map_node(enum bpf_map_type map_type, int key_size, + int inner_map_fd, int max_entries, + __u32 map_flags, int node); int bpf_create_map_in_map(enum bpf_map_type map_type, int key_size, int inner_map_fd, int max_entries, __u32 map_flags); diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 8c67a90dbd82..35f6dfcdc565 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -1745,3 +1745,32 @@ long libbpf_get_error(const void *ptr) return PTR_ERR(ptr); return 0; } + +int bpf_prog_load(const char *file, enum bpf_prog_type type, + struct bpf_object **pobj, int *prog_fd) +{ + struct bpf_program *prog; + struct bpf_object *obj; + int err; + + obj = bpf_object__open(file); + if (IS_ERR(obj)) + return -ENOENT; + + prog = bpf_program__next(NULL, obj); + if (!prog) { + bpf_object__close(obj); + return -ENOENT; + } + + bpf_program__set_type(prog, type); + err = bpf_object__load(obj); + if (err) { + bpf_object__close(obj); + return -EINVAL; + } + + *pobj = obj; + *prog_fd = bpf_program__fd(prog); + return 0; +} diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 32c7252f734e..7959086eb9c9 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -243,4 +243,6 @@ int bpf_map__pin(struct bpf_map *map, const char *path); long libbpf_get_error(const void *ptr); +int bpf_prog_load(const char *file, enum bpf_prog_type type, + struct bpf_object **pobj, int *prog_fd); #endif diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 153c3a181a4c..f4b23d697448 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -15,9 +15,9 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test test_align 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_pkt_md_access.o test_xdp_redirect.o sockmap_parse_prog.o sockmap_verdict_prog.o -TEST_PROGS := test_kmod.sh +TEST_PROGS := test_kmod.sh test_xdp_redirect.sh include ../lib.mk diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index d50ac342dc92..36fb9161b34a 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -38,6 +38,8 @@ static int (*bpf_clone_redirect)(void *ctx, int ifindex, int flags) = (void *) BPF_FUNC_clone_redirect; static int (*bpf_redirect)(int ifindex, int flags) = (void *) BPF_FUNC_redirect; +static int (*bpf_redirect_map)(void *map, int key, int flags) = + (void *) BPF_FUNC_redirect_map; static int (*bpf_perf_event_output)(void *ctx, void *map, unsigned long long flags, void *data, int size) = @@ -63,6 +65,12 @@ static int (*bpf_xdp_adjust_head)(void *ctx, int offset) = static int (*bpf_setsockopt)(void *ctx, int level, int optname, void *optval, int optlen) = (void *) BPF_FUNC_setsockopt; +static int (*bpf_sk_redirect_map)(void *map, int key, int flags) = + (void *) BPF_FUNC_sk_redirect_map; +static int (*bpf_sock_map_update)(void *map, void *key, void *value, + unsigned long long flags) = + (void *) BPF_FUNC_sock_map_update; + /* llvm builtin functions that eBPF C program may use to * emit BPF_LD_ABS and BPF_LD_IND instructions @@ -85,6 +93,7 @@ struct bpf_map_def { unsigned int max_entries; unsigned int map_flags; unsigned int inner_map_idx; + unsigned int numa_node; }; static int (*bpf_skb_load_bytes)(void *ctx, int off, void *to, int len) = diff --git a/tools/testing/selftests/bpf/sockmap_parse_prog.c b/tools/testing/selftests/bpf/sockmap_parse_prog.c new file mode 100644 index 000000000000..fae3b96c3aa4 --- /dev/null +++ b/tools/testing/selftests/bpf/sockmap_parse_prog.c @@ -0,0 +1,38 @@ +#include <linux/bpf.h> +#include "bpf_helpers.h" +#include "bpf_util.h" +#include "bpf_endian.h" + +int _version SEC("version") = 1; + +#define bpf_printk(fmt, ...) \ +({ \ + char ____fmt[] = fmt; \ + bpf_trace_printk(____fmt, sizeof(____fmt), \ + ##__VA_ARGS__); \ +}) + +SEC("sk_skb1") +int bpf_prog1(struct __sk_buff *skb) +{ + void *data_end = (void *)(long) skb->data_end; + void *data = (void *)(long) skb->data; + __u32 lport = skb->local_port; + __u32 rport = skb->remote_port; + __u8 *d = data; + + if (data + 10 > data_end) + return skb->len; + + /* This write/read is a bit pointless but tests the verifier and + * strparser handler for read/write pkt data and access into sk + * fields. + */ + d[7] = 1; + + bpf_printk("parse: data[0] = (%u): local_port %i remote %i\n", + d[0], lport, bpf_ntohl(rport)); + return skb->len; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/sockmap_verdict_prog.c b/tools/testing/selftests/bpf/sockmap_verdict_prog.c new file mode 100644 index 000000000000..9b99bd10807d --- /dev/null +++ b/tools/testing/selftests/bpf/sockmap_verdict_prog.c @@ -0,0 +1,68 @@ +#include <linux/bpf.h> +#include "bpf_helpers.h" +#include "bpf_util.h" +#include "bpf_endian.h" + +int _version SEC("version") = 1; + +#define bpf_printk(fmt, ...) \ +({ \ + char ____fmt[] = fmt; \ + bpf_trace_printk(____fmt, sizeof(____fmt), \ + ##__VA_ARGS__); \ +}) + +struct bpf_map_def SEC("maps") sock_map_rx = { + .type = BPF_MAP_TYPE_SOCKMAP, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 20, +}; + +struct bpf_map_def SEC("maps") sock_map_tx = { + .type = BPF_MAP_TYPE_SOCKMAP, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 20, +}; + +struct bpf_map_def SEC("maps") sock_map_break = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 20, +}; + +SEC("sk_skb2") +int bpf_prog2(struct __sk_buff *skb) +{ + void *data_end = (void *)(long) skb->data_end; + void *data = (void *)(long) skb->data; + __u32 lport = skb->local_port; + __u32 rport = skb->remote_port; + __u8 *d = data; + __u8 sk, map; + + if (data + 8 > data_end) + return SK_DROP; + + map = d[0]; + sk = d[1]; + + d[0] = 0xd; + d[1] = 0xe; + d[2] = 0xa; + d[3] = 0xd; + d[4] = 0xb; + d[5] = 0xe; + d[6] = 0xe; + d[7] = 0xf; + + bpf_printk("verdict: data[0] = redir(%u:%u)\n", map, sk); + + if (!map) + return bpf_sk_redirect_map(&sock_map_rx, sk, 0); + return bpf_sk_redirect_map(&sock_map_tx, sk, 0); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_align.c b/tools/testing/selftests/bpf/test_align.c index 29793694cbc7..8591c89c0828 100644 --- a/tools/testing/selftests/bpf/test_align.c +++ b/tools/testing/selftests/bpf/test_align.c @@ -27,6 +27,11 @@ #define MAX_INSNS 512 #define MAX_MATCHES 16 +struct bpf_reg_match { + unsigned int line; + const char *match; +}; + struct bpf_align_test { const char *descr; struct bpf_insn insns[MAX_INSNS]; @@ -36,10 +41,14 @@ struct bpf_align_test { REJECT } result; enum bpf_prog_type prog_type; - const char *matches[MAX_MATCHES]; + /* Matches must be in order of increasing line */ + struct bpf_reg_match matches[MAX_MATCHES]; }; static struct bpf_align_test tests[] = { + /* Four tests of known constants. These aren't staggeringly + * interesting since we track exact values now. + */ { .descr = "mov", .insns = { @@ -53,11 +62,13 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - "1: R1=ctx R3=imm2,min_value=2,max_value=2,min_align=2 R10=fp", - "2: R1=ctx R3=imm4,min_value=4,max_value=4,min_align=4 R10=fp", - "3: R1=ctx R3=imm8,min_value=8,max_value=8,min_align=8 R10=fp", - "4: R1=ctx R3=imm16,min_value=16,max_value=16,min_align=16 R10=fp", - "5: R1=ctx R3=imm32,min_value=32,max_value=32,min_align=32 R10=fp", + {1, "R1=ctx(id=0,off=0,imm=0)"}, + {1, "R10=fp0"}, + {1, "R3=inv2"}, + {2, "R3=inv4"}, + {3, "R3=inv8"}, + {4, "R3=inv16"}, + {5, "R3=inv32"}, }, }, { @@ -79,17 +90,19 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - "1: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R10=fp", - "2: R1=ctx R3=imm2,min_value=2,max_value=2,min_align=2 R10=fp", - "3: R1=ctx R3=imm4,min_value=4,max_value=4,min_align=4 R10=fp", - "4: R1=ctx R3=imm8,min_value=8,max_value=8,min_align=8 R10=fp", - "5: R1=ctx R3=imm16,min_value=16,max_value=16,min_align=16 R10=fp", - "6: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R10=fp", - "7: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm32,min_value=32,max_value=32,min_align=32 R10=fp", - "8: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm16,min_value=16,max_value=16,min_align=16 R10=fp", - "9: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm8,min_value=8,max_value=8,min_align=8 R10=fp", - "10: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm4,min_value=4,max_value=4,min_align=4 R10=fp", - "11: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm2,min_value=2,max_value=2,min_align=2 R10=fp", + {1, "R1=ctx(id=0,off=0,imm=0)"}, + {1, "R10=fp0"}, + {1, "R3=inv1"}, + {2, "R3=inv2"}, + {3, "R3=inv4"}, + {4, "R3=inv8"}, + {5, "R3=inv16"}, + {6, "R3=inv1"}, + {7, "R4=inv32"}, + {8, "R4=inv16"}, + {9, "R4=inv8"}, + {10, "R4=inv4"}, + {11, "R4=inv2"}, }, }, { @@ -106,12 +119,14 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - "1: R1=ctx R3=imm4,min_value=4,max_value=4,min_align=4 R10=fp", - "2: R1=ctx R3=imm8,min_value=8,max_value=8,min_align=4 R10=fp", - "3: R1=ctx R3=imm10,min_value=10,max_value=10,min_align=2 R10=fp", - "4: R1=ctx R3=imm10,min_value=10,max_value=10,min_align=2 R4=imm8,min_value=8,max_value=8,min_align=8 R10=fp", - "5: R1=ctx R3=imm10,min_value=10,max_value=10,min_align=2 R4=imm12,min_value=12,max_value=12,min_align=4 R10=fp", - "6: R1=ctx R3=imm10,min_value=10,max_value=10,min_align=2 R4=imm14,min_value=14,max_value=14,min_align=2 R10=fp", + {1, "R1=ctx(id=0,off=0,imm=0)"}, + {1, "R10=fp0"}, + {1, "R3=inv4"}, + {2, "R3=inv8"}, + {3, "R3=inv10"}, + {4, "R4=inv8"}, + {5, "R4=inv12"}, + {6, "R4=inv14"}, }, }, { @@ -126,13 +141,16 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - "1: R1=ctx R3=imm7,min_value=7,max_value=7,min_align=1 R10=fp", - "2: R1=ctx R3=imm7,min_value=7,max_value=7,min_align=1 R10=fp", - "3: R1=ctx R3=imm14,min_value=14,max_value=14,min_align=2 R10=fp", - "4: R1=ctx R3=imm56,min_value=56,max_value=56,min_align=4 R10=fp", + {1, "R1=ctx(id=0,off=0,imm=0)"}, + {1, "R10=fp0"}, + {1, "R3=inv7"}, + {2, "R3=inv7"}, + {3, "R3=inv14"}, + {4, "R3=inv56"}, }, }, + /* Tests using unknown values */ #define PREP_PKT_POINTERS \ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, \ offsetof(struct __sk_buff, data)), \ @@ -166,17 +184,19 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - "7: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R10=fp", - "8: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv55,min_align=2 R10=fp", - "9: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv54,min_align=4 R10=fp", - "10: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv53,min_align=8 R10=fp", - "11: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv52,min_align=16 R10=fp", - "18: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv56 R10=fp", - "19: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv51,min_align=32 R10=fp", - "20: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv52,min_align=16 R10=fp", - "21: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv53,min_align=8 R10=fp", - "22: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv54,min_align=4 R10=fp", - "23: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv55,min_align=2 R10=fp", + {7, "R0=pkt(id=0,off=8,r=8,imm=0)"}, + {7, "R3=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, + {8, "R3=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"}, + {9, "R3=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {10, "R3=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"}, + {11, "R3=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"}, + {18, "R3=pkt_end(id=0,off=0,imm=0)"}, + {18, "R4=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, + {19, "R4=inv(id=0,umax_value=8160,var_off=(0x0; 0x1fe0))"}, + {20, "R4=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"}, + {21, "R4=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"}, + {22, "R4=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {23, "R4=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"}, }, }, { @@ -197,16 +217,16 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - "7: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R10=fp", - "8: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv56 R10=fp", - "9: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv55,min_align=1 R10=fp", - "10: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv56 R10=fp", - "11: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv54,min_align=2 R10=fp", - "12: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv56 R10=fp", - "13: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv53,min_align=4 R10=fp", - "14: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv56 R10=fp", - "15: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv52,min_align=8 R10=fp", - "16: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv50,min_align=8 R10=fp" + {7, "R3=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, + {8, "R4=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, + {9, "R4=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, + {10, "R4=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, + {11, "R4=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"}, + {12, "R4=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, + {13, "R4=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {14, "R4=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, + {15, "R4=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"}, + {16, "R4=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"}, }, }, { @@ -237,12 +257,14 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - "4: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=0) R3=pkt_end R5=pkt(id=0,off=0,r=0) R10=fp", - "5: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=0) R3=pkt_end R5=pkt(id=0,off=14,r=0) R10=fp", - "6: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=0) R3=pkt_end R4=pkt(id=0,off=14,r=0) R5=pkt(id=0,off=14,r=0) R10=fp", - "10: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=18) R3=pkt_end R4=inv56 R5=pkt(id=0,off=14,r=18) R10=fp", - "14: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=18) R3=pkt_end R4=inv48 R5=pkt(id=0,off=14,r=18) R10=fp", - "15: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=18) R3=pkt_end R4=inv48 R5=pkt(id=0,off=14,r=18) R10=fp", + {4, "R5=pkt(id=0,off=0,r=0,imm=0)"}, + {5, "R5=pkt(id=0,off=14,r=0,imm=0)"}, + {6, "R4=pkt(id=0,off=14,r=0,imm=0)"}, + {10, "R2=pkt(id=0,off=0,r=18,imm=0)"}, + {10, "R5=pkt(id=0,off=14,r=18,imm=0)"}, + {10, "R4=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, + {14, "R4=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff))"}, + {15, "R4=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff))"}, }, }, { @@ -297,62 +319,286 @@ static struct bpf_align_test tests[] = { /* Calculated offset in R6 has unknown value, but known * alignment of 4. */ - "8: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R6=inv54,min_align=4 R10=fp", - - /* Offset is added to packet pointer R5, resulting in known - * auxiliary alignment and offset. + {8, "R2=pkt(id=0,off=0,r=8,imm=0)"}, + {8, "R6=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + /* Offset is added to packet pointer R5, resulting in + * known fixed offset, and variable offset from R6. */ - "11: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R5=pkt(id=1,off=0,r=0),aux_off=14,aux_off_align=4 R6=inv54,min_align=4 R10=fp", - + {11, "R5=pkt(id=1,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* At the time the word size load is performed from R5, * it's total offset is NET_IP_ALIGN + reg->off (0) + * reg->aux_off (14) which is 16. Then the variable * offset is considered using reg->aux_off_align which * is 4 and meets the load's requirements. */ - "15: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=pkt(id=1,off=4,r=4),aux_off=14,aux_off_align=4 R5=pkt(id=1,off=0,r=4),aux_off=14,aux_off_align=4 R6=inv54,min_align=4 R10=fp", - - + {15, "R4=pkt(id=1,off=18,r=18,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {15, "R5=pkt(id=1,off=14,r=18,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* Variable offset is added to R5 packet pointer, * resulting in auxiliary alignment of 4. */ - "18: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off=14,aux_off_align=4 R5=pkt(id=2,off=0,r=0),aux_off_align=4 R6=inv54,min_align=4 R10=fp", - + {18, "R5=pkt(id=2,off=0,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* Constant offset is added to R5, resulting in * reg->off of 14. */ - "19: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off=14,aux_off_align=4 R5=pkt(id=2,off=14,r=0),aux_off_align=4 R6=inv54,min_align=4 R10=fp", - + {19, "R5=pkt(id=2,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* At the time the word size load is performed from R5, - * it's total offset is NET_IP_ALIGN + reg->off (14) which - * is 16. Then the variable offset is considered using - * reg->aux_off_align which is 4 and meets the load's - * requirements. + * its total fixed offset is NET_IP_ALIGN + reg->off + * (14) which is 16. Then the variable offset is 4-byte + * aligned, so the total offset is 4-byte aligned and + * meets the load's requirements. */ - "23: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=pkt(id=2,off=18,r=18),aux_off_align=4 R5=pkt(id=2,off=14,r=18),aux_off_align=4 R6=inv54,min_align=4 R10=fp", - + {23, "R4=pkt(id=2,off=18,r=18,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {23, "R5=pkt(id=2,off=14,r=18,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* Constant offset is added to R5 packet pointer, * resulting in reg->off value of 14. */ - "26: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off_align=4 R5=pkt(id=0,off=14,r=8) R6=inv54,min_align=4 R10=fp", - /* Variable offset is added to R5, resulting in an - * auxiliary offset of 14, and an auxiliary alignment of 4. + {26, "R5=pkt(id=0,off=14,r=8"}, + /* Variable offset is added to R5, resulting in a + * variable offset of (4n). */ - "27: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off_align=4 R5=pkt(id=3,off=0,r=0),aux_off=14,aux_off_align=4 R6=inv54,min_align=4 R10=fp", - /* Constant is added to R5 again, setting reg->off to 4. */ - "28: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off_align=4 R5=pkt(id=3,off=4,r=0),aux_off=14,aux_off_align=4 R6=inv54,min_align=4 R10=fp", - /* And once more we add a variable, which causes an accumulation - * of reg->off into reg->aux_off_align, with resulting value of - * 18. The auxiliary alignment stays at 4. + {27, "R5=pkt(id=3,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + /* Constant is added to R5 again, setting reg->off to 18. */ + {28, "R5=pkt(id=3,off=18,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + /* And once more we add a variable; resulting var_off + * is still (4n), fixed offset is not changed. + * Also, we create a new reg->id. */ - "29: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off_align=4 R5=pkt(id=4,off=0,r=0),aux_off=18,aux_off_align=4 R6=inv54,min_align=4 R10=fp", + {29, "R5=pkt(id=4,off=18,r=0,umax_value=2040,var_off=(0x0; 0x7fc))"}, /* At the time the word size load is performed from R5, - * it's total offset is NET_IP_ALIGN + reg->off (0) + - * reg->aux_off (18) which is 20. Then the variable offset - * is considered using reg->aux_off_align which is 4 and meets - * the load's requirements. + * its total fixed offset is NET_IP_ALIGN + reg->off (18) + * which is 20. Then the variable offset is (4n), so + * the total offset is 4-byte aligned and meets the + * load's requirements. + */ + {33, "R4=pkt(id=4,off=22,r=22,umax_value=2040,var_off=(0x0; 0x7fc))"}, + {33, "R5=pkt(id=4,off=18,r=22,umax_value=2040,var_off=(0x0; 0x7fc))"}, + }, + }, + { + .descr = "packet variable offset 2", + .insns = { + /* Create an unknown offset, (4n+2)-aligned */ + LOAD_UNKNOWN(BPF_REG_6), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_6, 2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 14), + /* Add it to the packet pointer */ + BPF_MOV64_REG(BPF_REG_5, BPF_REG_2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6), + /* Check bounds and perform a read */ + BPF_MOV64_REG(BPF_REG_4, BPF_REG_5), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_5, 0), + /* Make a (4n) offset from the value we just read */ + BPF_ALU64_IMM(BPF_AND, BPF_REG_6, 0xff), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_6, 2), + /* Add it to the packet pointer */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6), + /* Check bounds and perform a read */ + BPF_MOV64_REG(BPF_REG_4, BPF_REG_5), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_5, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .matches = { + /* Calculated offset in R6 has unknown value, but known + * alignment of 4. + */ + {8, "R2=pkt(id=0,off=0,r=8,imm=0)"}, + {8, "R6=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + /* Adding 14 makes R6 be (4n+2) */ + {9, "R6=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, + /* Packet pointer has (4n+2) offset */ + {11, "R5=pkt(id=1,off=0,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, + {13, "R4=pkt(id=1,off=4,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, + /* At the time the word size load is performed from R5, + * its total fixed offset is NET_IP_ALIGN + reg->off (0) + * which is 2. Then the variable offset is (4n+2), so + * the total offset is 4-byte aligned and meets the + * load's requirements. + */ + {15, "R5=pkt(id=1,off=0,r=4,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, + /* Newly read value in R6 was shifted left by 2, so has + * known alignment of 4. + */ + {18, "R6=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + /* Added (4n) to packet pointer's (4n+2) var_off, giving + * another (4n+2). + */ + {19, "R5=pkt(id=2,off=0,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc))"}, + {21, "R4=pkt(id=2,off=4,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc))"}, + /* At the time the word size load is performed from R5, + * its total fixed offset is NET_IP_ALIGN + reg->off (0) + * which is 2. Then the variable offset is (4n+2), so + * the total offset is 4-byte aligned and meets the + * load's requirements. + */ + {23, "R5=pkt(id=2,off=0,r=4,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc))"}, + }, + }, + { + .descr = "dubious pointer arithmetic", + .insns = { + PREP_PKT_POINTERS, + BPF_MOV64_IMM(BPF_REG_0, 0), + /* ptr & const => unknown & const */ + BPF_MOV64_REG(BPF_REG_5, BPF_REG_2), + BPF_ALU64_IMM(BPF_AND, BPF_REG_5, 0x40), + /* ptr << const => unknown << const */ + BPF_MOV64_REG(BPF_REG_5, BPF_REG_2), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_5, 2), + /* We have a (4n) value. Let's make a packet offset + * out of it. First add 14, to make it a (4n+2) + */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 14), + /* Then make sure it's nonnegative */ + BPF_JMP_IMM(BPF_JSGE, BPF_REG_5, 0, 1), + BPF_EXIT_INSN(), + /* Add it to packet pointer */ + BPF_MOV64_REG(BPF_REG_6, BPF_REG_2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_6, BPF_REG_5), + /* Check bounds and perform a read */ + BPF_MOV64_REG(BPF_REG_4, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_6, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .matches = { + {4, "R5=pkt(id=0,off=0,r=0,imm=0)"}, + /* ptr & 0x40 == either 0 or 0x40 */ + {5, "R5=inv(id=0,umax_value=64,var_off=(0x0; 0x40))"}, + /* ptr << 2 == unknown, (4n) */ + {7, "R5=inv(id=0,smax_value=9223372036854775804,umax_value=18446744073709551612,var_off=(0x0; 0xfffffffffffffffc))"}, + /* (4n) + 14 == (4n+2). We blow our bounds, because + * the add could overflow. + */ + {8, "R5=inv(id=0,var_off=(0x2; 0xfffffffffffffffc))"}, + /* Checked s>=0 */ + {10, "R5=inv(id=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"}, + /* packet pointer + nonnegative (4n+2) */ + {12, "R6=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"}, + {14, "R4=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"}, + /* NET_IP_ALIGN + (4n+2) == (4n), alignment is fine. + * We checked the bounds, but it might have been able + * to overflow if the packet pointer started in the + * upper half of the address space. + * So we did not get a 'range' on R6, and the access + * attempt will fail. + */ + {16, "R6=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"}, + } + }, + { + .descr = "variable subtraction", + .insns = { + /* Create an unknown offset, (4n+2)-aligned */ + LOAD_UNKNOWN(BPF_REG_6), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_6), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_6, 2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 14), + /* Create another unknown, (4n)-aligned, and subtract + * it from the first one + */ + BPF_ALU64_IMM(BPF_LSH, BPF_REG_7, 2), + BPF_ALU64_REG(BPF_SUB, BPF_REG_6, BPF_REG_7), + /* Bounds-check the result */ + BPF_JMP_IMM(BPF_JSGE, BPF_REG_6, 0, 1), + BPF_EXIT_INSN(), + /* Add it to the packet pointer */ + BPF_MOV64_REG(BPF_REG_5, BPF_REG_2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6), + /* Check bounds and perform a read */ + BPF_MOV64_REG(BPF_REG_4, BPF_REG_5), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_5, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .matches = { + /* Calculated offset in R6 has unknown value, but known + * alignment of 4. + */ + {7, "R2=pkt(id=0,off=0,r=8,imm=0)"}, + {9, "R6=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + /* Adding 14 makes R6 be (4n+2) */ + {10, "R6=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, + /* New unknown value in R7 is (4n) */ + {11, "R7=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + /* Subtracting it from R6 blows our unsigned bounds */ + {12, "R6=inv(id=0,smin_value=-1006,smax_value=1034,var_off=(0x2; 0xfffffffffffffffc))"}, + /* Checked s>= 0 */ + {14, "R6=inv(id=0,umin_value=2,umax_value=1034,var_off=(0x2; 0x7fc))"}, + /* At the time the word size load is performed from R5, + * its total fixed offset is NET_IP_ALIGN + reg->off (0) + * which is 2. Then the variable offset is (4n+2), so + * the total offset is 4-byte aligned and meets the + * load's requirements. + */ + {20, "R5=pkt(id=1,off=0,r=4,umin_value=2,umax_value=1034,var_off=(0x2; 0x7fc))"}, + }, + }, + { + .descr = "pointer variable subtraction", + .insns = { + /* Create an unknown offset, (4n+2)-aligned and bounded + * to [14,74] + */ + LOAD_UNKNOWN(BPF_REG_6), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_6), + BPF_ALU64_IMM(BPF_AND, BPF_REG_6, 0xf), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_6, 2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 14), + /* Subtract it from the packet pointer */ + BPF_MOV64_REG(BPF_REG_5, BPF_REG_2), + BPF_ALU64_REG(BPF_SUB, BPF_REG_5, BPF_REG_6), + /* Create another unknown, (4n)-aligned and >= 74. + * That in fact means >= 76, since 74 % 4 == 2 */ - "33: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=pkt(id=4,off=4,r=4),aux_off=18,aux_off_align=4 R5=pkt(id=4,off=0,r=4),aux_off=18,aux_off_align=4 R6=inv54,min_align=4 R10=fp", + BPF_ALU64_IMM(BPF_LSH, BPF_REG_7, 2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, 76), + /* Add it to the packet pointer */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_7), + /* Check bounds and perform a read */ + BPF_MOV64_REG(BPF_REG_4, BPF_REG_5), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_5, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .matches = { + /* Calculated offset in R6 has unknown value, but known + * alignment of 4. + */ + {7, "R2=pkt(id=0,off=0,r=8,imm=0)"}, + {10, "R6=inv(id=0,umax_value=60,var_off=(0x0; 0x3c))"}, + /* Adding 14 makes R6 be (4n+2) */ + {11, "R6=inv(id=0,umin_value=14,umax_value=74,var_off=(0x2; 0x7c))"}, + /* Subtracting from packet pointer overflows ubounds */ + {13, "R5=pkt(id=1,off=0,r=8,umin_value=18446744073709551542,umax_value=18446744073709551602,var_off=(0xffffffffffffff82; 0x7c))"}, + /* New unknown value in R7 is (4n), >= 76 */ + {15, "R7=inv(id=0,umin_value=76,umax_value=1096,var_off=(0x0; 0x7fc))"}, + /* Adding it to packet pointer gives nice bounds again */ + {16, "R5=pkt(id=2,off=0,r=0,umin_value=2,umax_value=1082,var_off=(0x2; 0x7fc))"}, + /* At the time the word size load is performed from R5, + * its total fixed offset is NET_IP_ALIGN + reg->off (0) + * which is 2. Then the variable offset is (4n+2), so + * the total offset is 4-byte aligned and meets the + * load's requirements. + */ + {20, "R5=pkt(id=2,off=0,r=4,umin_value=2,umax_value=1082,var_off=(0x2; 0x7fc))"}, }, }, }; @@ -373,6 +619,9 @@ static int do_test_single(struct bpf_align_test *test) { struct bpf_insn *prog = test->insns; int prog_type = test->prog_type; + char bpf_vlog_copy[32768]; + const char *line_ptr; + int cur_line = -1; int prog_len, i; int fd_prog; int ret; @@ -381,26 +630,49 @@ static int do_test_single(struct bpf_align_test *test) fd_prog = bpf_verify_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER, prog, prog_len, 1, "GPL", 0, bpf_vlog, sizeof(bpf_vlog), 2); - if (fd_prog < 0) { + if (fd_prog < 0 && test->result != REJECT) { printf("Failed to load program.\n"); printf("%s", bpf_vlog); ret = 1; + } else if (fd_prog >= 0 && test->result == REJECT) { + printf("Unexpected success to load!\n"); + printf("%s", bpf_vlog); + ret = 1; + close(fd_prog); } else { ret = 0; + /* We make a local copy so that we can strtok() it */ + strncpy(bpf_vlog_copy, bpf_vlog, sizeof(bpf_vlog_copy)); + line_ptr = strtok(bpf_vlog_copy, "\n"); for (i = 0; i < MAX_MATCHES; i++) { - const char *t, *m = test->matches[i]; + struct bpf_reg_match m = test->matches[i]; - if (!m) + if (!m.match) break; - t = strstr(bpf_vlog, m); - if (!t) { - printf("Failed to find match: %s\n", m); + while (line_ptr) { + cur_line = -1; + sscanf(line_ptr, "%u: ", &cur_line); + if (cur_line == m.line) + break; + line_ptr = strtok(NULL, "\n"); + } + if (!line_ptr) { + printf("Failed to find line %u for match: %s\n", + m.line, m.match); + ret = 1; + printf("%s", bpf_vlog); + break; + } + if (!strstr(line_ptr, m.match)) { + printf("Failed to find match %u: %s\n", + m.line, m.match); ret = 1; printf("%s", bpf_vlog); break; } } - close(fd_prog); + if (fd_prog >= 0) + close(fd_prog); } return ret; } diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index 79601c81e169..4acc772a28c0 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -22,6 +22,7 @@ #include <linux/bpf.h> #include <bpf/bpf.h> +#include <bpf/libbpf.h> #include "bpf_util.h" static int map_flags; @@ -438,6 +439,395 @@ static void test_arraymap_percpu_many_keys(void) close(fd); } +static void test_devmap(int task, void *data) +{ + int fd; + __u32 key, value; + + fd = bpf_create_map(BPF_MAP_TYPE_DEVMAP, sizeof(key), sizeof(value), + 2, 0); + if (fd < 0) { + printf("Failed to create arraymap '%s'!\n", strerror(errno)); + exit(1); + } + + close(fd); +} + +#include <sys/socket.h> +#include <sys/ioctl.h> +#include <arpa/inet.h> +#include <sys/select.h> +#include <linux/err.h> +#define SOCKMAP_PARSE_PROG "./sockmap_parse_prog.o" +#define SOCKMAP_VERDICT_PROG "./sockmap_verdict_prog.o" +static void test_sockmap(int tasks, void *data) +{ + int one = 1, map_fd_rx, map_fd_tx, map_fd_break, s, sc, rc; + struct bpf_map *bpf_map_rx, *bpf_map_tx, *bpf_map_break; + int ports[] = {50200, 50201, 50202, 50204}; + int err, i, fd, sfd[6] = {0xdeadbeef}; + u8 buf[20] = {0x0, 0x5, 0x3, 0x2, 0x1, 0x0}; + int parse_prog, verdict_prog; + struct sockaddr_in addr; + struct bpf_object *obj; + struct timeval to; + __u32 key, value; + pid_t pid[tasks]; + fd_set w; + + /* Create some sockets to use with sockmap */ + for (i = 0; i < 2; i++) { + sfd[i] = socket(AF_INET, SOCK_STREAM, 0); + if (sfd[i] < 0) + goto out; + err = setsockopt(sfd[i], SOL_SOCKET, SO_REUSEADDR, + (char *)&one, sizeof(one)); + if (err) { + printf("failed to setsockopt\n"); + goto out; + } + err = ioctl(sfd[i], FIONBIO, (char *)&one); + if (err < 0) { + printf("failed to ioctl\n"); + goto out; + } + memset(&addr, 0, sizeof(struct sockaddr_in)); + addr.sin_family = AF_INET; + addr.sin_addr.s_addr = inet_addr("127.0.0.1"); + addr.sin_port = htons(ports[i]); + err = bind(sfd[i], (struct sockaddr *)&addr, sizeof(addr)); + if (err < 0) { + printf("failed to bind: err %i: %i:%i\n", + err, i, sfd[i]); + goto out; + } + err = listen(sfd[i], 32); + if (err < 0) { + printf("failed to listen\n"); + goto out; + } + } + + for (i = 2; i < 4; i++) { + sfd[i] = socket(AF_INET, SOCK_STREAM, 0); + if (sfd[i] < 0) + goto out; + err = setsockopt(sfd[i], SOL_SOCKET, SO_REUSEADDR, + (char *)&one, sizeof(one)); + if (err) { + printf("set sock opt\n"); + goto out; + } + memset(&addr, 0, sizeof(struct sockaddr_in)); + addr.sin_family = AF_INET; + addr.sin_addr.s_addr = inet_addr("127.0.0.1"); + addr.sin_port = htons(ports[i - 2]); + err = connect(sfd[i], (struct sockaddr *)&addr, sizeof(addr)); + if (err) { + printf("failed to connect\n"); + goto out; + } + } + + + for (i = 4; i < 6; i++) { + sfd[i] = accept(sfd[i - 4], NULL, NULL); + if (sfd[i] < 0) { + printf("accept failed\n"); + goto out; + } + } + + /* Test sockmap with connected sockets */ + fd = bpf_create_map(BPF_MAP_TYPE_SOCKMAP, + sizeof(key), sizeof(value), + 6, 0); + if (fd < 0) { + printf("Failed to create sockmap %i\n", fd); + goto out_sockmap; + } + + /* Test update without programs */ + for (i = 0; i < 6; i++) { + err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_ANY); + if (err) { + printf("Failed noprog update sockmap '%i:%i'\n", + i, sfd[i]); + goto out_sockmap; + } + } + + /* Test attaching bad fds */ + err = bpf_prog_attach(-1, fd, BPF_SK_SKB_STREAM_PARSER, 0); + if (!err) { + printf("Failed invalid parser prog attach\n"); + goto out_sockmap; + } + + err = bpf_prog_attach(-1, fd, BPF_SK_SKB_STREAM_VERDICT, 0); + if (!err) { + printf("Failed invalid verdict prog attach\n"); + goto out_sockmap; + } + + /* Load SK_SKB program and Attach */ + err = bpf_prog_load(SOCKMAP_PARSE_PROG, + BPF_PROG_TYPE_SK_SKB, &obj, &parse_prog); + if (err) { + printf("Failed to load SK_SKB parse prog\n"); + goto out_sockmap; + } + + err = bpf_prog_load(SOCKMAP_VERDICT_PROG, + BPF_PROG_TYPE_SK_SKB, &obj, &verdict_prog); + if (err) { + printf("Failed to load SK_SKB verdict prog\n"); + goto out_sockmap; + } + + bpf_map_rx = bpf_object__find_map_by_name(obj, "sock_map_rx"); + if (IS_ERR(bpf_map_rx)) { + printf("Failed to load map rx from verdict prog\n"); + goto out_sockmap; + } + + map_fd_rx = bpf_map__fd(bpf_map_rx); + if (map_fd_rx < 0) { + printf("Failed to get map fd\n"); + goto out_sockmap; + } + + bpf_map_tx = bpf_object__find_map_by_name(obj, "sock_map_tx"); + if (IS_ERR(bpf_map_tx)) { + printf("Failed to load map tx from verdict prog\n"); + goto out_sockmap; + } + + map_fd_tx = bpf_map__fd(bpf_map_tx); + if (map_fd_tx < 0) { + printf("Failed to get map tx fd\n"); + goto out_sockmap; + } + + bpf_map_break = bpf_object__find_map_by_name(obj, "sock_map_break"); + if (IS_ERR(bpf_map_break)) { + printf("Failed to load map tx from verdict prog\n"); + goto out_sockmap; + } + + map_fd_break = bpf_map__fd(bpf_map_break); + if (map_fd_break < 0) { + printf("Failed to get map tx fd\n"); + goto out_sockmap; + } + + err = bpf_prog_attach(parse_prog, map_fd_break, + BPF_SK_SKB_STREAM_PARSER, 0); + if (!err) { + printf("Allowed attaching SK_SKB program to invalid map\n"); + goto out_sockmap; + } + + err = bpf_prog_attach(parse_prog, map_fd_rx, + BPF_SK_SKB_STREAM_PARSER, 0); + if (err) { + printf("Failed stream parser bpf prog attach\n"); + goto out_sockmap; + } + + err = bpf_prog_attach(verdict_prog, map_fd_rx, + BPF_SK_SKB_STREAM_VERDICT, 0); + if (err) { + printf("Failed stream verdict bpf prog attach\n"); + goto out_sockmap; + } + + /* Test map update elem afterwards fd lives in fd and map_fd */ + for (i = 0; i < 6; i++) { + err = bpf_map_update_elem(map_fd_rx, &i, &sfd[i], BPF_ANY); + if (err) { + printf("Failed map_fd_rx update sockmap %i '%i:%i'\n", + err, i, sfd[i]); + goto out_sockmap; + } + err = bpf_map_update_elem(map_fd_tx, &i, &sfd[i], BPF_ANY); + if (err) { + printf("Failed map_fd_tx update sockmap %i '%i:%i'\n", + err, i, sfd[i]); + goto out_sockmap; + } + } + + /* Test map delete elem and remove send/recv sockets */ + for (i = 2; i < 4; i++) { + err = bpf_map_delete_elem(map_fd_rx, &i); + if (err) { + printf("Failed delete sockmap rx %i '%i:%i'\n", + err, i, sfd[i]); + goto out_sockmap; + } + err = bpf_map_delete_elem(map_fd_tx, &i); + if (err) { + printf("Failed delete sockmap tx %i '%i:%i'\n", + err, i, sfd[i]); + goto out_sockmap; + } + } + + /* Test map send/recv */ + for (i = 0; i < 2; i++) { + buf[0] = i; + buf[1] = 0x5; + sc = send(sfd[2], buf, 20, 0); + if (sc < 0) { + printf("Failed sockmap send\n"); + goto out_sockmap; + } + + FD_ZERO(&w); + FD_SET(sfd[3], &w); + to.tv_sec = 1; + to.tv_usec = 0; + s = select(sfd[3] + 1, &w, NULL, NULL, &to); + if (s == -1) { + perror("Failed sockmap select()"); + goto out_sockmap; + } else if (!s) { + printf("Failed sockmap unexpected timeout\n"); + goto out_sockmap; + } + + if (!FD_ISSET(sfd[3], &w)) { + printf("Failed sockmap select/recv\n"); + goto out_sockmap; + } + + rc = recv(sfd[3], buf, sizeof(buf), 0); + if (rc < 0) { + printf("Failed sockmap recv\n"); + goto out_sockmap; + } + } + + /* Negative null entry lookup from datapath should be dropped */ + buf[0] = 1; + buf[1] = 12; + sc = send(sfd[2], buf, 20, 0); + if (sc < 0) { + printf("Failed sockmap send\n"); + goto out_sockmap; + } + + /* Push fd into same slot */ + i = 2; + err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_NOEXIST); + if (!err) { + printf("Failed allowed sockmap dup slot BPF_NOEXIST\n"); + goto out_sockmap; + } + + err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_ANY); + if (err) { + printf("Failed sockmap update new slot BPF_ANY\n"); + goto out_sockmap; + } + + err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_EXIST); + if (err) { + printf("Failed sockmap update new slot BPF_EXIST\n"); + goto out_sockmap; + } + + /* Delete the elems without programs */ + for (i = 0; i < 6; i++) { + err = bpf_map_delete_elem(fd, &i); + if (err) { + printf("Failed delete sockmap %i '%i:%i'\n", + err, i, sfd[i]); + } + } + + /* Test having multiple maps open and set with programs on same fds */ + err = bpf_prog_attach(parse_prog, fd, + BPF_SK_SKB_STREAM_PARSER, 0); + if (err) { + printf("Failed fd bpf parse prog attach\n"); + goto out_sockmap; + } + err = bpf_prog_attach(verdict_prog, fd, + BPF_SK_SKB_STREAM_VERDICT, 0); + if (err) { + printf("Failed fd bpf verdict prog attach\n"); + goto out_sockmap; + } + + for (i = 4; i < 6; i++) { + err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_ANY); + if (!err) { + printf("Failed allowed duplicate programs in update ANY sockmap %i '%i:%i'\n", + err, i, sfd[i]); + goto out_sockmap; + } + err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_NOEXIST); + if (!err) { + printf("Failed allowed duplicate program in update NOEXIST sockmap %i '%i:%i'\n", + err, i, sfd[i]); + goto out_sockmap; + } + err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_EXIST); + if (!err) { + printf("Failed allowed duplicate program in update EXIST sockmap %i '%i:%i'\n", + err, i, sfd[i]); + goto out_sockmap; + } + } + + /* Test tasks number of forked operations */ + for (i = 0; i < tasks; i++) { + pid[i] = fork(); + if (pid[i] == 0) { + for (i = 0; i < 6; i++) { + bpf_map_delete_elem(map_fd_tx, &i); + bpf_map_delete_elem(map_fd_rx, &i); + bpf_map_update_elem(map_fd_tx, &i, + &sfd[i], BPF_ANY); + bpf_map_update_elem(map_fd_rx, &i, + &sfd[i], BPF_ANY); + } + exit(0); + } else if (pid[i] == -1) { + printf("Couldn't spawn #%d process!\n", i); + exit(1); + } + } + + for (i = 0; i < tasks; i++) { + int status; + + assert(waitpid(pid[i], &status, 0) == pid[i]); + assert(status == 0); + } + + /* Test map close sockets */ + for (i = 0; i < 6; i++) + close(sfd[i]); + close(fd); + close(map_fd_rx); + bpf_object__close(obj); + return; +out: + for (i = 0; i < 6; i++) + close(sfd[i]); + printf("Failed to create sockmap '%i:%s'!\n", i, strerror(errno)); + exit(1); +out_sockmap: + for (i = 0; i < 6; i++) + close(sfd[i]); + close(fd); + exit(1); +} + #define MAP_SIZE (32 * 1024) static void test_map_large(void) @@ -605,6 +995,9 @@ static void run_all_tests(void) test_arraymap_percpu_many_keys(); + test_devmap(0, NULL); + test_sockmap(0, NULL); + test_map_large(); test_map_parallel(); test_map_stress(); diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index 1f7dd35551b9..11ee25cea227 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -75,39 +75,6 @@ static struct { __ret; \ }) -static int bpf_prog_load(const char *file, enum bpf_prog_type type, - struct bpf_object **pobj, int *prog_fd) -{ - struct bpf_program *prog; - struct bpf_object *obj; - int err; - - obj = bpf_object__open(file); - if (IS_ERR(obj)) { - error_cnt++; - return -ENOENT; - } - - prog = bpf_program__next(NULL, obj); - if (!prog) { - bpf_object__close(obj); - error_cnt++; - return -ENOENT; - } - - bpf_program__set_type(prog, type); - err = bpf_object__load(obj); - if (err) { - bpf_object__close(obj); - error_cnt++; - return -EINVAL; - } - - *pobj = obj; - *prog_fd = bpf_program__fd(prog); - return 0; -} - static int bpf_find_map(const char *test, struct bpf_object *obj, const char *name) { @@ -130,8 +97,10 @@ static void test_pkt_access(void) int err, prog_fd; err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); - if (err) + if (err) { + error_cnt++; return; + } err = bpf_prog_test_run(prog_fd, 100000, &pkt_v4, sizeof(pkt_v4), NULL, NULL, &retval, &duration); @@ -162,8 +131,10 @@ static void test_xdp(void) int err, prog_fd, map_fd; err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); - if (err) + if (err) { + error_cnt++; return; + } map_fd = bpf_find_map(__func__, obj, "vip2tnl"); if (map_fd < 0) @@ -223,8 +194,10 @@ static void test_l4lb(void) u32 *magic = (u32 *)buf; err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); - if (err) + if (err) { + error_cnt++; return; + } map_fd = bpf_find_map(__func__, obj, "vip_map"); if (map_fd < 0) @@ -280,8 +253,10 @@ static void test_tcp_estats(void) err = bpf_prog_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd); CHECK(err, "", "err %d errno %d\n", err, errno); - if (err) + if (err) { + error_cnt++; return; + } bpf_object__close(obj); } @@ -304,7 +279,7 @@ static void test_bpf_obj_id(void) /* +1 to test for the info_len returned by kernel */ struct bpf_prog_info prog_infos[nr_iters + 1]; struct bpf_map_info map_infos[nr_iters + 1]; - char jited_insns[128], xlated_insns[128]; + char jited_insns[128], xlated_insns[128], zeros[128]; __u32 i, next_id, info_len, nr_id_found, duration = 0; int sysctl_fd, jit_enabled = 0, err = 0; __u64 array_value; @@ -330,17 +305,22 @@ static void test_bpf_obj_id(void) objs[i] = NULL; /* Check bpf_obj_get_info_by_fd() */ + bzero(zeros, sizeof(zeros)); for (i = 0; i < nr_iters; i++) { err = bpf_prog_load(file, BPF_PROG_TYPE_SOCKET_FILTER, &objs[i], &prog_fds[i]); /* test_obj_id.o is a dumb prog. It should never fail * to load. */ + if (err) + error_cnt++; assert(!err); /* Check getting prog info */ info_len = sizeof(struct bpf_prog_info) * 2; bzero(&prog_infos[i], info_len); + bzero(jited_insns, sizeof(jited_insns)); + bzero(xlated_insns, sizeof(xlated_insns)); prog_infos[i].jited_prog_insns = ptr_to_u64(jited_insns); prog_infos[i].jited_prog_len = sizeof(jited_insns); prog_infos[i].xlated_prog_insns = ptr_to_u64(xlated_insns); @@ -351,15 +331,20 @@ static void test_bpf_obj_id(void) prog_infos[i].type != BPF_PROG_TYPE_SOCKET_FILTER || info_len != sizeof(struct bpf_prog_info) || (jit_enabled && !prog_infos[i].jited_prog_len) || - !prog_infos[i].xlated_prog_len, + (jit_enabled && + !memcmp(jited_insns, zeros, sizeof(zeros))) || + !prog_infos[i].xlated_prog_len || + !memcmp(xlated_insns, zeros, sizeof(zeros)), "get-prog-info(fd)", - "err %d errno %d i %d type %d(%d) info_len %u(%lu) jit_enabled %d jited_prog_len %u xlated_prog_len %u\n", + "err %d errno %d i %d type %d(%d) info_len %u(%lu) jit_enabled %d jited_prog_len %u xlated_prog_len %u jited_prog %d xlated_prog %d\n", err, errno, i, prog_infos[i].type, BPF_PROG_TYPE_SOCKET_FILTER, info_len, sizeof(struct bpf_prog_info), jit_enabled, prog_infos[i].jited_prog_len, - prog_infos[i].xlated_prog_len)) + prog_infos[i].xlated_prog_len, + !!memcmp(jited_insns, zeros, sizeof(zeros)), + !!memcmp(xlated_insns, zeros, sizeof(zeros)))) goto done; map_fds[i] = bpf_find_map(__func__, objs[i], "test_map_id"); @@ -496,8 +481,10 @@ static void test_pkt_md_access(void) int err, prog_fd; err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); - if (err) + if (err) { + error_cnt++; return; + } err = bpf_prog_test_run(prog_fd, 10, &pkt_v4, sizeof(pkt_v4), NULL, NULL, &retval, &duration); diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index d3ed7324105e..8eb09950258b 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -422,7 +422,7 @@ static struct bpf_test tests[] = { BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R1 pointer arithmetic", + .errstr_unpriv = "R1 subtraction from stack pointer", .result_unpriv = REJECT, .errstr = "R1 invalid mem access", .result = REJECT, @@ -604,8 +604,9 @@ static struct bpf_test tests[] = { BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, -4), BPF_EXIT_INSN(), }, - .errstr = "misaligned access", + .errstr = "misaligned stack access", .result = REJECT, + .flags = F_LOAD_WITH_STRICT_ALIGNMENT, }, { "invalid map_fd for function call", @@ -651,8 +652,9 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr = "misaligned access", + .errstr = "misaligned value access", .result = REJECT, + .flags = F_LOAD_WITH_STRICT_ALIGNMENT, }, { "sometimes access memory with incorrect alignment", @@ -673,6 +675,7 @@ static struct bpf_test tests[] = { .errstr = "R0 invalid mem access", .errstr_unpriv = "R0 leaks addr", .result = REJECT, + .flags = F_LOAD_WITH_STRICT_ALIGNMENT, }, { "jump test 1", @@ -964,6 +967,256 @@ static struct bpf_test tests[] = { .result = REJECT, }, { + "invalid access __sk_buff family", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, family)), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + }, + { + "invalid access __sk_buff remote_ip4", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, remote_ip4)), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + }, + { + "invalid access __sk_buff local_ip4", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, local_ip4)), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + }, + { + "invalid access __sk_buff remote_ip6", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, remote_ip6)), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + }, + { + "invalid access __sk_buff local_ip6", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, local_ip6)), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + }, + { + "invalid access __sk_buff remote_port", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, remote_port)), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + }, + { + "invalid access __sk_buff remote_port", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, local_port)), + BPF_EXIT_INSN(), + }, + .errstr = "invalid bpf_context access", + .result = REJECT, + }, + { + "valid access __sk_buff family", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, family)), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_SKB, + }, + { + "valid access __sk_buff remote_ip4", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, remote_ip4)), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_SKB, + }, + { + "valid access __sk_buff local_ip4", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, local_ip4)), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_SKB, + }, + { + "valid access __sk_buff remote_ip6", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, remote_ip6[0])), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, remote_ip6[1])), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, remote_ip6[2])), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, remote_ip6[3])), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_SKB, + }, + { + "valid access __sk_buff local_ip6", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, local_ip6[0])), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, local_ip6[1])), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, local_ip6[2])), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, local_ip6[3])), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_SKB, + }, + { + "valid access __sk_buff remote_port", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, remote_port)), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_SKB, + }, + { + "valid access __sk_buff remote_port", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, local_port)), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_SKB, + }, + { + "invalid access of tc_classid for SK_SKB", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, tc_classid)), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SK_SKB, + .errstr = "invalid bpf_context access", + }, + { + "check skb->mark is writeable by SK_SKB", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, mark)), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_SKB, + }, + { + "check skb->tc_index is writeable by SK_SKB", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, tc_index)), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_SKB, + }, + { + "check skb->priority is writeable by SK_SKB", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, priority)), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_SKB, + }, + { + "direct packet read for SK_SKB", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_SKB, + }, + { + "direct packet write for SK_SKB", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + BPF_STX_MEM(BPF_B, BPF_REG_2, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_SKB, + }, + { + "overlapping checks for direct packet access SK_SKB", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_2, 6), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SK_SKB, + }, + { "check skb->mark is not writeable by sockets", .insns = { BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_1, @@ -1216,8 +1469,9 @@ static struct bpf_test tests[] = { offsetof(struct __sk_buff, cb[0]) + 1), BPF_EXIT_INSN(), }, - .errstr = "misaligned access", + .errstr = "misaligned context access", .result = REJECT, + .flags = F_LOAD_WITH_STRICT_ALIGNMENT, }, { "check __sk_buff->hash, offset 0, half store not permitted", @@ -1320,8 +1574,9 @@ static struct bpf_test tests[] = { offsetof(struct __sk_buff, cb[0]) + 2), BPF_EXIT_INSN(), }, - .errstr = "misaligned access", + .errstr = "misaligned context access", .result = REJECT, + .flags = F_LOAD_WITH_STRICT_ALIGNMENT, }, { "check cb access: word, unaligned 2", @@ -1331,8 +1586,9 @@ static struct bpf_test tests[] = { offsetof(struct __sk_buff, cb[4]) + 1), BPF_EXIT_INSN(), }, - .errstr = "misaligned access", + .errstr = "misaligned context access", .result = REJECT, + .flags = F_LOAD_WITH_STRICT_ALIGNMENT, }, { "check cb access: word, unaligned 3", @@ -1342,8 +1598,9 @@ static struct bpf_test tests[] = { offsetof(struct __sk_buff, cb[4]) + 2), BPF_EXIT_INSN(), }, - .errstr = "misaligned access", + .errstr = "misaligned context access", .result = REJECT, + .flags = F_LOAD_WITH_STRICT_ALIGNMENT, }, { "check cb access: word, unaligned 4", @@ -1353,8 +1610,9 @@ static struct bpf_test tests[] = { offsetof(struct __sk_buff, cb[4]) + 3), BPF_EXIT_INSN(), }, - .errstr = "misaligned access", + .errstr = "misaligned context access", .result = REJECT, + .flags = F_LOAD_WITH_STRICT_ALIGNMENT, }, { "check cb access: double", @@ -1380,8 +1638,9 @@ static struct bpf_test tests[] = { offsetof(struct __sk_buff, cb[1])), BPF_EXIT_INSN(), }, - .errstr = "misaligned access", + .errstr = "misaligned context access", .result = REJECT, + .flags = F_LOAD_WITH_STRICT_ALIGNMENT, }, { "check cb access: double, unaligned 2", @@ -1391,8 +1650,9 @@ static struct bpf_test tests[] = { offsetof(struct __sk_buff, cb[3])), BPF_EXIT_INSN(), }, - .errstr = "misaligned access", + .errstr = "misaligned context access", .result = REJECT, + .flags = F_LOAD_WITH_STRICT_ALIGNMENT, }, { "check cb access: double, oob 1", @@ -1524,7 +1784,8 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .result = REJECT, - .errstr = "misaligned access off -6 size 8", + .errstr = "misaligned stack access off (0x0; 0x0)+-8+2 size 8", + .flags = F_LOAD_WITH_STRICT_ALIGNMENT, }, { "PTR_TO_STACK store/load - bad alignment on reg", @@ -1536,7 +1797,8 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .result = REJECT, - .errstr = "misaligned access off -2 size 8", + .errstr = "misaligned stack access off (0x0; 0x0)+-10+8 size 8", + .flags = F_LOAD_WITH_STRICT_ALIGNMENT, }, { "PTR_TO_STACK store/load - out of bounds low", @@ -1580,8 +1842,6 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .result = ACCEPT, - .result_unpriv = REJECT, - .errstr_unpriv = "R1 pointer arithmetic", }, { "unpriv: add pointer to pointer", @@ -1592,7 +1852,7 @@ static struct bpf_test tests[] = { }, .result = ACCEPT, .result_unpriv = REJECT, - .errstr_unpriv = "R1 pointer arithmetic", + .errstr_unpriv = "R1 pointer += pointer", }, { "unpriv: neg pointer", @@ -1933,10 +2193,7 @@ static struct bpf_test tests[] = { BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, -8), BPF_EXIT_INSN(), }, - .errstr_unpriv = "pointer arithmetic prohibited", - .result_unpriv = REJECT, - .errstr = "R1 invalid mem access", - .result = REJECT, + .result = ACCEPT, }, { "unpriv: cmp of stack pointer", @@ -2000,7 +2257,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .result = REJECT, - .errstr = "invalid stack type R3", + .errstr = "R4 min value is negative", .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, { @@ -2017,7 +2274,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .result = REJECT, - .errstr = "invalid stack type R3", + .errstr = "R4 min value is negative", .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, { @@ -2219,7 +2476,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .result = REJECT, - .errstr = "invalid stack type R3 off=-1 access_size=-1", + .errstr = "R4 min value is negative", .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, { @@ -2236,7 +2493,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .result = REJECT, - .errstr = "invalid stack type R3 off=-1 access_size=2147483647", + .errstr = "R4 unbounded memory access, use 'var &= const' or 'if (var < const)'", .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, { @@ -2253,7 +2510,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .result = REJECT, - .errstr = "invalid stack type R3 off=-512 access_size=2147483647", + .errstr = "R4 unbounded memory access, use 'var &= const' or 'if (var < const)'", .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, { @@ -2324,8 +2581,8 @@ static struct bpf_test tests[] = { offsetof(struct __sk_buff, data)), BPF_ALU64_REG(BPF_ADD, BPF_REG_3, BPF_REG_4), BPF_MOV64_REG(BPF_REG_2, BPF_REG_1), - BPF_ALU64_IMM(BPF_LSH, BPF_REG_2, 48), - BPF_ALU64_IMM(BPF_RSH, BPF_REG_2, 48), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_2, 49), + BPF_ALU64_IMM(BPF_RSH, BPF_REG_2, 49), BPF_ALU64_REG(BPF_ADD, BPF_REG_3, BPF_REG_2), BPF_MOV64_REG(BPF_REG_2, BPF_REG_3), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 8), @@ -2653,7 +2910,7 @@ static struct bpf_test tests[] = { BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1), BPF_JMP_A(-6), }, - .errstr = "misaligned packet access off 2+15+-4 size 4", + .errstr = "misaligned packet access off 2+(0x0; 0x0)+15+-4 size 4", .result = REJECT, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .flags = F_LOAD_WITH_STRICT_ALIGNMENT, @@ -2704,11 +2961,11 @@ static struct bpf_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 0xffffffff), BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8), BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8), - BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 0xffff), + BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 0x7fff), BPF_MOV64_REG(BPF_REG_4, BPF_REG_0), BPF_ALU64_REG(BPF_ADD, BPF_REG_4, BPF_REG_2), BPF_MOV64_REG(BPF_REG_5, BPF_REG_4), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 0xffff - 1), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 0x7fff - 1), BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 1), BPF_STX_MEM(BPF_DW, BPF_REG_5, BPF_REG_4, 0), BPF_MOV64_IMM(BPF_REG_0, 0), @@ -2730,10 +2987,10 @@ static struct bpf_test tests[] = { BPF_MOV64_IMM(BPF_REG_4, 0xffffffff), BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_4, -8), BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8), - BPF_ALU64_IMM(BPF_AND, BPF_REG_4, 0xffff), + BPF_ALU64_IMM(BPF_AND, BPF_REG_4, 0x7fff), BPF_ALU64_REG(BPF_ADD, BPF_REG_4, BPF_REG_2), BPF_MOV64_REG(BPF_REG_5, BPF_REG_4), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 0xffff - 1), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 0x7fff - 1), BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 1), BPF_STX_MEM(BPF_DW, BPF_REG_5, BPF_REG_4, 0), BPF_MOV64_IMM(BPF_REG_0, 0), @@ -2759,7 +3016,7 @@ static struct bpf_test tests[] = { BPF_MOV64_IMM(BPF_REG_4, 0xffffffff), BPF_STX_XADD(BPF_DW, BPF_REG_10, BPF_REG_4, -8), BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8), - BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 48), + BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 49), BPF_ALU64_REG(BPF_ADD, BPF_REG_4, BPF_REG_2), BPF_MOV64_REG(BPF_REG_0, BPF_REG_4), BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 2), @@ -2796,7 +3053,7 @@ static struct bpf_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .result = REJECT, - .errstr = "cannot add integer value with 47 upper zero bits to ptr_to_packet", + .errstr = "invalid access to packet, off=0 size=8, R5(id=1,off=0,r=0)", }, { "direct packet access: test24 (x += pkt_ptr, 5)", @@ -2814,7 +3071,7 @@ static struct bpf_test tests[] = { BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4), BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_2), BPF_MOV64_REG(BPF_REG_5, BPF_REG_0), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 0xffff - 1), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 0x7fff - 1), BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), BPF_STX_MEM(BPF_DW, BPF_REG_5, BPF_REG_0, 0), BPF_MOV64_IMM(BPF_REG_0, 0), @@ -2824,6 +3081,79 @@ static struct bpf_test tests[] = { .result = ACCEPT, }, { + "direct packet access: test25 (marking on <, good access)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JLT, BPF_REG_0, BPF_REG_3, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, -4), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "direct packet access: test26 (marking on <, bad access)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JLT, BPF_REG_0, BPF_REG_3, 3), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JA, 0, 0, -3), + }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "direct packet access: test27 (marking on <=, good access)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_0, 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "direct packet access: test28 (marking on <=, bad access)", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), + BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_0, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0), + BPF_JMP_IMM(BPF_JA, 0, 0, -4), + }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { "helper access to packet: test1, valid packet_ptr range", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, @@ -3113,7 +3443,7 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, { - "helper access to packet: test14, cls helper fail sub", + "helper access to packet: test14, cls helper ok sub", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, offsetof(struct __sk_buff, data)), @@ -3133,12 +3463,36 @@ static struct bpf_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "helper access to packet: test15, cls helper fail sub", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_7, 6), + BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 12), + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_MOV64_IMM(BPF_REG_5, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_csum_diff), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, .result = REJECT, - .errstr = "type=inv expected=fp", + .errstr = "invalid access to packet", .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, { - "helper access to packet: test15, cls helper fail range 1", + "helper access to packet: test16, cls helper fail range 1", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, offsetof(struct __sk_buff, data)), @@ -3163,7 +3517,7 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, { - "helper access to packet: test16, cls helper fail range 2", + "helper access to packet: test17, cls helper fail range 2", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, offsetof(struct __sk_buff, data)), @@ -3184,11 +3538,11 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .result = REJECT, - .errstr = "invalid access to packet", + .errstr = "R2 min value is negative", .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, { - "helper access to packet: test17, cls helper fail range 3", + "helper access to packet: test18, cls helper fail range 3", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, offsetof(struct __sk_buff, data)), @@ -3209,11 +3563,11 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .result = REJECT, - .errstr = "invalid access to packet", + .errstr = "R2 min value is negative", .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, { - "helper access to packet: test18, cls helper fail range zero", + "helper access to packet: test19, cls helper fail range zero", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, offsetof(struct __sk_buff, data)), @@ -3238,7 +3592,7 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, { - "helper access to packet: test19, pkt end as input", + "helper access to packet: test20, pkt end as input", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, offsetof(struct __sk_buff, data)), @@ -3263,7 +3617,7 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, { - "helper access to packet: test20, wrong reg", + "helper access to packet: test21, wrong reg", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, offsetof(struct __sk_buff, data)), @@ -3323,7 +3677,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr_unpriv = "R0 leaks addr", .result_unpriv = REJECT, .result = ACCEPT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, @@ -3347,7 +3701,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr_unpriv = "R0 leaks addr", .result_unpriv = REJECT, .result = ACCEPT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, @@ -3375,7 +3729,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr_unpriv = "R0 leaks addr", .result_unpriv = REJECT, .result = ACCEPT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, @@ -3416,9 +3770,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", .errstr = "R0 min value is outside of the array range", - .result_unpriv = REJECT, .result = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, @@ -3440,9 +3792,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", - .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.", - .result_unpriv = REJECT, + .errstr = "R0 unbounded memory access, make sure to bounds check any array access into a map", .result = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, @@ -3456,7 +3806,7 @@ static struct bpf_test tests[] = { BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), - BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0), BPF_MOV32_IMM(BPF_REG_2, MAX_ENTRIES), BPF_JMP_REG(BPF_JSGT, BPF_REG_2, BPF_REG_1, 1), BPF_MOV32_IMM(BPF_REG_1, 0), @@ -3467,8 +3817,8 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", - .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.", + .errstr_unpriv = "R0 leaks addr", + .errstr = "R0 unbounded memory access", .result_unpriv = REJECT, .result = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, @@ -3494,7 +3844,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr_unpriv = "R0 leaks addr", .errstr = "invalid access to map value, value_size=48 off=44 size=8", .result_unpriv = REJECT, .result = REJECT, @@ -3524,8 +3874,8 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3, 11 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", - .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.", + .errstr_unpriv = "R0 pointer += pointer", + .errstr = "R0 invalid mem access 'inv'", .result_unpriv = REJECT, .result = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, @@ -3667,34 +4017,6 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_SCHED_CLS }, { - "multiple registers share map_lookup_elem bad reg type", - .insns = { - BPF_MOV64_IMM(BPF_REG_1, 10), - BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8), - BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), - BPF_LD_MAP_FD(BPF_REG_1, 0), - BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, - BPF_FUNC_map_lookup_elem), - BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), - BPF_MOV64_REG(BPF_REG_3, BPF_REG_0), - BPF_MOV64_REG(BPF_REG_4, BPF_REG_0), - BPF_MOV64_REG(BPF_REG_5, BPF_REG_0), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), - BPF_MOV64_IMM(BPF_REG_1, 1), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), - BPF_MOV64_IMM(BPF_REG_1, 2), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_3, 0, 1), - BPF_ST_MEM(BPF_DW, BPF_REG_3, 0, 0), - BPF_MOV64_IMM(BPF_REG_1, 3), - BPF_EXIT_INSN(), - }, - .fixup_map1 = { 4 }, - .result = REJECT, - .errstr = "R3 invalid mem access 'inv'", - .prog_type = BPF_PROG_TYPE_SCHED_CLS - }, - { "invalid map access from else condition", .insns = { BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), @@ -3712,9 +4034,9 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr = "R0 unbounded memory access, make sure to bounds check any array access into a map", + .errstr = "R0 unbounded memory access", .result = REJECT, - .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr_unpriv = "R0 leaks addr", .result_unpriv = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, @@ -4092,7 +4414,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr = "invalid access to map value, value_size=48 off=0 size=-8", + .errstr = "R2 min value is negative", .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, @@ -4158,7 +4480,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr = "R1 min value is outside of the array range", + .errstr = "invalid access to map value, value_size=48 off=4 size=0", .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, @@ -4204,7 +4526,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr = "invalid access to map value, value_size=48 off=4 size=-8", + .errstr = "R2 min value is negative", .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, @@ -4226,7 +4548,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr = "R1 min value is outside of the array range", + .errstr = "R2 min value is negative", .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, @@ -4342,7 +4664,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr = "invalid access to map value, value_size=48 off=4 size=-8", + .errstr = "R2 min value is negative", .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, @@ -4365,7 +4687,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr = "R1 min value is outside of the array range", + .errstr = "R2 min value is negative", .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, @@ -4453,13 +4775,13 @@ static struct bpf_test tests[] = { BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3), - BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_2, 1), BPF_MOV64_IMM(BPF_REG_3, 0), BPF_EMIT_CALL(BPF_FUNC_probe_read), BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr = "R1 min value is negative, either use unsigned index or do a if (index >=0) check", + .errstr = "R1 unbounded memory access", .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, @@ -4490,6 +4812,246 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, { + "helper access to map: bounds check using <, good access", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JLT, BPF_REG_3, 32, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3), + BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to map: bounds check using <, bad access", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JLT, BPF_REG_3, 32, 4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3), + BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .result = REJECT, + .errstr = "R1 unbounded memory access", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to map: bounds check using <=, good access", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JLE, BPF_REG_3, 32, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3), + BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to map: bounds check using <=, bad access", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JLE, BPF_REG_3, 32, 4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3), + BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .result = REJECT, + .errstr = "R1 unbounded memory access", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to map: bounds check using s<, good access", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JSLT, BPF_REG_3, 32, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JSLT, BPF_REG_3, 0, -3), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3), + BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to map: bounds check using s<, good access 2", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JSLT, BPF_REG_3, 32, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JSLT, BPF_REG_3, -3, -3), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3), + BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to map: bounds check using s<, bad access", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JSLT, BPF_REG_3, 32, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JSLT, BPF_REG_3, -3, -3), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3), + BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .result = REJECT, + .errstr = "R1 min value is negative", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to map: bounds check using s<=, good access", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JSLE, BPF_REG_3, 32, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JSLE, BPF_REG_3, 0, -3), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3), + BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to map: bounds check using s<=, good access 2", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JSLE, BPF_REG_3, 32, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JSLE, BPF_REG_3, -3, -3), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3), + BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "helper access to map: bounds check using s<=, bad access", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JSLE, BPF_REG_3, 32, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_JMP_IMM(BPF_JSLE, BPF_REG_3, -3, -3), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3), + BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .result = REJECT, + .errstr = "R1 min value is negative", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { "map element value is preserved across register spilling", .insns = { BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), @@ -4579,7 +5141,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr_unpriv = "R0 leaks addr", .result = ACCEPT, .result_unpriv = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, @@ -4607,7 +5169,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr_unpriv = "R0 leaks addr", .result = ACCEPT, .result_unpriv = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, @@ -4626,7 +5188,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr_unpriv = "R0 bitwise operator &= on pointer", .errstr = "invalid mem access 'inv'", .result = REJECT, .result_unpriv = REJECT, @@ -4645,7 +5207,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr_unpriv = "R0 32-bit pointer arithmetic prohibited", .errstr = "invalid mem access 'inv'", .result = REJECT, .result_unpriv = REJECT, @@ -4664,7 +5226,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr_unpriv = "R0 pointer arithmetic with /= operator", .errstr = "invalid mem access 'inv'", .result = REJECT, .result_unpriv = REJECT, @@ -4707,10 +5269,8 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 invalid mem access 'inv'", .errstr = "R0 invalid mem access 'inv'", .result = REJECT, - .result_unpriv = REJECT, }, { "map element value is preserved across register spilling", @@ -4732,7 +5292,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr_unpriv = "R0 leaks addr", .result = ACCEPT, .result_unpriv = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, @@ -4914,7 +5474,8 @@ static struct bpf_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr = "R2 unbounded memory access", + /* because max wasn't checked, signed min is negative */ + .errstr = "R2 min value is negative, either use unsigned or 'var &= const'", .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, @@ -5063,6 +5624,20 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, { + "helper access to variable memory: size = 0 allowed on NULL", + .insns = { + BPF_MOV64_IMM(BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_MOV64_IMM(BPF_REG_5, 0), + BPF_EMIT_CALL(BPF_FUNC_csum_diff), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { "helper access to variable memory: size > 0 not allowed on NULL", .insns = { BPF_MOV64_IMM(BPF_REG_1, 0), @@ -5076,7 +5651,7 @@ static struct bpf_test tests[] = { BPF_EMIT_CALL(BPF_FUNC_csum_diff), BPF_EXIT_INSN(), }, - .errstr = "R1 type=imm expected=fp", + .errstr = "R1 type=inv expected=fp", .result = REJECT, .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, @@ -5161,7 +5736,7 @@ static struct bpf_test tests[] = { BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), - BPF_MOV64_IMM(BPF_REG_1, 6), + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), BPF_ALU64_IMM(BPF_AND, BPF_REG_1, -4), BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 2), BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), @@ -5170,10 +5745,8 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", - .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.", + .errstr = "R0 max value is outside of the array range", .result = REJECT, - .result_unpriv = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { @@ -5202,10 +5775,8 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", - .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.", + .errstr = "R0 max value is outside of the array range", .result = REJECT, - .result_unpriv = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { @@ -5252,7 +5823,7 @@ static struct bpf_test tests[] = { }, .fixup_map_in_map = { 3 }, .errstr = "R1 type=inv expected=map_ptr", - .errstr_unpriv = "R1 pointer arithmetic prohibited", + .errstr_unpriv = "R1 pointer arithmetic on CONST_PTR_TO_MAP prohibited", .result = REJECT, }, { @@ -5532,10 +6103,8 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", .errstr = "R0 min value is negative", .result = REJECT, - .result_unpriv = REJECT, }, { "bounds checks mixing signed and unsigned", @@ -5558,10 +6127,8 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", .errstr = "R0 min value is negative", .result = REJECT, - .result_unpriv = REJECT, }, { "bounds checks mixing signed and unsigned, variant 2", @@ -5586,10 +6153,8 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", .errstr = "R8 invalid mem access 'inv'", .result = REJECT, - .result_unpriv = REJECT, }, { "bounds checks mixing signed and unsigned, variant 3", @@ -5613,10 +6178,8 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", .errstr = "R8 invalid mem access 'inv'", .result = REJECT, - .result_unpriv = REJECT, }, { "bounds checks mixing signed and unsigned, variant 4", @@ -5639,10 +6202,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", - .errstr = "R0 min value is negative", - .result = REJECT, - .result_unpriv = REJECT, + .result = ACCEPT, }, { "bounds checks mixing signed and unsigned, variant 5", @@ -5666,10 +6226,8 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", - .errstr = "R0 invalid mem access", + .errstr = "R0 min value is negative", .result = REJECT, - .result_unpriv = REJECT, }, { "bounds checks mixing signed and unsigned, variant 6", @@ -5690,10 +6248,8 @@ static struct bpf_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R4 min value is negative, either use unsigned", .errstr = "R4 min value is negative, either use unsigned", .result = REJECT, - .result_unpriv = REJECT, }, { "bounds checks mixing signed and unsigned, variant 7", @@ -5716,10 +6272,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", - .errstr = "R0 min value is negative", - .result = REJECT, - .result_unpriv = REJECT, + .result = ACCEPT, }, { "bounds checks mixing signed and unsigned, variant 8", @@ -5730,32 +6283,6 @@ static struct bpf_test tests[] = { BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), - BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), - BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), - BPF_MOV64_IMM(BPF_REG_2, 1024 * 1024 * 1024 + 1), - BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 3), - BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2), - BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), - BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0), - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - }, - .fixup_map1 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", - .errstr = "R0 min value is negative", - .result = REJECT, - .result_unpriv = REJECT, - }, - { - "bounds checks mixing signed and unsigned, variant 9", - .insns = { - BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), - BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), - BPF_LD_MAP_FD(BPF_REG_1, 0), - BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, - BPF_FUNC_map_lookup_elem), BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8), BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16), @@ -5770,13 +6297,11 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", .errstr = "R0 min value is negative", .result = REJECT, - .result_unpriv = REJECT, }, { - "bounds checks mixing signed and unsigned, variant 10", + "bounds checks mixing signed and unsigned, variant 9", .insns = { BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), @@ -5798,13 +6323,10 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", - .errstr = "R0 min value is negative", - .result = REJECT, - .result_unpriv = REJECT, + .result = ACCEPT, }, { - "bounds checks mixing signed and unsigned, variant 11", + "bounds checks mixing signed and unsigned, variant 10", .insns = { BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), @@ -5826,13 +6348,11 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", .errstr = "R0 min value is negative", .result = REJECT, - .result_unpriv = REJECT, }, { - "bounds checks mixing signed and unsigned, variant 12", + "bounds checks mixing signed and unsigned, variant 11", .insns = { BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), @@ -5855,13 +6375,11 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", .errstr = "R0 min value is negative", .result = REJECT, - .result_unpriv = REJECT, }, { - "bounds checks mixing signed and unsigned, variant 13", + "bounds checks mixing signed and unsigned, variant 12", .insns = { BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), @@ -5883,13 +6401,11 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", .errstr = "R0 min value is negative", .result = REJECT, - .result_unpriv = REJECT, }, { - "bounds checks mixing signed and unsigned, variant 14", + "bounds checks mixing signed and unsigned, variant 13", .insns = { BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), @@ -5914,13 +6430,11 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", .errstr = "R0 min value is negative", .result = REJECT, - .result_unpriv = REJECT, }, { - "bounds checks mixing signed and unsigned, variant 15", + "bounds checks mixing signed and unsigned, variant 14", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_1, offsetof(struct __sk_buff, mark)), @@ -5946,13 +6460,11 @@ static struct bpf_test tests[] = { BPF_JMP_IMM(BPF_JA, 0, 0, -7), }, .fixup_map1 = { 4 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", .errstr = "R0 min value is negative", .result = REJECT, - .result_unpriv = REJECT, }, { - "bounds checks mixing signed and unsigned, variant 16", + "bounds checks mixing signed and unsigned, variant 15", .insns = { BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), @@ -5976,13 +6488,13 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr_unpriv = "R0 pointer comparison prohibited", .errstr = "R0 min value is negative", .result = REJECT, .result_unpriv = REJECT, }, { - "subtraction bounds (map value)", + "subtraction bounds (map value) variant 1", .insns = { BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), @@ -6004,10 +6516,118 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic prohibited", + .errstr = "R0 max value is outside of the array range", + .result = REJECT, + }, + { + "subtraction bounds (map value) variant 2", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JGT, BPF_REG_1, 0xff, 6), + BPF_LDX_MEM(BPF_B, BPF_REG_3, BPF_REG_0, 1), + BPF_JMP_IMM(BPF_JGT, BPF_REG_3, 0xff, 4), + BPF_ALU64_REG(BPF_SUB, BPF_REG_1, BPF_REG_3), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.", .result = REJECT, + }, + { + "variable-offset ctx access", + .insns = { + /* Get an unknown value */ + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0), + /* Make it small and 4-byte aligned */ + BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 4), + /* add it to skb. We now have either &skb->len or + * &skb->pkt_type, but we don't know which + */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_2), + /* dereference it */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0), + BPF_EXIT_INSN(), + }, + .errstr = "variable ctx access var_off=(0x0; 0x4)", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_LWT_IN, + }, + { + "variable-offset stack access", + .insns = { + /* Fill the top 8 bytes of the stack */ + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + /* Get an unknown value */ + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0), + /* Make it small and 4-byte aligned */ + BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 4), + BPF_ALU64_IMM(BPF_SUB, BPF_REG_2, 8), + /* add it to fp. We now have either fp-4 or fp-8, but + * we don't know which + */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_10), + /* dereference it */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0), + BPF_EXIT_INSN(), + }, + .errstr = "variable stack access var_off=(0xfffffffffffffff8; 0x4)", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_LWT_IN, + }, + { + "liveness pruning and write screening", + .insns = { + /* Get an unknown value */ + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0), + /* branch conditions teach us nothing about R2 */ + BPF_JMP_IMM(BPF_JGE, BPF_REG_2, 0, 1), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JGE, BPF_REG_2, 0, 1), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R0 !read_ok", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_LWT_IN, + }, + { + "varlen_map_value_access pruning", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0), + BPF_MOV32_IMM(BPF_REG_2, MAX_ENTRIES), + BPF_JMP_REG(BPF_JSGT, BPF_REG_2, BPF_REG_1, 1), + BPF_MOV32_IMM(BPF_REG_1, 0), + BPF_ALU32_IMM(BPF_LSH, BPF_REG_1, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_JMP_IMM(BPF_JA, 0, 0, 0), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, + offsetof(struct test_val, foo)), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 3 }, + .errstr_unpriv = "R0 leaks addr", + .errstr = "R0 unbounded memory access", .result_unpriv = REJECT, + .result = REJECT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, }; diff --git a/tools/testing/selftests/bpf/test_xdp_redirect.c b/tools/testing/selftests/bpf/test_xdp_redirect.c new file mode 100644 index 000000000000..ef9e704be140 --- /dev/null +++ b/tools/testing/selftests/bpf/test_xdp_redirect.c @@ -0,0 +1,28 @@ +/* Copyright (c) 2017 VMware + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ +#include <linux/bpf.h> +#include "bpf_helpers.h" + +int _version SEC("version") = 1; + +SEC("redirect_to_111") +int xdp_redirect_to_111(struct xdp_md *xdp) +{ + return bpf_redirect(111, 0); +} +SEC("redirect_to_222") +int xdp_redirect_to_222(struct xdp_md *xdp) +{ + return bpf_redirect(222, 0); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_xdp_redirect.sh b/tools/testing/selftests/bpf/test_xdp_redirect.sh new file mode 100755 index 000000000000..344a3656dea6 --- /dev/null +++ b/tools/testing/selftests/bpf/test_xdp_redirect.sh @@ -0,0 +1,59 @@ +#!/bin/sh +# Create 2 namespaces with two veth peers, and +# forward packets in-between using generic XDP +# +# NS1(veth11) NS2(veth22) +# | | +# | | +# (veth1, ------ (veth2, +# id:111) id:222) +# | xdp forwarding | +# ------------------ + +cleanup() +{ + if [ "$?" = "0" ]; then + echo "selftests: test_xdp_redirect [PASS]"; + else + echo "selftests: test_xdp_redirect [FAILED]"; + fi + + set +e + ip netns del ns1 2> /dev/null + ip netns del ns2 2> /dev/null +} + +ip link set dev lo xdpgeneric off 2>/dev/null > /dev/null +if [ $? -ne 0 ];then + echo "selftests: [SKIP] Could not run test without the ip xdpgeneric support" + exit 0 +fi +set -e + +ip netns add ns1 +ip netns add ns2 + +trap cleanup 0 2 3 6 9 + +ip link add veth1 index 111 type veth peer name veth11 +ip link add veth2 index 222 type veth peer name veth22 + +ip link set veth11 netns ns1 +ip link set veth22 netns ns2 + +ip link set veth1 up +ip link set veth2 up + +ip netns exec ns1 ip addr add 10.1.1.11/24 dev veth11 +ip netns exec ns2 ip addr add 10.1.1.22/24 dev veth22 + +ip netns exec ns1 ip link set dev veth11 up +ip netns exec ns2 ip link set dev veth22 up + +ip link set dev veth1 xdpgeneric obj test_xdp_redirect.o sec redirect_to_222 +ip link set dev veth2 xdpgeneric obj test_xdp_redirect.o sec redirect_to_111 + +ip netns exec ns1 ping -c 1 10.1.1.22 +ip netns exec ns2 ping -c 1 10.1.1.11 + +exit 0 diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index afe109e5508a..9801253e4802 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -1,3 +1,4 @@ +msg_zerocopy socket psock_fanout psock_tpacket diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index f6c9dbf478f8..de1f5772b878 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -3,11 +3,11 @@ CFLAGS = -Wall -Wl,--no-as-needed -O2 -g CFLAGS += -I../../../../usr/include/ -TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh +TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh TEST_GEN_FILES = socket TEST_GEN_FILES += psock_fanout psock_tpacket TEST_GEN_FILES += reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa -TEST_GEN_FILES += reuseport_dualstack +TEST_GEN_FILES += reuseport_dualstack msg_zerocopy include ../lib.mk diff --git a/tools/testing/selftests/net/msg_zerocopy.c b/tools/testing/selftests/net/msg_zerocopy.c new file mode 100644 index 000000000000..40232af5b023 --- /dev/null +++ b/tools/testing/selftests/net/msg_zerocopy.c @@ -0,0 +1,697 @@ +/* Evaluate MSG_ZEROCOPY + * + * Send traffic between two processes over one of the supported + * protocols and modes: + * + * PF_INET/PF_INET6 + * - SOCK_STREAM + * - SOCK_DGRAM + * - SOCK_DGRAM with UDP_CORK + * - SOCK_RAW + * - SOCK_RAW with IP_HDRINCL + * + * PF_PACKET + * - SOCK_DGRAM + * - SOCK_RAW + * + * Start this program on two connected hosts, one in send mode and + * the other with option '-r' to put it in receiver mode. + * + * If zerocopy mode ('-z') is enabled, the sender will verify that + * the kernel queues completions on the error queue for all zerocopy + * transfers. + */ + +#define _GNU_SOURCE + +#include <arpa/inet.h> +#include <error.h> +#include <errno.h> +#include <limits.h> +#include <linux/errqueue.h> +#include <linux/if_packet.h> +#include <linux/ipv6.h> +#include <linux/socket.h> +#include <linux/sockios.h> +#include <net/ethernet.h> +#include <net/if.h> +#include <netinet/ip.h> +#include <netinet/ip6.h> +#include <netinet/tcp.h> +#include <netinet/udp.h> +#include <poll.h> +#include <sched.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdint.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> +#include <sys/socket.h> +#include <sys/stat.h> +#include <sys/time.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <unistd.h> + +#ifndef SO_EE_ORIGIN_ZEROCOPY +#define SO_EE_ORIGIN_ZEROCOPY SO_EE_ORIGIN_UPAGE +#endif + +#ifndef SO_ZEROCOPY +#define SO_ZEROCOPY 60 +#endif + +#ifndef SO_EE_CODE_ZEROCOPY_COPIED +#define SO_EE_CODE_ZEROCOPY_COPIED 1 +#endif + +#ifndef MSG_ZEROCOPY +#define MSG_ZEROCOPY 0x4000000 +#endif + +static int cfg_cork; +static bool cfg_cork_mixed; +static int cfg_cpu = -1; /* default: pin to last cpu */ +static int cfg_family = PF_UNSPEC; +static int cfg_ifindex = 1; +static int cfg_payload_len; +static int cfg_port = 8000; +static bool cfg_rx; +static int cfg_runtime_ms = 4200; +static int cfg_verbose; +static int cfg_waittime_ms = 500; +static bool cfg_zerocopy; + +static socklen_t cfg_alen; +static struct sockaddr_storage cfg_dst_addr; +static struct sockaddr_storage cfg_src_addr; + +static char payload[IP_MAXPACKET]; +static long packets, bytes, completions, expected_completions; +static int zerocopied = -1; +static uint32_t next_completion; + +static unsigned long gettimeofday_ms(void) +{ + struct timeval tv; + + gettimeofday(&tv, NULL); + return (tv.tv_sec * 1000) + (tv.tv_usec / 1000); +} + +static uint16_t get_ip_csum(const uint16_t *start, int num_words) +{ + unsigned long sum = 0; + int i; + + for (i = 0; i < num_words; i++) + sum += start[i]; + + while (sum >> 16) + sum = (sum & 0xFFFF) + (sum >> 16); + + return ~sum; +} + +static int do_setcpu(int cpu) +{ + cpu_set_t mask; + + CPU_ZERO(&mask); + CPU_SET(cpu, &mask); + if (sched_setaffinity(0, sizeof(mask), &mask)) + error(1, 0, "setaffinity %d", cpu); + + if (cfg_verbose) + fprintf(stderr, "cpu: %u\n", cpu); + + return 0; +} + +static void do_setsockopt(int fd, int level, int optname, int val) +{ + if (setsockopt(fd, level, optname, &val, sizeof(val))) + error(1, errno, "setsockopt %d.%d: %d", level, optname, val); +} + +static int do_poll(int fd, int events) +{ + struct pollfd pfd; + int ret; + + pfd.events = events; + pfd.revents = 0; + pfd.fd = fd; + + ret = poll(&pfd, 1, cfg_waittime_ms); + if (ret == -1) + error(1, errno, "poll"); + + return ret && (pfd.revents & events); +} + +static int do_accept(int fd) +{ + int fda = fd; + + fd = accept(fda, NULL, NULL); + if (fd == -1) + error(1, errno, "accept"); + if (close(fda)) + error(1, errno, "close listen sock"); + + return fd; +} + +static bool do_sendmsg(int fd, struct msghdr *msg, bool do_zerocopy) +{ + int ret, len, i, flags; + + len = 0; + for (i = 0; i < msg->msg_iovlen; i++) + len += msg->msg_iov[i].iov_len; + + flags = MSG_DONTWAIT; + if (do_zerocopy) + flags |= MSG_ZEROCOPY; + + ret = sendmsg(fd, msg, flags); + if (ret == -1 && errno == EAGAIN) + return false; + if (ret == -1) + error(1, errno, "send"); + if (cfg_verbose && ret != len) + fprintf(stderr, "send: ret=%u != %u\n", ret, len); + + if (len) { + packets++; + bytes += ret; + if (do_zerocopy && ret) + expected_completions++; + } + + return true; +} + +static void do_sendmsg_corked(int fd, struct msghdr *msg) +{ + bool do_zerocopy = cfg_zerocopy; + int i, payload_len, extra_len; + + /* split up the packet. for non-multiple, make first buffer longer */ + payload_len = cfg_payload_len / cfg_cork; + extra_len = cfg_payload_len - (cfg_cork * payload_len); + + do_setsockopt(fd, IPPROTO_UDP, UDP_CORK, 1); + + for (i = 0; i < cfg_cork; i++) { + + /* in mixed-frags mode, alternate zerocopy and copy frags + * start with non-zerocopy, to ensure attach later works + */ + if (cfg_cork_mixed) + do_zerocopy = (i & 1); + + msg->msg_iov[0].iov_len = payload_len + extra_len; + extra_len = 0; + + do_sendmsg(fd, msg, do_zerocopy); + } + + do_setsockopt(fd, IPPROTO_UDP, UDP_CORK, 0); +} + +static int setup_iph(struct iphdr *iph, uint16_t payload_len) +{ + struct sockaddr_in *daddr = (void *) &cfg_dst_addr; + struct sockaddr_in *saddr = (void *) &cfg_src_addr; + + memset(iph, 0, sizeof(*iph)); + + iph->version = 4; + iph->tos = 0; + iph->ihl = 5; + iph->ttl = 2; + iph->saddr = saddr->sin_addr.s_addr; + iph->daddr = daddr->sin_addr.s_addr; + iph->protocol = IPPROTO_EGP; + iph->tot_len = htons(sizeof(*iph) + payload_len); + iph->check = get_ip_csum((void *) iph, iph->ihl << 1); + + return sizeof(*iph); +} + +static int setup_ip6h(struct ipv6hdr *ip6h, uint16_t payload_len) +{ + struct sockaddr_in6 *daddr = (void *) &cfg_dst_addr; + struct sockaddr_in6 *saddr = (void *) &cfg_src_addr; + + memset(ip6h, 0, sizeof(*ip6h)); + + ip6h->version = 6; + ip6h->payload_len = htons(payload_len); + ip6h->nexthdr = IPPROTO_EGP; + ip6h->hop_limit = 2; + ip6h->saddr = saddr->sin6_addr; + ip6h->daddr = daddr->sin6_addr; + + return sizeof(*ip6h); +} + +static void setup_sockaddr(int domain, const char *str_addr, void *sockaddr) +{ + struct sockaddr_in6 *addr6 = (void *) sockaddr; + struct sockaddr_in *addr4 = (void *) sockaddr; + + switch (domain) { + case PF_INET: + addr4->sin_family = AF_INET; + addr4->sin_port = htons(cfg_port); + if (inet_pton(AF_INET, str_addr, &(addr4->sin_addr)) != 1) + error(1, 0, "ipv4 parse error: %s", str_addr); + break; + case PF_INET6: + addr6->sin6_family = AF_INET6; + addr6->sin6_port = htons(cfg_port); + if (inet_pton(AF_INET6, str_addr, &(addr6->sin6_addr)) != 1) + error(1, 0, "ipv6 parse error: %s", str_addr); + break; + default: + error(1, 0, "illegal domain"); + } +} + +static int do_setup_tx(int domain, int type, int protocol) +{ + int fd; + + fd = socket(domain, type, protocol); + if (fd == -1) + error(1, errno, "socket t"); + + do_setsockopt(fd, SOL_SOCKET, SO_SNDBUF, 1 << 21); + if (cfg_zerocopy) + do_setsockopt(fd, SOL_SOCKET, SO_ZEROCOPY, 1); + + if (domain != PF_PACKET) + if (connect(fd, (void *) &cfg_dst_addr, cfg_alen)) + error(1, errno, "connect"); + + return fd; +} + +static bool do_recv_completion(int fd) +{ + struct sock_extended_err *serr; + struct msghdr msg = {}; + struct cmsghdr *cm; + uint32_t hi, lo, range; + int ret, zerocopy; + char control[100]; + + msg.msg_control = control; + msg.msg_controllen = sizeof(control); + + ret = recvmsg(fd, &msg, MSG_ERRQUEUE); + if (ret == -1 && errno == EAGAIN) + return false; + if (ret == -1) + error(1, errno, "recvmsg notification"); + if (msg.msg_flags & MSG_CTRUNC) + error(1, errno, "recvmsg notification: truncated"); + + cm = CMSG_FIRSTHDR(&msg); + if (!cm) + error(1, 0, "cmsg: no cmsg"); + if (!((cm->cmsg_level == SOL_IP && cm->cmsg_type == IP_RECVERR) || + (cm->cmsg_level == SOL_IPV6 && cm->cmsg_type == IPV6_RECVERR) || + (cm->cmsg_level == SOL_PACKET && cm->cmsg_type == PACKET_TX_TIMESTAMP))) + error(1, 0, "serr: wrong type: %d.%d", + cm->cmsg_level, cm->cmsg_type); + + serr = (void *) CMSG_DATA(cm); + if (serr->ee_origin != SO_EE_ORIGIN_ZEROCOPY) + error(1, 0, "serr: wrong origin: %u", serr->ee_origin); + if (serr->ee_errno != 0) + error(1, 0, "serr: wrong error code: %u", serr->ee_errno); + + hi = serr->ee_data; + lo = serr->ee_info; + range = hi - lo + 1; + + /* Detect notification gaps. These should not happen often, if at all. + * Gaps can occur due to drops, reordering and retransmissions. + */ + if (lo != next_completion) + fprintf(stderr, "gap: %u..%u does not append to %u\n", + lo, hi, next_completion); + next_completion = hi + 1; + + zerocopy = !(serr->ee_code & SO_EE_CODE_ZEROCOPY_COPIED); + if (zerocopied == -1) + zerocopied = zerocopy; + else if (zerocopied != zerocopy) { + fprintf(stderr, "serr: inconsistent\n"); + zerocopied = zerocopy; + } + + if (cfg_verbose >= 2) + fprintf(stderr, "completed: %u (h=%u l=%u)\n", + range, hi, lo); + + completions += range; + return true; +} + +/* Read all outstanding messages on the errqueue */ +static void do_recv_completions(int fd) +{ + while (do_recv_completion(fd)) {} +} + +/* Wait for all remaining completions on the errqueue */ +static void do_recv_remaining_completions(int fd) +{ + int64_t tstop = gettimeofday_ms() + cfg_waittime_ms; + + while (completions < expected_completions && + gettimeofday_ms() < tstop) { + if (do_poll(fd, POLLERR)) + do_recv_completions(fd); + } + + if (completions < expected_completions) + fprintf(stderr, "missing notifications: %lu < %lu\n", + completions, expected_completions); +} + +static void do_tx(int domain, int type, int protocol) +{ + struct iovec iov[3] = { {0} }; + struct sockaddr_ll laddr; + struct msghdr msg = {0}; + struct ethhdr eth; + union { + struct ipv6hdr ip6h; + struct iphdr iph; + } nh; + uint64_t tstop; + int fd; + + fd = do_setup_tx(domain, type, protocol); + + if (domain == PF_PACKET) { + uint16_t proto = cfg_family == PF_INET ? ETH_P_IP : ETH_P_IPV6; + + /* sock_raw passes ll header as data */ + if (type == SOCK_RAW) { + memset(eth.h_dest, 0x06, ETH_ALEN); + memset(eth.h_source, 0x02, ETH_ALEN); + eth.h_proto = htons(proto); + iov[0].iov_base = ð + iov[0].iov_len = sizeof(eth); + msg.msg_iovlen++; + } + + /* both sock_raw and sock_dgram expect name */ + memset(&laddr, 0, sizeof(laddr)); + laddr.sll_family = AF_PACKET; + laddr.sll_ifindex = cfg_ifindex; + laddr.sll_protocol = htons(proto); + laddr.sll_halen = ETH_ALEN; + + memset(laddr.sll_addr, 0x06, ETH_ALEN); + + msg.msg_name = &laddr; + msg.msg_namelen = sizeof(laddr); + } + + /* packet and raw sockets with hdrincl must pass network header */ + if (domain == PF_PACKET || protocol == IPPROTO_RAW) { + if (cfg_family == PF_INET) + iov[1].iov_len = setup_iph(&nh.iph, cfg_payload_len); + else + iov[1].iov_len = setup_ip6h(&nh.ip6h, cfg_payload_len); + + iov[1].iov_base = (void *) &nh; + msg.msg_iovlen++; + } + + iov[2].iov_base = payload; + iov[2].iov_len = cfg_payload_len; + msg.msg_iovlen++; + msg.msg_iov = &iov[3 - msg.msg_iovlen]; + + tstop = gettimeofday_ms() + cfg_runtime_ms; + do { + if (cfg_cork) + do_sendmsg_corked(fd, &msg); + else + do_sendmsg(fd, &msg, cfg_zerocopy); + + while (!do_poll(fd, POLLOUT)) { + if (cfg_zerocopy) + do_recv_completions(fd); + } + + } while (gettimeofday_ms() < tstop); + + if (cfg_zerocopy) + do_recv_remaining_completions(fd); + + if (close(fd)) + error(1, errno, "close"); + + fprintf(stderr, "tx=%lu (%lu MB) txc=%lu zc=%c\n", + packets, bytes >> 20, completions, + zerocopied == 1 ? 'y' : 'n'); +} + +static int do_setup_rx(int domain, int type, int protocol) +{ + int fd; + + /* If tx over PF_PACKET, rx over PF_INET(6)/SOCK_RAW, + * to recv the only copy of the packet, not a clone + */ + if (domain == PF_PACKET) + error(1, 0, "Use PF_INET/SOCK_RAW to read"); + + if (type == SOCK_RAW && protocol == IPPROTO_RAW) + error(1, 0, "IPPROTO_RAW: not supported on Rx"); + + fd = socket(domain, type, protocol); + if (fd == -1) + error(1, errno, "socket r"); + + do_setsockopt(fd, SOL_SOCKET, SO_RCVBUF, 1 << 21); + do_setsockopt(fd, SOL_SOCKET, SO_RCVLOWAT, 1 << 16); + do_setsockopt(fd, SOL_SOCKET, SO_REUSEPORT, 1); + + if (bind(fd, (void *) &cfg_dst_addr, cfg_alen)) + error(1, errno, "bind"); + + if (type == SOCK_STREAM) { + if (listen(fd, 1)) + error(1, errno, "listen"); + fd = do_accept(fd); + } + + return fd; +} + +/* Flush all outstanding bytes for the tcp receive queue */ +static void do_flush_tcp(int fd) +{ + int ret; + + /* MSG_TRUNC flushes up to len bytes */ + ret = recv(fd, NULL, 1 << 21, MSG_TRUNC | MSG_DONTWAIT); + if (ret == -1 && errno == EAGAIN) + return; + if (ret == -1) + error(1, errno, "flush"); + if (!ret) + return; + + packets++; + bytes += ret; +} + +/* Flush all outstanding datagrams. Verify first few bytes of each. */ +static void do_flush_datagram(int fd, int type) +{ + int ret, off = 0; + char buf[64]; + + /* MSG_TRUNC will return full datagram length */ + ret = recv(fd, buf, sizeof(buf), MSG_DONTWAIT | MSG_TRUNC); + if (ret == -1 && errno == EAGAIN) + return; + + /* raw ipv4 return with header, raw ipv6 without */ + if (cfg_family == PF_INET && type == SOCK_RAW) { + off += sizeof(struct iphdr); + ret -= sizeof(struct iphdr); + } + + if (ret == -1) + error(1, errno, "recv"); + if (ret != cfg_payload_len) + error(1, 0, "recv: ret=%u != %u", ret, cfg_payload_len); + if (ret > sizeof(buf) - off) + ret = sizeof(buf) - off; + if (memcmp(buf + off, payload, ret)) + error(1, 0, "recv: data mismatch"); + + packets++; + bytes += cfg_payload_len; +} + +static void do_rx(int domain, int type, int protocol) +{ + uint64_t tstop; + int fd; + + fd = do_setup_rx(domain, type, protocol); + + tstop = gettimeofday_ms() + cfg_runtime_ms; + do { + if (type == SOCK_STREAM) + do_flush_tcp(fd); + else + do_flush_datagram(fd, type); + + do_poll(fd, POLLIN); + + } while (gettimeofday_ms() < tstop); + + if (close(fd)) + error(1, errno, "close"); + + fprintf(stderr, "rx=%lu (%lu MB)\n", packets, bytes >> 20); +} + +static void do_test(int domain, int type, int protocol) +{ + int i; + + if (cfg_cork && (domain == PF_PACKET || type != SOCK_DGRAM)) + error(1, 0, "can only cork udp sockets"); + + do_setcpu(cfg_cpu); + + for (i = 0; i < IP_MAXPACKET; i++) + payload[i] = 'a' + (i % 26); + + if (cfg_rx) + do_rx(domain, type, protocol); + else + do_tx(domain, type, protocol); +} + +static void usage(const char *filepath) +{ + error(1, 0, "Usage: %s [options] <test>", filepath); +} + +static void parse_opts(int argc, char **argv) +{ + const int max_payload_len = sizeof(payload) - + sizeof(struct ipv6hdr) - + sizeof(struct tcphdr) - + 40 /* max tcp options */; + int c; + + cfg_payload_len = max_payload_len; + + while ((c = getopt(argc, argv, "46c:C:D:i:mp:rs:S:t:vz")) != -1) { + switch (c) { + case '4': + if (cfg_family != PF_UNSPEC) + error(1, 0, "Pass one of -4 or -6"); + cfg_family = PF_INET; + cfg_alen = sizeof(struct sockaddr_in); + break; + case '6': + if (cfg_family != PF_UNSPEC) + error(1, 0, "Pass one of -4 or -6"); + cfg_family = PF_INET6; + cfg_alen = sizeof(struct sockaddr_in6); + break; + case 'c': + cfg_cork = strtol(optarg, NULL, 0); + break; + case 'C': + cfg_cpu = strtol(optarg, NULL, 0); + break; + case 'D': + setup_sockaddr(cfg_family, optarg, &cfg_dst_addr); + break; + case 'i': + cfg_ifindex = if_nametoindex(optarg); + if (cfg_ifindex == 0) + error(1, errno, "invalid iface: %s", optarg); + break; + case 'm': + cfg_cork_mixed = true; + break; + case 'p': + cfg_port = htons(strtoul(optarg, NULL, 0)); + break; + case 'r': + cfg_rx = true; + break; + case 's': + cfg_payload_len = strtoul(optarg, NULL, 0); + break; + case 'S': + setup_sockaddr(cfg_family, optarg, &cfg_src_addr); + break; + case 't': + cfg_runtime_ms = 200 + strtoul(optarg, NULL, 10) * 1000; + break; + case 'v': + cfg_verbose++; + break; + case 'z': + cfg_zerocopy = true; + break; + } + } + + if (cfg_payload_len > max_payload_len) + error(1, 0, "-s: payload exceeds max (%d)", max_payload_len); + if (cfg_cork_mixed && (!cfg_zerocopy || !cfg_cork)) + error(1, 0, "-m: cork_mixed requires corking and zerocopy"); + + if (optind != argc - 1) + usage(argv[0]); +} + +int main(int argc, char **argv) +{ + const char *cfg_test; + + parse_opts(argc, argv); + + cfg_test = argv[argc - 1]; + + if (!strcmp(cfg_test, "packet")) + do_test(PF_PACKET, SOCK_RAW, 0); + else if (!strcmp(cfg_test, "packet_dgram")) + do_test(PF_PACKET, SOCK_DGRAM, 0); + else if (!strcmp(cfg_test, "raw")) + do_test(cfg_family, SOCK_RAW, IPPROTO_EGP); + else if (!strcmp(cfg_test, "raw_hdrincl")) + do_test(cfg_family, SOCK_RAW, IPPROTO_RAW); + else if (!strcmp(cfg_test, "tcp")) + do_test(cfg_family, SOCK_STREAM, 0); + else if (!strcmp(cfg_test, "udp")) + do_test(cfg_family, SOCK_DGRAM, 0); + else + error(1, 0, "unknown cfg_test %s", cfg_test); + + return 0; +} diff --git a/tools/testing/selftests/net/msg_zerocopy.sh b/tools/testing/selftests/net/msg_zerocopy.sh new file mode 100755 index 000000000000..d571d213418d --- /dev/null +++ b/tools/testing/selftests/net/msg_zerocopy.sh @@ -0,0 +1,112 @@ +#!/bin/bash +# +# Send data between two processes across namespaces +# Run twice: once without and once with zerocopy + +set -e + +readonly DEV="veth0" +readonly DEV_MTU=65535 +readonly BIN="./msg_zerocopy" + +readonly RAND="$(mktemp -u XXXXXX)" +readonly NSPREFIX="ns-${RAND}" +readonly NS1="${NSPREFIX}1" +readonly NS2="${NSPREFIX}2" + +readonly SADDR4='192.168.1.1' +readonly DADDR4='192.168.1.2' +readonly SADDR6='fd::1' +readonly DADDR6='fd::2' + +readonly path_sysctl_mem="net.core.optmem_max" + +# Argument parsing +if [[ "$#" -lt "2" ]]; then + echo "Usage: $0 [4|6] [tcp|udp|raw|raw_hdrincl|packet|packet_dgram] <args>" + exit 1 +fi + +readonly IP="$1" +shift +readonly TXMODE="$1" +shift +readonly EXTRA_ARGS="$@" + +# Argument parsing: configure addresses +if [[ "${IP}" == "4" ]]; then + readonly SADDR="${SADDR4}" + readonly DADDR="${DADDR4}" +elif [[ "${IP}" == "6" ]]; then + readonly SADDR="${SADDR6}" + readonly DADDR="${DADDR6}" +else + echo "Invalid IP version ${IP}" + exit 1 +fi + +# Argument parsing: select receive mode +# +# This differs from send mode for +# - packet: use raw recv, because packet receives skb clones +# - raw_hdrinc: use raw recv, because hdrincl is a tx-only option +case "${TXMODE}" in +'packet' | 'packet_dgram' | 'raw_hdrincl') + RXMODE='raw' + ;; +*) + RXMODE="${TXMODE}" + ;; +esac + +# Start of state changes: install cleanup handler +save_sysctl_mem="$(sysctl -n ${path_sysctl_mem})" + +cleanup() { + ip netns del "${NS2}" + ip netns del "${NS1}" + sysctl -w -q "${path_sysctl_mem}=${save_sysctl_mem}" +} + +trap cleanup EXIT + +# Configure system settings +sysctl -w -q "${path_sysctl_mem}=1000000" + +# Create virtual ethernet pair between network namespaces +ip netns add "${NS1}" +ip netns add "${NS2}" + +ip link add "${DEV}" mtu "${DEV_MTU}" netns "${NS1}" type veth \ + peer name "${DEV}" mtu "${DEV_MTU}" netns "${NS2}" + +# Bring the devices up +ip -netns "${NS1}" link set "${DEV}" up +ip -netns "${NS2}" link set "${DEV}" up + +# Set fixed MAC addresses on the devices +ip -netns "${NS1}" link set dev "${DEV}" address 02:02:02:02:02:02 +ip -netns "${NS2}" link set dev "${DEV}" address 06:06:06:06:06:06 + +# Add fixed IP addresses to the devices +ip -netns "${NS1}" addr add 192.168.1.1/24 dev "${DEV}" +ip -netns "${NS2}" addr add 192.168.1.2/24 dev "${DEV}" +ip -netns "${NS1}" addr add fd::1/64 dev "${DEV}" nodad +ip -netns "${NS2}" addr add fd::2/64 dev "${DEV}" nodad + +# Optionally disable sg or csum offload to test edge cases +# ip netns exec "${NS1}" ethtool -K "${DEV}" sg off + +do_test() { + local readonly ARGS="$1" + + echo "ipv${IP} ${TXMODE} ${ARGS}" + ip netns exec "${NS2}" "${BIN}" "-${IP}" -i "${DEV}" -t 2 -C 2 -S "${SADDR}" -D "${DADDR}" ${ARGS} -r "${RXMODE}" & + sleep 0.2 + ip netns exec "${NS1}" "${BIN}" "-${IP}" -i "${DEV}" -t 1 -C 3 -S "${SADDR}" -D "${DADDR}" ${ARGS} "${TXMODE}" + wait +} + +do_test "${EXTRA_ARGS}" +do_test "-z ${EXTRA_ARGS}" +echo ok diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh new file mode 100755 index 000000000000..57b5ff576240 --- /dev/null +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -0,0 +1,272 @@ +#!/bin/sh +# +# This test is for checking rtnetlink callpaths, and get as much coverage as possible. +# +# set -e + +devdummy="test-dummy0" +ret=0 + +# set global exit status, but never reset nonzero one. +check_err() +{ + if [ $ret -eq 0 ]; then + ret=$1 + fi +} + +kci_add_dummy() +{ + ip link add name "$devdummy" type dummy + check_err $? + ip link set "$devdummy" up + check_err $? +} + +kci_del_dummy() +{ + ip link del dev "$devdummy" + check_err $? +} + +# add a bridge with vlans on top +kci_test_bridge() +{ + devbr="test-br0" + vlandev="testbr-vlan1" + + ret=0 + ip link add name "$devbr" type bridge + check_err $? + + ip link set dev "$devdummy" master "$devbr" + check_err $? + + ip link set "$devbr" up + check_err $? + + ip link add link "$devbr" name "$vlandev" type vlan id 1 + check_err $? + ip addr add dev "$vlandev" 10.200.7.23/30 + check_err $? + ip -6 addr add dev "$vlandev" dead:42::1234/64 + check_err $? + ip -d link > /dev/null + check_err $? + ip r s t all > /dev/null + check_err $? + ip -6 addr del dev "$vlandev" dead:42::1234/64 + check_err $? + + ip link del dev "$vlandev" + check_err $? + ip link del dev "$devbr" + check_err $? + + if [ $ret -ne 0 ];then + echo "FAIL: bridge setup" + return 1 + fi + echo "PASS: bridge setup" + +} + +kci_test_gre() +{ + gredev=neta + rem=10.42.42.1 + loc=10.0.0.1 + + ret=0 + ip tunnel add $gredev mode gre remote $rem local $loc ttl 1 + check_err $? + ip link set $gredev up + check_err $? + ip addr add 10.23.7.10 dev $gredev + check_err $? + ip route add 10.23.8.0/30 dev $gredev + check_err $? + ip addr add dev "$devdummy" 10.23.7.11/24 + check_err $? + ip link > /dev/null + check_err $? + ip addr > /dev/null + check_err $? + ip addr del dev "$devdummy" 10.23.7.11/24 + check_err $? + + ip link del $gredev + check_err $? + + if [ $ret -ne 0 ];then + echo "FAIL: gre tunnel endpoint" + return 1 + fi + echo "PASS: gre tunnel endpoint" +} + +# tc uses rtnetlink too, for full tc testing +# please see tools/testing/selftests/tc-testing. +kci_test_tc() +{ + dev=lo + ret=0 + + tc qdisc add dev "$dev" root handle 1: htb + check_err $? + tc class add dev "$dev" parent 1: classid 1:10 htb rate 1mbit + check_err $? + tc filter add dev "$dev" parent 1:0 prio 5 handle ffe: protocol ip u32 divisor 256 + check_err $? + tc filter add dev "$dev" parent 1:0 prio 5 handle ffd: protocol ip u32 divisor 256 + check_err $? + tc filter add dev "$dev" parent 1:0 prio 5 handle ffc: protocol ip u32 divisor 256 + check_err $? + tc filter add dev "$dev" protocol ip parent 1: prio 5 handle ffe:2:3 u32 ht ffe:2: match ip src 10.0.0.3 flowid 1:10 + check_err $? + tc filter add dev "$dev" protocol ip parent 1: prio 5 handle ffe:2:2 u32 ht ffe:2: match ip src 10.0.0.2 flowid 1:10 + check_err $? + tc filter show dev "$dev" parent 1:0 > /dev/null + check_err $? + tc filter del dev "$dev" protocol ip parent 1: prio 5 handle ffe:2:3 u32 + check_err $? + tc filter show dev "$dev" parent 1:0 > /dev/null + check_err $? + tc qdisc del dev "$dev" root handle 1: htb + check_err $? + + if [ $ret -ne 0 ];then + echo "FAIL: tc htb hierarchy" + return 1 + fi + echo "PASS: tc htb hierarchy" + +} + +kci_test_polrouting() +{ + ret=0 + ip rule add fwmark 1 lookup 100 + check_err $? + ip route add local 0.0.0.0/0 dev lo table 100 + check_err $? + ip r s t all > /dev/null + check_err $? + ip rule del fwmark 1 lookup 100 + check_err $? + ip route del local 0.0.0.0/0 dev lo table 100 + check_err $? + + if [ $ret -ne 0 ];then + echo "FAIL: policy route test" + return 1 + fi + echo "PASS: policy routing" +} + +kci_test_route_get() +{ + ret=0 + + ip route get 127.0.0.1 > /dev/null + check_err $? + ip route get 127.0.0.1 dev "$devdummy" > /dev/null + check_err $? + ip route get ::1 > /dev/null + check_err $? + ip route get fe80::1 dev "$devdummy" > /dev/null + check_err $? + ip route get 127.0.0.1 from 127.0.0.1 oif lo tos 0x1 mark 0x1 > /dev/null + check_err $? + ip route get ::1 from ::1 iif lo oif lo tos 0x1 mark 0x1 > /dev/null + check_err $? + ip addr add dev "$devdummy" 10.23.7.11/24 + check_err $? + ip route get 10.23.7.11 from 10.23.7.12 iif "$devdummy" > /dev/null + check_err $? + ip addr del dev "$devdummy" 10.23.7.11/24 + check_err $? + + if [ $ret -ne 0 ];then + echo "FAIL: route get" + return 1 + fi + + echo "PASS: route get" +} + +kci_test_addrlabel() +{ + ret=0 + + ip addrlabel add prefix dead::/64 dev lo label 1 + check_err $? + + ip addrlabel list |grep -q "prefix dead::/64 dev lo label 1" + check_err $? + + ip addrlabel del prefix dead::/64 dev lo label 1 2> /dev/null + check_err $? + + ip addrlabel add prefix dead::/64 label 1 2> /dev/null + check_err $? + + ip addrlabel del prefix dead::/64 label 1 2> /dev/null + check_err $? + + # concurrent add/delete + for i in $(seq 1 1000); do + ip addrlabel add prefix 1c3::/64 label 12345 2>/dev/null + done & + + for i in $(seq 1 1000); do + ip addrlabel del prefix 1c3::/64 label 12345 2>/dev/null + done + + wait + + ip addrlabel del prefix 1c3::/64 label 12345 2>/dev/null + + if [ $ret -ne 0 ];then + echo "FAIL: ipv6 addrlabel" + return 1 + fi + + echo "PASS: ipv6 addrlabel" +} + +kci_test_rtnl() +{ + kci_add_dummy + if [ $ret -ne 0 ];then + echo "FAIL: cannot add dummy interface" + return 1 + fi + + kci_test_polrouting + kci_test_route_get + kci_test_tc + kci_test_gre + kci_test_bridge + kci_test_addrlabel + + kci_del_dummy +} + +#check for needed privileges +if [ "$(id -u)" -ne 0 ];then + echo "SKIP: Need root privileges" + exit 0 +fi + +for x in ip tc;do + $x -Version 2>/dev/null >/dev/null + if [ $? -ne 0 ];then + echo "SKIP: Could not run test without the $x tool" + exit 0 + fi +done + +kci_test_rtnl + +exit $ret diff --git a/tools/testing/selftests/networking/timestamping/.gitignore b/tools/testing/selftests/networking/timestamping/.gitignore index 9e69e982fb38..d9355035e746 100644 --- a/tools/testing/selftests/networking/timestamping/.gitignore +++ b/tools/testing/selftests/networking/timestamping/.gitignore @@ -1,3 +1,4 @@ timestamping +rxtimestamp txtimestamp hwtstamp_config diff --git a/tools/testing/selftests/networking/timestamping/Makefile b/tools/testing/selftests/networking/timestamping/Makefile index ccbb9edbbbb9..92fb8ee917c5 100644 --- a/tools/testing/selftests/networking/timestamping/Makefile +++ b/tools/testing/selftests/networking/timestamping/Makefile @@ -1,4 +1,6 @@ -TEST_PROGS := hwtstamp_config timestamping txtimestamp +CFLAGS += -I../../../../../usr/include + +TEST_PROGS := hwtstamp_config rxtimestamp timestamping txtimestamp all: $(TEST_PROGS) diff --git a/tools/testing/selftests/networking/timestamping/rxtimestamp.c b/tools/testing/selftests/networking/timestamping/rxtimestamp.c new file mode 100644 index 000000000000..00f286661dcd --- /dev/null +++ b/tools/testing/selftests/networking/timestamping/rxtimestamp.c @@ -0,0 +1,389 @@ +#include <errno.h> +#include <error.h> +#include <getopt.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> + +#include <sys/time.h> +#include <sys/socket.h> +#include <sys/select.h> +#include <sys/ioctl.h> +#include <arpa/inet.h> +#include <net/if.h> + +#include <asm/types.h> +#include <linux/net_tstamp.h> +#include <linux/errqueue.h> + +#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) + +struct options { + int so_timestamp; + int so_timestampns; + int so_timestamping; +}; + +struct tstamps { + bool tstamp; + bool tstampns; + bool swtstamp; + bool hwtstamp; +}; + +struct socket_type { + char *friendly_name; + int type; + int protocol; + bool enabled; +}; + +struct test_case { + struct options sockopt; + struct tstamps expected; + bool enabled; +}; + +struct sof_flag { + int mask; + char *name; +}; + +static struct sof_flag sof_flags[] = { +#define SOF_FLAG(f) { f, #f } + SOF_FLAG(SOF_TIMESTAMPING_SOFTWARE), + SOF_FLAG(SOF_TIMESTAMPING_RX_SOFTWARE), + SOF_FLAG(SOF_TIMESTAMPING_RX_HARDWARE), +}; + +static struct socket_type socket_types[] = { + { "ip", SOCK_RAW, IPPROTO_EGP }, + { "udp", SOCK_DGRAM, IPPROTO_UDP }, + { "tcp", SOCK_STREAM, IPPROTO_TCP }, +}; + +static struct test_case test_cases[] = { + { {}, {} }, + { + { so_timestamp: 1 }, + { tstamp: true } + }, + { + { so_timestampns: 1 }, + { tstampns: true } + }, + { + { so_timestamp: 1, so_timestampns: 1 }, + { tstampns: true } + }, + { + { so_timestamping: SOF_TIMESTAMPING_RX_SOFTWARE }, + {} + }, + { + /* Loopback device does not support hw timestamps. */ + { so_timestamping: SOF_TIMESTAMPING_RX_HARDWARE }, + {} + }, + { + { so_timestamping: SOF_TIMESTAMPING_SOFTWARE }, + {} + }, + { + { so_timestamping: SOF_TIMESTAMPING_RX_SOFTWARE + | SOF_TIMESTAMPING_RX_HARDWARE }, + {} + }, + { + { so_timestamping: SOF_TIMESTAMPING_SOFTWARE + | SOF_TIMESTAMPING_RX_SOFTWARE }, + { swtstamp: true } + }, + { + { so_timestamp: 1, so_timestamping: SOF_TIMESTAMPING_SOFTWARE + | SOF_TIMESTAMPING_RX_SOFTWARE }, + { tstamp: true, swtstamp: true } + }, +}; + +static struct option long_options[] = { + { "list_tests", no_argument, 0, 'l' }, + { "test_num", required_argument, 0, 'n' }, + { "op_size", required_argument, 0, 's' }, + { "tcp", no_argument, 0, 't' }, + { "udp", no_argument, 0, 'u' }, + { "ip", no_argument, 0, 'i' }, +}; + +static int next_port = 19999; +static int op_size = 10 * 1024; + +void print_test_case(struct test_case *t) +{ + int f = 0; + + printf("sockopts {"); + if (t->sockopt.so_timestamp) + printf(" SO_TIMESTAMP "); + if (t->sockopt.so_timestampns) + printf(" SO_TIMESTAMPNS "); + if (t->sockopt.so_timestamping) { + printf(" SO_TIMESTAMPING: {"); + for (f = 0; f < ARRAY_SIZE(sof_flags); f++) + if (t->sockopt.so_timestamping & sof_flags[f].mask) + printf(" %s |", sof_flags[f].name); + printf("}"); + } + printf("} expected cmsgs: {"); + if (t->expected.tstamp) + printf(" SCM_TIMESTAMP "); + if (t->expected.tstampns) + printf(" SCM_TIMESTAMPNS "); + if (t->expected.swtstamp || t->expected.hwtstamp) { + printf(" SCM_TIMESTAMPING {"); + if (t->expected.swtstamp) + printf("0"); + if (t->expected.swtstamp && t->expected.hwtstamp) + printf(","); + if (t->expected.hwtstamp) + printf("2"); + printf("}"); + } + printf("}\n"); +} + +void do_send(int src) +{ + int r; + char *buf = malloc(op_size); + + memset(buf, 'z', op_size); + r = write(src, buf, op_size); + if (r < 0) + error(1, errno, "Failed to sendmsg"); + + free(buf); +} + +bool do_recv(int rcv, int read_size, struct tstamps expected) +{ + const int CMSG_SIZE = 1024; + + struct scm_timestamping *ts; + struct tstamps actual = {}; + char cmsg_buf[CMSG_SIZE]; + struct iovec recv_iov; + struct cmsghdr *cmsg; + bool failed = false; + struct msghdr hdr; + int flags = 0; + int r; + + memset(&hdr, 0, sizeof(hdr)); + hdr.msg_iov = &recv_iov; + hdr.msg_iovlen = 1; + recv_iov.iov_base = malloc(read_size); + recv_iov.iov_len = read_size; + + hdr.msg_control = cmsg_buf; + hdr.msg_controllen = sizeof(cmsg_buf); + + r = recvmsg(rcv, &hdr, flags); + if (r < 0) + error(1, errno, "Failed to recvmsg"); + if (r != read_size) + error(1, 0, "Only received %d bytes of payload.", r); + + if (hdr.msg_flags & (MSG_TRUNC | MSG_CTRUNC)) + error(1, 0, "Message was truncated."); + + for (cmsg = CMSG_FIRSTHDR(&hdr); cmsg != NULL; + cmsg = CMSG_NXTHDR(&hdr, cmsg)) { + if (cmsg->cmsg_level != SOL_SOCKET) + error(1, 0, "Unexpected cmsg_level %d", + cmsg->cmsg_level); + switch (cmsg->cmsg_type) { + case SCM_TIMESTAMP: + actual.tstamp = true; + break; + case SCM_TIMESTAMPNS: + actual.tstampns = true; + break; + case SCM_TIMESTAMPING: + ts = (struct scm_timestamping *)CMSG_DATA(cmsg); + actual.swtstamp = !!ts->ts[0].tv_sec; + if (ts->ts[1].tv_sec != 0) + error(0, 0, "ts[1] should not be set."); + actual.hwtstamp = !!ts->ts[2].tv_sec; + break; + default: + error(1, 0, "Unexpected cmsg_type %d", cmsg->cmsg_type); + } + } + +#define VALIDATE(field) \ + do { \ + if (expected.field != actual.field) { \ + if (expected.field) \ + error(0, 0, "Expected " #field " to be set."); \ + else \ + error(0, 0, \ + "Expected " #field " to not be set."); \ + failed = true; \ + } \ + } while (0) + + VALIDATE(tstamp); + VALIDATE(tstampns); + VALIDATE(swtstamp); + VALIDATE(hwtstamp); +#undef VALIDATE + + free(recv_iov.iov_base); + + return failed; +} + +void config_so_flags(int rcv, struct options o) +{ + int on = 1; + + if (setsockopt(rcv, SOL_SOCKET, SO_REUSEADDR, &on, sizeof(on)) < 0) + error(1, errno, "Failed to enable SO_REUSEADDR"); + + if (o.so_timestamp && + setsockopt(rcv, SOL_SOCKET, SO_TIMESTAMP, + &o.so_timestamp, sizeof(o.so_timestamp)) < 0) + error(1, errno, "Failed to enable SO_TIMESTAMP"); + + if (o.so_timestampns && + setsockopt(rcv, SOL_SOCKET, SO_TIMESTAMPNS, + &o.so_timestampns, sizeof(o.so_timestampns)) < 0) + error(1, errno, "Failed to enable SO_TIMESTAMPNS"); + + if (o.so_timestamping && + setsockopt(rcv, SOL_SOCKET, SO_TIMESTAMPING, + &o.so_timestamping, sizeof(o.so_timestamping)) < 0) + error(1, errno, "Failed to set SO_TIMESTAMPING"); +} + +bool run_test_case(struct socket_type s, struct test_case t) +{ + int port = (s.type == SOCK_RAW) ? 0 : next_port++; + int read_size = op_size; + struct sockaddr_in addr; + bool failed = false; + int src, dst, rcv; + + src = socket(AF_INET, s.type, s.protocol); + if (src < 0) + error(1, errno, "Failed to open src socket"); + + dst = socket(AF_INET, s.type, s.protocol); + if (dst < 0) + error(1, errno, "Failed to open dst socket"); + + memset(&addr, 0, sizeof(addr)); + addr.sin_family = AF_INET; + addr.sin_addr.s_addr = htonl(INADDR_LOOPBACK); + addr.sin_port = htons(port); + + if (bind(dst, (struct sockaddr *)&addr, sizeof(addr)) < 0) + error(1, errno, "Failed to bind to port %d", port); + + if (s.type == SOCK_STREAM && (listen(dst, 1) < 0)) + error(1, errno, "Failed to listen"); + + if (connect(src, (struct sockaddr *)&addr, sizeof(addr)) < 0) + error(1, errno, "Failed to connect"); + + if (s.type == SOCK_STREAM) { + rcv = accept(dst, NULL, NULL); + if (rcv < 0) + error(1, errno, "Failed to accept"); + close(dst); + } else { + rcv = dst; + } + + config_so_flags(rcv, t.sockopt); + usleep(20000); /* setsockopt for SO_TIMESTAMPING is asynchronous */ + do_send(src); + + if (s.type == SOCK_RAW) + read_size += 20; /* for IP header */ + failed = do_recv(rcv, read_size, t.expected); + + close(rcv); + close(src); + + return failed; +} + +int main(int argc, char **argv) +{ + bool all_protocols = true; + bool all_tests = true; + int arg_index = 0; + int failures = 0; + int s, t; + char opt; + + while ((opt = getopt_long(argc, argv, "", long_options, + &arg_index)) != -1) { + switch (opt) { + case 'l': + for (t = 0; t < ARRAY_SIZE(test_cases); t++) { + printf("%d\t", t); + print_test_case(&test_cases[t]); + } + return 0; + case 'n': + t = atoi(optarg); + if (t > ARRAY_SIZE(test_cases)) + error(1, 0, "Invalid test case: %d", t); + all_tests = false; + test_cases[t].enabled = true; + break; + case 's': + op_size = atoi(optarg); + break; + case 't': + all_protocols = false; + socket_types[2].enabled = true; + break; + case 'u': + all_protocols = false; + socket_types[1].enabled = true; + break; + case 'i': + all_protocols = false; + socket_types[0].enabled = true; + break; + default: + error(1, 0, "Failed to parse parameters."); + } + } + + for (s = 0; s < ARRAY_SIZE(socket_types); s++) { + if (!all_protocols && !socket_types[s].enabled) + continue; + + printf("Testing %s...\n", socket_types[s].friendly_name); + for (t = 0; t < ARRAY_SIZE(test_cases); t++) { + if (!all_tests && !test_cases[t].enabled) + continue; + + printf("Starting testcase %d...\n", t); + if (run_test_case(socket_types[s], test_cases[t])) { + failures++; + printf("FAILURE in test case "); + print_test_case(&test_cases[t]); + } + } + } + if (!failures) + printf("PASSED.\n"); + return failures; +} diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/tests.json b/tools/testing/selftests/tc-testing/tc-tests/actions/tests.json index af519bc97a8e..6973bdc5b5bf 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/tests.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/tests.json @@ -1111,5 +1111,55 @@ "teardown": [ "$TC actions flush action gact" ] + }, + { + "id": "a568", + "name": "Add action with ife type", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ], + "$TC actions add action ife encode type 0xDEAD index 1" + ], + "cmdUnderTest": "$TC actions get action ife index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "type 0xDEAD", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "b983", + "name": "Add action without ife type", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ], + "$TC actions add action ife encode index 1" + ], + "cmdUnderTest": "$TC actions get action ife index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "type 0xED3E", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] } ]
\ No newline at end of file |