diff options
Diffstat (limited to 'tools/testing/selftests')
96 files changed, 3477 insertions, 915 deletions
diff --git a/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c b/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c new file mode 100644 index 000000000000..0c365f36c73b --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c @@ -0,0 +1,135 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2024 Meta + +#include <test_progs.h> +#include "network_helpers.h" +#include "sock_iter_batch.skel.h" + +#define TEST_NS "sock_iter_batch_netns" + +static const int nr_soreuse = 4; + +static void do_test(int sock_type, bool onebyone) +{ + int err, i, nread, to_read, total_read, iter_fd = -1; + int first_idx, second_idx, indices[nr_soreuse]; + struct bpf_link *link = NULL; + struct sock_iter_batch *skel; + int *fds[2] = {}; + + skel = sock_iter_batch__open(); + if (!ASSERT_OK_PTR(skel, "sock_iter_batch__open")) + return; + + /* Prepare 2 buckets of sockets in the kernel hashtable */ + for (i = 0; i < ARRAY_SIZE(fds); i++) { + int local_port; + + fds[i] = start_reuseport_server(AF_INET6, sock_type, "::1", 0, 0, + nr_soreuse); + if (!ASSERT_OK_PTR(fds[i], "start_reuseport_server")) + goto done; + local_port = get_socket_local_port(*fds[i]); + if (!ASSERT_GE(local_port, 0, "get_socket_local_port")) + goto done; + skel->rodata->ports[i] = ntohs(local_port); + } + + err = sock_iter_batch__load(skel); + if (!ASSERT_OK(err, "sock_iter_batch__load")) + goto done; + + link = bpf_program__attach_iter(sock_type == SOCK_STREAM ? + skel->progs.iter_tcp_soreuse : + skel->progs.iter_udp_soreuse, + NULL); + if (!ASSERT_OK_PTR(link, "bpf_program__attach_iter")) + goto done; + + iter_fd = bpf_iter_create(bpf_link__fd(link)); + if (!ASSERT_GE(iter_fd, 0, "bpf_iter_create")) + goto done; + + /* Test reading a bucket (either from fds[0] or fds[1]). + * Only read "nr_soreuse - 1" number of sockets + * from a bucket and leave one socket out from + * that bucket on purpose. + */ + to_read = (nr_soreuse - 1) * sizeof(*indices); + total_read = 0; + first_idx = -1; + do { + nread = read(iter_fd, indices, onebyone ? sizeof(*indices) : to_read); + if (nread <= 0 || nread % sizeof(*indices)) + break; + total_read += nread; + + if (first_idx == -1) + first_idx = indices[0]; + for (i = 0; i < nread / sizeof(*indices); i++) + ASSERT_EQ(indices[i], first_idx, "first_idx"); + } while (total_read < to_read); + ASSERT_EQ(nread, onebyone ? sizeof(*indices) : to_read, "nread"); + ASSERT_EQ(total_read, to_read, "total_read"); + + free_fds(fds[first_idx], nr_soreuse); + fds[first_idx] = NULL; + + /* Read the "whole" second bucket */ + to_read = nr_soreuse * sizeof(*indices); + total_read = 0; + second_idx = !first_idx; + do { + nread = read(iter_fd, indices, onebyone ? sizeof(*indices) : to_read); + if (nread <= 0 || nread % sizeof(*indices)) + break; + total_read += nread; + + for (i = 0; i < nread / sizeof(*indices); i++) + ASSERT_EQ(indices[i], second_idx, "second_idx"); + } while (total_read <= to_read); + ASSERT_EQ(nread, 0, "nread"); + /* Both so_reuseport ports should be in different buckets, so + * total_read must equal to the expected to_read. + * + * For a very unlikely case, both ports collide at the same bucket, + * the bucket offset (i.e. 3) will be skipped and it cannot + * expect the to_read number of bytes. + */ + if (skel->bss->bucket[0] != skel->bss->bucket[1]) + ASSERT_EQ(total_read, to_read, "total_read"); + +done: + for (i = 0; i < ARRAY_SIZE(fds); i++) + free_fds(fds[i], nr_soreuse); + if (iter_fd < 0) + close(iter_fd); + bpf_link__destroy(link); + sock_iter_batch__destroy(skel); +} + +void test_sock_iter_batch(void) +{ + struct nstoken *nstoken = NULL; + + SYS_NOFAIL("ip netns del " TEST_NS " &> /dev/null"); + SYS(done, "ip netns add %s", TEST_NS); + SYS(done, "ip -net %s link set dev lo up", TEST_NS); + + nstoken = open_netns(TEST_NS); + if (!ASSERT_OK_PTR(nstoken, "open_netns")) + goto done; + + if (test__start_subtest("tcp")) { + do_test(SOCK_STREAM, true); + do_test(SOCK_STREAM, false); + } + if (test__start_subtest("udp")) { + do_test(SOCK_DGRAM, true); + do_test(SOCK_DGRAM, false); + } + close_netns(nstoken); + +done: + SYS_NOFAIL("ip netns del " TEST_NS " &> /dev/null"); +} diff --git a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c index 67d4ef9e62b3..e905cbaf6b3d 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c +++ b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c @@ -47,6 +47,19 @@ static void subtest_ctx_arg_rewrite(void) struct btf *btf = NULL; __u32 info_len = sizeof(info); int err, fd, i; + struct btf *kern_btf = NULL; + + kern_btf = btf__load_vmlinux_btf(); + if (!ASSERT_OK_PTR(kern_btf, "kern_btf_load")) + return; + + /* simple detection of kernel native arg:ctx tag support */ + if (btf__find_by_name_kind(kern_btf, "bpf_subprog_arg_info", BTF_KIND_STRUCT) > 0) { + test__skip(); + btf__free(kern_btf); + return; + } + btf__free(kern_btf); skel = test_global_func_ctx_args__open(); if (!ASSERT_OK_PTR(skel, "skel_open")) diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h index 1bdc680b0e0e..e8bd4b7b5ef7 100644 --- a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h +++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h @@ -72,6 +72,8 @@ #define inet_rcv_saddr sk.__sk_common.skc_rcv_saddr #define inet_dport sk.__sk_common.skc_dport +#define udp_portaddr_hash inet.sk.__sk_common.skc_u16hashes[1] + #define ir_loc_addr req.__req_common.skc_rcv_saddr #define ir_num req.__req_common.skc_num #define ir_rmt_addr req.__req_common.skc_daddr @@ -85,6 +87,7 @@ #define sk_rmem_alloc sk_backlog.rmem_alloc #define sk_refcnt __sk_common.skc_refcnt #define sk_state __sk_common.skc_state +#define sk_net __sk_common.skc_net #define sk_v6_daddr __sk_common.skc_v6_daddr #define sk_v6_rcv_saddr __sk_common.skc_v6_rcv_saddr #define sk_flags __sk_common.skc_flags diff --git a/tools/testing/selftests/bpf/progs/sock_iter_batch.c b/tools/testing/selftests/bpf/progs/sock_iter_batch.c new file mode 100644 index 000000000000..ffbbfe1fa1c1 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/sock_iter_batch.c @@ -0,0 +1,91 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2024 Meta + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> +#include <bpf/bpf_endian.h> +#include "bpf_tracing_net.h" +#include "bpf_kfuncs.h" + +#define ATTR __always_inline +#include "test_jhash.h" + +static bool ipv6_addr_loopback(const struct in6_addr *a) +{ + return (a->s6_addr32[0] | a->s6_addr32[1] | + a->s6_addr32[2] | (a->s6_addr32[3] ^ bpf_htonl(1))) == 0; +} + +volatile const __u16 ports[2]; +unsigned int bucket[2]; + +SEC("iter/tcp") +int iter_tcp_soreuse(struct bpf_iter__tcp *ctx) +{ + struct sock *sk = (struct sock *)ctx->sk_common; + struct inet_hashinfo *hinfo; + unsigned int hash; + struct net *net; + int idx; + + if (!sk) + return 0; + + sk = bpf_rdonly_cast(sk, bpf_core_type_id_kernel(struct sock)); + if (sk->sk_family != AF_INET6 || + sk->sk_state != TCP_LISTEN || + !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr)) + return 0; + + if (sk->sk_num == ports[0]) + idx = 0; + else if (sk->sk_num == ports[1]) + idx = 1; + else + return 0; + + /* bucket selection as in inet_lhash2_bucket_sk() */ + net = sk->sk_net.net; + hash = jhash2(sk->sk_v6_rcv_saddr.s6_addr32, 4, net->hash_mix); + hash ^= sk->sk_num; + hinfo = net->ipv4.tcp_death_row.hashinfo; + bucket[idx] = hash & hinfo->lhash2_mask; + bpf_seq_write(ctx->meta->seq, &idx, sizeof(idx)); + + return 0; +} + +#define udp_sk(ptr) container_of(ptr, struct udp_sock, inet.sk) + +SEC("iter/udp") +int iter_udp_soreuse(struct bpf_iter__udp *ctx) +{ + struct sock *sk = (struct sock *)ctx->udp_sk; + struct udp_table *udptable; + int idx; + + if (!sk) + return 0; + + sk = bpf_rdonly_cast(sk, bpf_core_type_id_kernel(struct sock)); + if (sk->sk_family != AF_INET6 || + !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr)) + return 0; + + if (sk->sk_num == ports[0]) + idx = 0; + else if (sk->sk_num == ports[1]) + idx = 1; + else + return 0; + + /* bucket selection as in udp_hashslot2() */ + udptable = sk->sk_net.net->ipv4.udp_table; + bucket[idx] = udp_sk(sk)->udp_portaddr_hash & udptable->mask; + bpf_seq_write(ctx->meta->seq, &idx, sizeof(idx)); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_jhash.h b/tools/testing/selftests/bpf/progs/test_jhash.h index c300734d26f6..ef53559bbbdf 100644 --- a/tools/testing/selftests/bpf/progs/test_jhash.h +++ b/tools/testing/selftests/bpf/progs/test_jhash.h @@ -69,3 +69,34 @@ u32 jhash(const void *key, u32 length, u32 initval) return c; } + +static __always_inline u32 jhash2(const u32 *k, u32 length, u32 initval) +{ + u32 a, b, c; + + /* Set up the internal state */ + a = b = c = JHASH_INITVAL + (length<<2) + initval; + + /* Handle most of the key */ + while (length > 3) { + a += k[0]; + b += k[1]; + c += k[2]; + __jhash_mix(a, b, c); + length -= 3; + k += 3; + } + + /* Handle the last 3 u32's */ + switch (length) { + case 3: c += k[2]; + case 2: b += k[1]; + case 1: a += k[0]; + __jhash_final(a, b, c); + break; + case 0: /* Nothing left to add */ + break; + } + + return c; +} diff --git a/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c b/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c index 9eeb2d89cda8..67dddd941891 100644 --- a/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c +++ b/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c @@ -3,6 +3,7 @@ #include <vmlinux.h> #include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> #include "bpf_misc.h" #include "xdp_metadata.h" #include "bpf_kfuncs.h" @@ -138,25 +139,182 @@ __weak int subprog_ctx_tag(void *ctx __arg_ctx) return bpf_get_stack(ctx, stack, sizeof(stack), 0); } +__weak int raw_tp_canonical(struct bpf_raw_tracepoint_args *ctx __arg_ctx) +{ + return 0; +} + +__weak int raw_tp_u64_array(u64 *ctx __arg_ctx) +{ + return 0; +} + SEC("?raw_tp") __success __log_level(2) int arg_tag_ctx_raw_tp(void *ctx) { - return subprog_ctx_tag(ctx); + return subprog_ctx_tag(ctx) + raw_tp_canonical(ctx) + raw_tp_u64_array(ctx); +} + +SEC("?raw_tp.w") +__success __log_level(2) +int arg_tag_ctx_raw_tp_writable(void *ctx) +{ + return subprog_ctx_tag(ctx) + raw_tp_canonical(ctx) + raw_tp_u64_array(ctx); +} + +SEC("?tp_btf/sys_enter") +__success __log_level(2) +int arg_tag_ctx_raw_tp_btf(void *ctx) +{ + return subprog_ctx_tag(ctx) + raw_tp_canonical(ctx) + raw_tp_u64_array(ctx); +} + +struct whatever { }; + +__weak int tp_whatever(struct whatever *ctx __arg_ctx) +{ + return 0; } SEC("?tp") __success __log_level(2) int arg_tag_ctx_tp(void *ctx) { - return subprog_ctx_tag(ctx); + return subprog_ctx_tag(ctx) + tp_whatever(ctx); +} + +__weak int kprobe_subprog_pt_regs(struct pt_regs *ctx __arg_ctx) +{ + return 0; +} + +__weak int kprobe_subprog_typedef(bpf_user_pt_regs_t *ctx __arg_ctx) +{ + return 0; } SEC("?kprobe") __success __log_level(2) int arg_tag_ctx_kprobe(void *ctx) { - return subprog_ctx_tag(ctx); + return subprog_ctx_tag(ctx) + + kprobe_subprog_pt_regs(ctx) + + kprobe_subprog_typedef(ctx); +} + +__weak int perf_subprog_regs( +#if defined(bpf_target_riscv) + struct user_regs_struct *ctx __arg_ctx +#elif defined(bpf_target_s390) + /* user_pt_regs typedef is anonymous struct, so only `void *` works */ + void *ctx __arg_ctx +#elif defined(bpf_target_loongarch) || defined(bpf_target_arm64) || defined(bpf_target_powerpc) + struct user_pt_regs *ctx __arg_ctx +#else + struct pt_regs *ctx __arg_ctx +#endif +) +{ + return 0; +} + +__weak int perf_subprog_typedef(bpf_user_pt_regs_t *ctx __arg_ctx) +{ + return 0; +} + +__weak int perf_subprog_canonical(struct bpf_perf_event_data *ctx __arg_ctx) +{ + return 0; +} + +SEC("?perf_event") +__success __log_level(2) +int arg_tag_ctx_perf(void *ctx) +{ + return subprog_ctx_tag(ctx) + + perf_subprog_regs(ctx) + + perf_subprog_typedef(ctx) + + perf_subprog_canonical(ctx); +} + +__weak int iter_subprog_void(void *ctx __arg_ctx) +{ + return 0; +} + +__weak int iter_subprog_typed(struct bpf_iter__task *ctx __arg_ctx) +{ + return 0; +} + +SEC("?iter/task") +__success __log_level(2) +int arg_tag_ctx_iter_task(struct bpf_iter__task *ctx) +{ + return (iter_subprog_void(ctx) + iter_subprog_typed(ctx)) & 1; +} + +__weak int tracing_subprog_void(void *ctx __arg_ctx) +{ + return 0; +} + +__weak int tracing_subprog_u64(u64 *ctx __arg_ctx) +{ + return 0; +} + +int acc; + +SEC("?fentry/" SYS_PREFIX "sys_nanosleep") +__success __log_level(2) +int BPF_PROG(arg_tag_ctx_fentry) +{ + acc += tracing_subprog_void(ctx) + tracing_subprog_u64(ctx); + return 0; +} + +SEC("?fexit/" SYS_PREFIX "sys_nanosleep") +__success __log_level(2) +int BPF_PROG(arg_tag_ctx_fexit) +{ + acc += tracing_subprog_void(ctx) + tracing_subprog_u64(ctx); + return 0; +} + +SEC("?fmod_ret/" SYS_PREFIX "sys_nanosleep") +__success __log_level(2) +int BPF_PROG(arg_tag_ctx_fmod_ret) +{ + return tracing_subprog_void(ctx) + tracing_subprog_u64(ctx); +} + +SEC("?lsm/bpf") +__success __log_level(2) +int BPF_PROG(arg_tag_ctx_lsm) +{ + return tracing_subprog_void(ctx) + tracing_subprog_u64(ctx); +} + +SEC("?struct_ops/test_1") +__success __log_level(2) +int BPF_PROG(arg_tag_ctx_struct_ops) +{ + return tracing_subprog_void(ctx) + tracing_subprog_u64(ctx); +} + +SEC(".struct_ops") +struct bpf_dummy_ops dummy_1 = { + .test_1 = (void *)arg_tag_ctx_struct_ops, +}; + +SEC("?syscall") +__success __log_level(2) +int arg_tag_ctx_syscall(void *ctx) +{ + return tracing_subprog_void(ctx) + tracing_subprog_u64(ctx) + tp_whatever(ctx); } __weak int subprog_dynptr(struct bpf_dynptr *dptr) diff --git a/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c b/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c index 71814a753216..a9ab37d3b9e2 100644 --- a/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c +++ b/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c @@ -146,4 +146,23 @@ l0_%=: exit; \ : __clobber_all); } +SEC("flow_dissector") +__description("flow_keys illegal alu op with variable offset") +__failure __msg("R7 pointer arithmetic on flow_keys prohibited") +__naked void flow_keys_illegal_variable_offset_alu(void) +{ + asm volatile(" \ + r6 = r1; \ + r7 = *(u64*)(r6 + %[flow_keys_off]); \ + r8 = 8; \ + r8 /= 1; \ + r8 &= 8; \ + r7 += r8; \ + r0 = *(u64*)(r7 + 0); \ + exit; \ +" : + : __imm_const(flow_keys_off, offsetof(struct __sk_buff, flow_keys)) + : __clobber_all); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/drivers/net/bonding/bond_options.sh b/tools/testing/selftests/drivers/net/bonding/bond_options.sh index c54d1697f439..d508486cc0bd 100755 --- a/tools/testing/selftests/drivers/net/bonding/bond_options.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond_options.sh @@ -162,7 +162,7 @@ prio_arp() local mode=$1 for primary_reselect in 0 1 2; do - prio_test "mode active-backup arp_interval 100 arp_ip_target ${g_ip4} primary eth1 primary_reselect $primary_reselect" + prio_test "mode $mode arp_interval 100 arp_ip_target ${g_ip4} primary eth1 primary_reselect $primary_reselect" log_test "prio" "$mode arp_ip_target primary_reselect $primary_reselect" done } @@ -178,7 +178,7 @@ prio_ns() fi for primary_reselect in 0 1 2; do - prio_test "mode active-backup arp_interval 100 ns_ip6_target ${g_ip6} primary eth1 primary_reselect $primary_reselect" + prio_test "mode $mode arp_interval 100 ns_ip6_target ${g_ip6} primary eth1 primary_reselect $primary_reselect" log_test "prio" "$mode ns_ip6_target primary_reselect $primary_reselect" done } @@ -194,9 +194,9 @@ prio() for mode in $modes; do prio_miimon $mode - prio_arp $mode - prio_ns $mode done + prio_arp "active-backup" + prio_ns "active-backup" } arp_validate_test() diff --git a/tools/testing/selftests/drivers/net/bonding/config b/tools/testing/selftests/drivers/net/bonding/config index 70638fa50b2c..899d7fb6ea8e 100644 --- a/tools/testing/selftests/drivers/net/bonding/config +++ b/tools/testing/selftests/drivers/net/bonding/config @@ -1,2 +1,10 @@ CONFIG_BONDING=y +CONFIG_BRIDGE=y +CONFIG_DUMMY=y +CONFIG_IPV6=y CONFIG_MACVLAN=y +CONFIG_NET_ACT_GACT=y +CONFIG_NET_CLS_FLOWER=y +CONFIG_NET_SCH_INGRESS=y +CONFIG_NLMON=y +CONFIG_VETH=y diff --git a/tools/testing/selftests/drivers/net/bonding/mode-1-recovery-updelay.sh b/tools/testing/selftests/drivers/net/bonding/mode-1-recovery-updelay.sh index ad4c845a4ac7..b76bf5030952 100755 --- a/tools/testing/selftests/drivers/net/bonding/mode-1-recovery-updelay.sh +++ b/tools/testing/selftests/drivers/net/bonding/mode-1-recovery-updelay.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 # Regression Test: diff --git a/tools/testing/selftests/drivers/net/bonding/mode-2-recovery-updelay.sh b/tools/testing/selftests/drivers/net/bonding/mode-2-recovery-updelay.sh index 2330d37453f9..8c2619002147 100755 --- a/tools/testing/selftests/drivers/net/bonding/mode-2-recovery-updelay.sh +++ b/tools/testing/selftests/drivers/net/bonding/mode-2-recovery-updelay.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 # Regression Test: diff --git a/tools/testing/selftests/drivers/net/bonding/settings b/tools/testing/selftests/drivers/net/bonding/settings index 6091b45d226b..79b65bdf05db 100644 --- a/tools/testing/selftests/drivers/net/bonding/settings +++ b/tools/testing/selftests/drivers/net/bonding/settings @@ -1 +1 @@ -timeout=120 +timeout=1200 diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh index 42ce602d8d49..0f0f4f05807c 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh @@ -40,7 +40,6 @@ # | + $swp1 $swp3 + + $swp4 | # | | iPOOL1 iPOOL0 | | iPOOL2 | # | | ePOOL4 ePOOL5 | | ePOOL4 | -# | | 1Gbps | | 1Gbps | # | | PFC:enabled=1 | | PFC:enabled=1 | # | +-|----------------------|-+ +-|------------------------+ | # | | + $swp1.111 $swp3.111 + | | + $swp4.111 | | @@ -120,6 +119,9 @@ h2_destroy() switch_create() { + local lanes_swp4 + local pg1_size + # pools # ----- @@ -229,7 +231,20 @@ switch_create() dcb pfc set dev $swp4 prio-pfc all:off 1:on # PG0 will get autoconfigured to Xoff, give PG1 arbitrarily 100K, which # is (-2*MTU) about 80K of delay provision. - dcb buffer set dev $swp4 buffer-size all:0 1:$_100KB + pg1_size=$_100KB + + setup_wait_dev_with_timeout $swp4 + + lanes_swp4=$(ethtool $swp4 | grep 'Lanes:') + lanes_swp4=${lanes_swp4#*"Lanes: "} + + # 8-lane ports use two buffers among which the configured buffer + # is split, so double the size to get twice (20K + 80K). + if [[ $lanes_swp4 -eq 8 ]]; then + pg1_size=$((pg1_size * 2)) + fi + + dcb buffer set dev $swp4 buffer-size all:0 1:$pg1_size # bridges # ------- diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh index fb850e0ec837..616d3581419c 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh @@ -10,7 +10,8 @@ lib_dir=$(dirname $0)/../../../../net/forwarding ALL_TESTS="single_mask_test identical_filters_test two_masks_test \ multiple_masks_test ctcam_edge_cases_test delta_simple_test \ delta_two_masks_one_key_test delta_simple_rehash_test \ - bloom_simple_test bloom_complex_test bloom_delta_test" + bloom_simple_test bloom_complex_test bloom_delta_test \ + max_erp_entries_test max_group_size_test" NUM_NETIFS=2 source $lib_dir/lib.sh source $lib_dir/tc_common.sh @@ -983,6 +984,109 @@ bloom_delta_test() log_test "bloom delta test ($tcflags)" } +max_erp_entries_test() +{ + # The number of eRP entries is limited. Once the maximum number of eRPs + # has been reached, filters cannot be added. This test verifies that + # when this limit is reached, inserstion fails without crashing. + + RET=0 + + local num_masks=32 + local num_regions=15 + local chain_failed + local mask_failed + local ret + + if [[ "$tcflags" != "skip_sw" ]]; then + return 0; + fi + + for ((i=1; i < $num_regions; i++)); do + for ((j=$num_masks; j >= 0; j--)); do + tc filter add dev $h2 ingress chain $i protocol ip \ + pref $i handle $j flower $tcflags \ + dst_ip 192.1.0.0/$j &> /dev/null + ret=$? + + if [ $ret -ne 0 ]; then + chain_failed=$i + mask_failed=$j + break 2 + fi + done + done + + # We expect to exceed the maximum number of eRP entries, so that + # insertion eventually fails. Otherwise, the test should be adjusted to + # add more filters. + check_fail $ret "expected to exceed number of eRP entries" + + for ((; i >= 1; i--)); do + for ((j=0; j <= $num_masks; j++)); do + tc filter del dev $h2 ingress chain $i protocol ip \ + pref $i handle $j flower &> /dev/null + done + done + + log_test "max eRP entries test ($tcflags). " \ + "max chain $chain_failed, mask $mask_failed" +} + +max_group_size_test() +{ + # The number of ACLs in an ACL group is limited. Once the maximum + # number of ACLs has been reached, filters cannot be added. This test + # verifies that when this limit is reached, insertion fails without + # crashing. + + RET=0 + + local num_acls=32 + local max_size + local ret + + if [[ "$tcflags" != "skip_sw" ]]; then + return 0; + fi + + for ((i=1; i < $num_acls; i++)); do + if [[ $(( i % 2 )) == 1 ]]; then + tc filter add dev $h2 ingress pref $i proto ipv4 \ + flower $tcflags dst_ip 198.51.100.1/32 \ + ip_proto tcp tcp_flags 0x01/0x01 \ + action drop &> /dev/null + else + tc filter add dev $h2 ingress pref $i proto ipv6 \ + flower $tcflags dst_ip 2001:db8:1::1/128 \ + action drop &> /dev/null + fi + + ret=$? + [[ $ret -ne 0 ]] && max_size=$((i - 1)) && break + done + + # We expect to exceed the maximum number of ACLs in a group, so that + # insertion eventually fails. Otherwise, the test should be adjusted to + # add more filters. + check_fail $ret "expected to exceed number of ACLs in a group" + + for ((; i >= 1; i--)); do + if [[ $(( i % 2 )) == 1 ]]; then + tc filter del dev $h2 ingress pref $i proto ipv4 \ + flower $tcflags dst_ip 198.51.100.1/32 \ + ip_proto tcp tcp_flags 0x01/0x01 \ + action drop &> /dev/null + else + tc filter del dev $h2 ingress pref $i proto ipv6 \ + flower $tcflags dst_ip 2001:db8:1::1/128 \ + action drop &> /dev/null + fi + done + + log_test "max ACL group size test ($tcflags). max size $max_size" +} + setup_prepare() { h1=${NETIFS[p1]} diff --git a/tools/testing/selftests/drivers/net/netdevsim/config b/tools/testing/selftests/drivers/net/netdevsim/config new file mode 100644 index 000000000000..adf45a3a78b4 --- /dev/null +++ b/tools/testing/selftests/drivers/net/netdevsim/config @@ -0,0 +1,10 @@ +CONFIG_DUMMY=y +CONFIG_GENEVE=m +CONFIG_IPV6=y +CONFIG_NETDEVSIM=m +CONFIG_NET_SCH_MQPRIO=y +CONFIG_NET_SCH_MULTIQ=y +CONFIG_NET_SCH_PRIO=y +CONFIG_PSAMPLE=y +CONFIG_PTP_1588_CLOCK_MOCK=y +CONFIG_VXLAN=m diff --git a/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh b/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh index 922744059aaa..80160579e0cc 100644 --- a/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh @@ -51,6 +51,7 @@ function make_netdev { fi echo $NSIM_ID $@ > /sys/bus/netdevsim/new_device + udevadm settle # get new device name ls /sys/bus/netdevsim/devices/netdevsim${NSIM_ID}/net/ } diff --git a/tools/testing/selftests/drivers/net/netdevsim/ethtool-fec.sh b/tools/testing/selftests/drivers/net/netdevsim/ethtool-fec.sh index 0c56746e9ce0..7d7829f57550 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/ethtool-fec.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/ethtool-fec.sh @@ -8,16 +8,20 @@ NSIM_NETDEV=$(make_netdev) set -o pipefail +# Since commit 2b3ddcb35357 ("ethtool: fec: Change the prompt ...") +# in ethtool CLI the Configured lines start with Supported/Configured. +configured=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2 | head -1 | cut -d' ' -f1) + # netdevsim starts out with None/None s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2) -check $? "$s" "Configured FEC encodings: None +check $? "$s" "$configured FEC encodings: None Active FEC encoding: None" # Test Auto $ETHTOOL --set-fec $NSIM_NETDEV encoding auto check $? s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2) -check $? "$s" "Configured FEC encodings: Auto +check $? "$s" "$configured FEC encodings: Auto Active FEC encoding: Off" # Test case in-sensitivity @@ -25,7 +29,7 @@ for o in off Off OFF; do $ETHTOOL --set-fec $NSIM_NETDEV encoding $o check $? s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2) - check $? "$s" "Configured FEC encodings: Off + check $? "$s" "$configured FEC encodings: Off Active FEC encoding: Off" done @@ -33,7 +37,7 @@ for o in BaseR baser BAser; do $ETHTOOL --set-fec $NSIM_NETDEV encoding $o check $? s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2) - check $? "$s" "Configured FEC encodings: BaseR + check $? "$s" "$configured FEC encodings: BaseR Active FEC encoding: BaseR" done @@ -41,7 +45,7 @@ for o in llrs rs; do $ETHTOOL --set-fec $NSIM_NETDEV encoding $o check $? s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2) - check $? "$s" "Configured FEC encodings: ${o^^} + check $? "$s" "$configured FEC encodings: ${o^^} Active FEC encoding: ${o^^}" done @@ -49,13 +53,13 @@ done $ETHTOOL --set-fec $NSIM_NETDEV encoding rs llrs check $? s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2) -check $? "$s" "Configured FEC encodings: RS LLRS +check $? "$s" "$configured FEC encodings: RS LLRS Active FEC encoding: LLRS" $ETHTOOL --set-fec $NSIM_NETDEV encoding rs off auto check $? s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2) -check $? "$s" "Configured FEC encodings: Auto Off RS +check $? "$s" "$configured FEC encodings: Auto Off RS Active FEC encoding: RS" # Make sure other link modes are rejected diff --git a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh index 1b08e042cf94..f98435c502f6 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh @@ -233,6 +233,7 @@ function print_tables { function get_netdev_name { local -n old=$1 + udevadm settle new=$(ls /sys/class/net) for netdev in $new; do @@ -269,6 +270,7 @@ for port in 0 1; do echo 1 > $NSIM_DEV_SYS/new_port fi NSIM_NETDEV=`get_netdev_name old_netdevs` + ifconfig $NSIM_NETDEV up msg="new NIC device created" exp0=( 0 0 0 0 ) @@ -430,6 +432,7 @@ for port in 0 1; do fi echo $port > $NSIM_DEV_SYS/new_port + NSIM_NETDEV=`get_netdev_name old_netdevs` ifconfig $NSIM_NETDEV up overflow_table0 "overflow NIC table" @@ -487,6 +490,7 @@ for port in 0 1; do fi echo $port > $NSIM_DEV_SYS/new_port + NSIM_NETDEV=`get_netdev_name old_netdevs` ifconfig $NSIM_NETDEV up overflow_table0 "overflow NIC table" @@ -543,6 +547,7 @@ for port in 0 1; do fi echo $port > $NSIM_DEV_SYS/new_port + NSIM_NETDEV=`get_netdev_name old_netdevs` ifconfig $NSIM_NETDEV up overflow_table0 "destroy NIC" @@ -572,6 +577,7 @@ for port in 0 1; do fi echo $port > $NSIM_DEV_SYS/new_port + NSIM_NETDEV=`get_netdev_name old_netdevs` ifconfig $NSIM_NETDEV up msg="create VxLANs v6" @@ -632,6 +638,7 @@ for port in 0 1; do fi echo $port > $NSIM_DEV_SYS/new_port + NSIM_NETDEV=`get_netdev_name old_netdevs` ifconfig $NSIM_NETDEV up echo 110 > $NSIM_DEV_DFS/ports/$port/udp_ports_inject_error @@ -687,6 +694,7 @@ for port in 0 1; do fi echo $port > $NSIM_DEV_SYS/new_port + NSIM_NETDEV=`get_netdev_name old_netdevs` ifconfig $NSIM_NETDEV up msg="create VxLANs v6" @@ -746,6 +754,7 @@ for port in 0 1; do fi echo $port > $NSIM_DEV_SYS/new_port + NSIM_NETDEV=`get_netdev_name old_netdevs` ifconfig $NSIM_NETDEV up msg="create VxLANs v6" @@ -876,6 +885,7 @@ msg="re-add a port" echo 2 > $NSIM_DEV_SYS/del_port echo 2 > $NSIM_DEV_SYS/new_port +NSIM_NETDEV=`get_netdev_name old_netdevs` check_tables msg="replace VxLAN in overflow table" diff --git a/tools/testing/selftests/ftrace/test.d/00basic/ringbuffer_subbuf_size.tc b/tools/testing/selftests/ftrace/test.d/00basic/ringbuffer_subbuf_size.tc new file mode 100644 index 000000000000..d44d09a33a74 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/00basic/ringbuffer_subbuf_size.tc @@ -0,0 +1,95 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: Change the ringbuffer sub-buffer size +# requires: buffer_subbuf_size_kb +# flags: instance + +get_buffer_data_size() { + sed -ne 's/^.*data.*size:\([0-9][0-9]*\).*/\1/p' events/header_page +} + +get_buffer_data_offset() { + sed -ne 's/^.*data.*offset:\([0-9][0-9]*\).*/\1/p' events/header_page +} + +get_event_header_size() { + type_len=`sed -ne 's/^.*type_len.*:[^0-9]*\([0-9][0-9]*\).*/\1/p' events/header_event` + time_len=`sed -ne 's/^.*time_delta.*:[^0-9]*\([0-9][0-9]*\).*/\1/p' events/header_event` + array_len=`sed -ne 's/^.*array.*:[^0-9]*\([0-9][0-9]*\).*/\1/p' events/header_event` + total_bits=$((type_len+time_len+array_len)) + total_bits=$((total_bits+7)) + echo $((total_bits/8)) +} + +get_print_event_buf_offset() { + sed -ne 's/^.*buf.*offset:\([0-9][0-9]*\).*/\1/p' events/ftrace/print/format +} + +event_header_size=`get_event_header_size` +print_header_size=`get_print_event_buf_offset` + +data_offset=`get_buffer_data_offset` + +marker_meta=$((event_header_size+print_header_size)) + +make_str() { + cnt=$1 + printf -- 'X%.0s' $(seq $cnt) +} + +write_buffer() { + size=$1 + + str=`make_str $size` + + # clear the buffer + echo > trace + + # write the string into the marker + echo $str > trace_marker + + echo $str +} + +test_buffer() { + size_kb=$1 + page_size=$((size_kb*1024)) + + size=`get_buffer_data_size` + + # the size must be greater than or equal to page_size - data_offset + page_size=$((page_size-data_offset)) + if [ $size -lt $page_size ]; then + exit fail + fi + + # Now add a little more the meta data overhead will overflow + + str=`write_buffer $size` + + # Make sure the line was broken + new_str=`awk ' /tracing_mark_write:/ { sub(/^.*tracing_mark_write: /,"");printf "%s", $0; exit}' trace` + + if [ "$new_str" = "$str" ]; then + exit fail; + fi + + # Make sure the entire line can be found + new_str=`awk ' /tracing_mark_write:/ { sub(/^.*tracing_mark_write: /,"");printf "%s", $0; }' trace` + + if [ "$new_str" != "$str" ]; then + exit fail; + fi +} + +ORIG=`cat buffer_subbuf_size_kb` + +# Could test bigger sizes than 32K, but then creating the string +# to write into the ring buffer takes too long +for a in 4 8 16 32 ; do + echo $a > buffer_subbuf_size_kb + test_buffer $a +done + +echo $ORIG > buffer_subbuf_size_kb + diff --git a/tools/testing/selftests/ftrace/test.d/00basic/trace_marker.tc b/tools/testing/selftests/ftrace/test.d/00basic/trace_marker.tc new file mode 100644 index 000000000000..9aa0db2b84fc --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/00basic/trace_marker.tc @@ -0,0 +1,82 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: Basic tests on writing to trace_marker +# requires: trace_marker +# flags: instance + +get_buffer_data_size() { + sed -ne 's/^.*data.*size:\([0-9][0-9]*\).*/\1/p' events/header_page +} + +get_buffer_data_offset() { + sed -ne 's/^.*data.*offset:\([0-9][0-9]*\).*/\1/p' events/header_page +} + +get_event_header_size() { + type_len=`sed -ne 's/^.*type_len.*:[^0-9]*\([0-9][0-9]*\).*/\1/p' events/header_event` + time_len=`sed -ne 's/^.*time_delta.*:[^0-9]*\([0-9][0-9]*\).*/\1/p' events/header_event` + array_len=`sed -ne 's/^.*array.*:[^0-9]*\([0-9][0-9]*\).*/\1/p' events/header_event` + total_bits=$((type_len+time_len+array_len)) + total_bits=$((total_bits+7)) + echo $((total_bits/8)) +} + +get_print_event_buf_offset() { + sed -ne 's/^.*buf.*offset:\([0-9][0-9]*\).*/\1/p' events/ftrace/print/format +} + +event_header_size=`get_event_header_size` +print_header_size=`get_print_event_buf_offset` + +data_offset=`get_buffer_data_offset` + +marker_meta=$((event_header_size+print_header_size)) + +make_str() { + cnt=$1 + # subtract two for \n\0 as marker adds these + cnt=$((cnt-2)) + printf -- 'X%.0s' $(seq $cnt) +} + +write_buffer() { + size=$1 + + str=`make_str $size` + + # clear the buffer + echo > trace + + # write the string into the marker + echo -n $str > trace_marker + + echo $str +} + +test_buffer() { + + size=`get_buffer_data_size` + oneline_size=$((size-marker_meta)) + echo size = $size + echo meta size = $marker_meta + + # Now add a little more the meta data overhead will overflow + + str=`write_buffer $size` + + # Make sure the line was broken + new_str=`awk ' /tracing_mark_write:/ { sub(/^.*tracing_mark_write: /,"");printf "%s", $0; exit}' trace` + + if [ "$new_str" = "$str" ]; then + exit fail; + fi + + # Make sure the entire line can be found + new_str=`awk ' /tracing_mark_write:/ { sub(/^.*tracing_mark_write: /,"");printf "%s", $0; }' trace` + + if [ "$new_str" != "$str" ]; then + exit fail; + fi +} + +test_buffer diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c index 6ed328c863c4..1a881e7a21d1 100644 --- a/tools/testing/selftests/iommu/iommufd.c +++ b/tools/testing/selftests/iommu/iommufd.c @@ -116,6 +116,7 @@ TEST_F(iommufd, cmd_length) TEST_LENGTH(iommu_destroy, IOMMU_DESTROY, id); TEST_LENGTH(iommu_hw_info, IOMMU_GET_HW_INFO, __reserved); TEST_LENGTH(iommu_hwpt_alloc, IOMMU_HWPT_ALLOC, __reserved); + TEST_LENGTH(iommu_hwpt_invalidate, IOMMU_HWPT_INVALIDATE, __reserved); TEST_LENGTH(iommu_ioas_alloc, IOMMU_IOAS_ALLOC, out_ioas_id); TEST_LENGTH(iommu_ioas_iova_ranges, IOMMU_IOAS_IOVA_RANGES, out_iova_alignment); @@ -271,7 +272,9 @@ TEST_F(iommufd_ioas, alloc_hwpt_nested) struct iommu_hwpt_selftest data = { .iotlb = IOMMU_TEST_IOTLB_DEFAULT, }; + struct iommu_hwpt_invalidate_selftest inv_reqs[2] = {}; uint32_t nested_hwpt_id[2] = {}; + uint32_t num_inv; uint32_t parent_hwpt_id = 0; uint32_t parent_hwpt_id_not_work = 0; uint32_t test_hwpt_id = 0; @@ -330,6 +333,10 @@ TEST_F(iommufd_ioas, alloc_hwpt_nested) &nested_hwpt_id[1], IOMMU_HWPT_DATA_SELFTEST, &data, sizeof(data)); + test_cmd_hwpt_check_iotlb_all(nested_hwpt_id[0], + IOMMU_TEST_IOTLB_DEFAULT); + test_cmd_hwpt_check_iotlb_all(nested_hwpt_id[1], + IOMMU_TEST_IOTLB_DEFAULT); /* Negative test: a nested hwpt on top of a nested hwpt */ test_err_hwpt_alloc_nested(EINVAL, self->device_id, @@ -340,6 +347,151 @@ TEST_F(iommufd_ioas, alloc_hwpt_nested) EXPECT_ERRNO(EBUSY, _test_ioctl_destroy(self->fd, parent_hwpt_id)); + /* hwpt_invalidate only supports a user-managed hwpt (nested) */ + num_inv = 1; + test_err_hwpt_invalidate(ENOENT, parent_hwpt_id, inv_reqs, + IOMMU_HWPT_INVALIDATE_DATA_SELFTEST, + sizeof(*inv_reqs), &num_inv); + assert(!num_inv); + + /* Check data_type by passing zero-length array */ + num_inv = 0; + test_cmd_hwpt_invalidate(nested_hwpt_id[0], inv_reqs, + IOMMU_HWPT_INVALIDATE_DATA_SELFTEST, + sizeof(*inv_reqs), &num_inv); + assert(!num_inv); + + /* Negative test: Invalid data_type */ + num_inv = 1; + test_err_hwpt_invalidate(EINVAL, nested_hwpt_id[0], inv_reqs, + IOMMU_HWPT_INVALIDATE_DATA_SELFTEST_INVALID, + sizeof(*inv_reqs), &num_inv); + assert(!num_inv); + + /* Negative test: structure size sanity */ + num_inv = 1; + test_err_hwpt_invalidate(EINVAL, nested_hwpt_id[0], inv_reqs, + IOMMU_HWPT_INVALIDATE_DATA_SELFTEST, + sizeof(*inv_reqs) + 1, &num_inv); + assert(!num_inv); + + num_inv = 1; + test_err_hwpt_invalidate(EINVAL, nested_hwpt_id[0], inv_reqs, + IOMMU_HWPT_INVALIDATE_DATA_SELFTEST, + 1, &num_inv); + assert(!num_inv); + + /* Negative test: invalid flag is passed */ + num_inv = 1; + inv_reqs[0].flags = 0xffffffff; + test_err_hwpt_invalidate(EOPNOTSUPP, nested_hwpt_id[0], inv_reqs, + IOMMU_HWPT_INVALIDATE_DATA_SELFTEST, + sizeof(*inv_reqs), &num_inv); + assert(!num_inv); + + /* Negative test: invalid data_uptr when array is not empty */ + num_inv = 1; + inv_reqs[0].flags = 0; + test_err_hwpt_invalidate(EINVAL, nested_hwpt_id[0], NULL, + IOMMU_HWPT_INVALIDATE_DATA_SELFTEST, + sizeof(*inv_reqs), &num_inv); + assert(!num_inv); + + /* Negative test: invalid entry_len when array is not empty */ + num_inv = 1; + inv_reqs[0].flags = 0; + test_err_hwpt_invalidate(EINVAL, nested_hwpt_id[0], inv_reqs, + IOMMU_HWPT_INVALIDATE_DATA_SELFTEST, + 0, &num_inv); + assert(!num_inv); + + /* Negative test: invalid iotlb_id */ + num_inv = 1; + inv_reqs[0].flags = 0; + inv_reqs[0].iotlb_id = MOCK_NESTED_DOMAIN_IOTLB_ID_MAX + 1; + test_err_hwpt_invalidate(EINVAL, nested_hwpt_id[0], inv_reqs, + IOMMU_HWPT_INVALIDATE_DATA_SELFTEST, + sizeof(*inv_reqs), &num_inv); + assert(!num_inv); + + /* + * Invalidate the 1st iotlb entry but fail the 2nd request + * due to invalid flags configuration in the 2nd request. + */ + num_inv = 2; + inv_reqs[0].flags = 0; + inv_reqs[0].iotlb_id = 0; + inv_reqs[1].flags = 0xffffffff; + inv_reqs[1].iotlb_id = 1; + test_err_hwpt_invalidate(EOPNOTSUPP, nested_hwpt_id[0], inv_reqs, + IOMMU_HWPT_INVALIDATE_DATA_SELFTEST, + sizeof(*inv_reqs), &num_inv); + assert(num_inv == 1); + test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 0, 0); + test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 1, + IOMMU_TEST_IOTLB_DEFAULT); + test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 2, + IOMMU_TEST_IOTLB_DEFAULT); + test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 3, + IOMMU_TEST_IOTLB_DEFAULT); + + /* + * Invalidate the 1st iotlb entry but fail the 2nd request + * due to invalid iotlb_id configuration in the 2nd request. + */ + num_inv = 2; + inv_reqs[0].flags = 0; + inv_reqs[0].iotlb_id = 0; + inv_reqs[1].flags = 0; + inv_reqs[1].iotlb_id = MOCK_NESTED_DOMAIN_IOTLB_ID_MAX + 1; + test_err_hwpt_invalidate(EINVAL, nested_hwpt_id[0], inv_reqs, + IOMMU_HWPT_INVALIDATE_DATA_SELFTEST, + sizeof(*inv_reqs), &num_inv); + assert(num_inv == 1); + test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 0, 0); + test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 1, + IOMMU_TEST_IOTLB_DEFAULT); + test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 2, + IOMMU_TEST_IOTLB_DEFAULT); + test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 3, + IOMMU_TEST_IOTLB_DEFAULT); + + /* Invalidate the 2nd iotlb entry and verify */ + num_inv = 1; + inv_reqs[0].flags = 0; + inv_reqs[0].iotlb_id = 1; + test_cmd_hwpt_invalidate(nested_hwpt_id[0], inv_reqs, + IOMMU_HWPT_INVALIDATE_DATA_SELFTEST, + sizeof(*inv_reqs), &num_inv); + assert(num_inv == 1); + test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 0, 0); + test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 1, 0); + test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 2, + IOMMU_TEST_IOTLB_DEFAULT); + test_cmd_hwpt_check_iotlb(nested_hwpt_id[0], 3, + IOMMU_TEST_IOTLB_DEFAULT); + + /* Invalidate the 3rd and 4th iotlb entries and verify */ + num_inv = 2; + inv_reqs[0].flags = 0; + inv_reqs[0].iotlb_id = 2; + inv_reqs[1].flags = 0; + inv_reqs[1].iotlb_id = 3; + test_cmd_hwpt_invalidate(nested_hwpt_id[0], inv_reqs, + IOMMU_HWPT_INVALIDATE_DATA_SELFTEST, + sizeof(*inv_reqs), &num_inv); + assert(num_inv == 2); + test_cmd_hwpt_check_iotlb_all(nested_hwpt_id[0], 0); + + /* Invalidate all iotlb entries for nested_hwpt_id[1] and verify */ + num_inv = 1; + inv_reqs[0].flags = IOMMU_TEST_INVALIDATE_FLAG_ALL; + test_cmd_hwpt_invalidate(nested_hwpt_id[1], inv_reqs, + IOMMU_HWPT_INVALIDATE_DATA_SELFTEST, + sizeof(*inv_reqs), &num_inv); + assert(num_inv == 1); + test_cmd_hwpt_check_iotlb_all(nested_hwpt_id[1], 0); + /* Attach device to nested_hwpt_id[0] that then will be busy */ test_cmd_mock_domain_replace(self->stdev_id, nested_hwpt_id[0]); EXPECT_ERRNO(EBUSY, diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h index ad9202335656..c646264aa41f 100644 --- a/tools/testing/selftests/iommu/iommufd_utils.h +++ b/tools/testing/selftests/iommu/iommufd_utils.h @@ -195,6 +195,61 @@ static int _test_cmd_hwpt_alloc(int fd, __u32 device_id, __u32 pt_id, _test_cmd_hwpt_alloc(self->fd, device_id, pt_id, flags, \ hwpt_id, data_type, data, data_len)) +#define test_cmd_hwpt_check_iotlb(hwpt_id, iotlb_id, expected) \ + ({ \ + struct iommu_test_cmd test_cmd = { \ + .size = sizeof(test_cmd), \ + .op = IOMMU_TEST_OP_MD_CHECK_IOTLB, \ + .id = hwpt_id, \ + .check_iotlb = { \ + .id = iotlb_id, \ + .iotlb = expected, \ + }, \ + }; \ + ASSERT_EQ(0, \ + ioctl(self->fd, \ + _IOMMU_TEST_CMD(IOMMU_TEST_OP_MD_CHECK_IOTLB), \ + &test_cmd)); \ + }) + +#define test_cmd_hwpt_check_iotlb_all(hwpt_id, expected) \ + ({ \ + int i; \ + for (i = 0; i < MOCK_NESTED_DOMAIN_IOTLB_NUM; i++) \ + test_cmd_hwpt_check_iotlb(hwpt_id, i, expected); \ + }) + +static int _test_cmd_hwpt_invalidate(int fd, __u32 hwpt_id, void *reqs, + uint32_t data_type, uint32_t lreq, + uint32_t *nreqs) +{ + struct iommu_hwpt_invalidate cmd = { + .size = sizeof(cmd), + .hwpt_id = hwpt_id, + .data_type = data_type, + .data_uptr = (uint64_t)reqs, + .entry_len = lreq, + .entry_num = *nreqs, + }; + int rc = ioctl(fd, IOMMU_HWPT_INVALIDATE, &cmd); + *nreqs = cmd.entry_num; + return rc; +} + +#define test_cmd_hwpt_invalidate(hwpt_id, reqs, data_type, lreq, nreqs) \ + ({ \ + ASSERT_EQ(0, \ + _test_cmd_hwpt_invalidate(self->fd, hwpt_id, reqs, \ + data_type, lreq, nreqs)); \ + }) +#define test_err_hwpt_invalidate(_errno, hwpt_id, reqs, data_type, lreq, \ + nreqs) \ + ({ \ + EXPECT_ERRNO(_errno, _test_cmd_hwpt_invalidate( \ + self->fd, hwpt_id, reqs, \ + data_type, lreq, nreqs)); \ + }) + static int _test_cmd_access_replace_ioas(int fd, __u32 access_id, unsigned int ioas_id) { diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 3e0c36b8ddd5..492e937fab00 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -77,11 +77,12 @@ TEST_GEN_PROGS_x86_64 += x86_64/hyperv_svm_test TEST_GEN_PROGS_x86_64 += x86_64/hyperv_tlb_flush TEST_GEN_PROGS_x86_64 += x86_64/kvm_clock_test TEST_GEN_PROGS_x86_64 += x86_64/kvm_pv_test -TEST_GEN_PROGS_x86_64 += x86_64/mmio_warning_test TEST_GEN_PROGS_x86_64 += x86_64/monitor_mwait_test TEST_GEN_PROGS_x86_64 += x86_64/nested_exceptions_test TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test TEST_GEN_PROGS_x86_64 += x86_64/pmu_event_filter_test +TEST_GEN_PROGS_x86_64 += x86_64/private_mem_conversions_test +TEST_GEN_PROGS_x86_64 += x86_64/private_mem_kvm_exits_test TEST_GEN_PROGS_x86_64 += x86_64/set_boot_cpu_id TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test TEST_GEN_PROGS_x86_64 += x86_64/smaller_maxphyaddr_emulation_test @@ -124,6 +125,7 @@ TEST_GEN_PROGS_x86_64 += access_tracking_perf_test TEST_GEN_PROGS_x86_64 += demand_paging_test TEST_GEN_PROGS_x86_64 += dirty_log_test TEST_GEN_PROGS_x86_64 += dirty_log_perf_test +TEST_GEN_PROGS_x86_64 += guest_memfd_test TEST_GEN_PROGS_x86_64 += guest_print_test TEST_GEN_PROGS_x86_64 += hardware_disable_test TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus @@ -184,12 +186,13 @@ TEST_GEN_PROGS_s390x += kvm_binary_stats_test TEST_GEN_PROGS_riscv += demand_paging_test TEST_GEN_PROGS_riscv += dirty_log_test -TEST_GEN_PROGS_riscv += guest_print_test TEST_GEN_PROGS_riscv += get-reg-list +TEST_GEN_PROGS_riscv += guest_print_test +TEST_GEN_PROGS_riscv += kvm_binary_stats_test TEST_GEN_PROGS_riscv += kvm_create_max_vcpus TEST_GEN_PROGS_riscv += kvm_page_table_test TEST_GEN_PROGS_riscv += set_memory_region_test -TEST_GEN_PROGS_riscv += kvm_binary_stats_test +TEST_GEN_PROGS_riscv += steal_time SPLIT_TESTS += get-reg-list diff --git a/tools/testing/selftests/kvm/aarch64/page_fault_test.c b/tools/testing/selftests/kvm/aarch64/page_fault_test.c index eb4217b7c768..08a5ca5bed56 100644 --- a/tools/testing/selftests/kvm/aarch64/page_fault_test.c +++ b/tools/testing/selftests/kvm/aarch64/page_fault_test.c @@ -705,7 +705,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) print_test_banner(mode, p); - vm = ____vm_create(mode); + vm = ____vm_create(VM_SHAPE(mode)); setup_memslots(vm, p); kvm_vm_elf_load(vm, program_invocation_name); setup_ucall(vm); diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c index 936f3a8d1b83..6cbecf499767 100644 --- a/tools/testing/selftests/kvm/dirty_log_test.c +++ b/tools/testing/selftests/kvm/dirty_log_test.c @@ -699,7 +699,7 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, struct kvm_vcpu **vcpu, pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode)); - vm = __vm_create(mode, 1, extra_mem_pages); + vm = __vm_create(VM_SHAPE(mode), 1, extra_mem_pages); log_mode_create_vm_done(vm); *vcpu = vm_vcpu_add(vm, 0, guest_code); diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c new file mode 100644 index 000000000000..c78a98c1a915 --- /dev/null +++ b/tools/testing/selftests/kvm/guest_memfd_test.c @@ -0,0 +1,198 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright Intel Corporation, 2023 + * + * Author: Chao Peng <chao.p.peng@linux.intel.com> + */ + +#define _GNU_SOURCE +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <errno.h> +#include <stdio.h> +#include <fcntl.h> + +#include <linux/bitmap.h> +#include <linux/falloc.h> +#include <sys/mman.h> +#include <sys/types.h> +#include <sys/stat.h> + +#include "test_util.h" +#include "kvm_util_base.h" + +static void test_file_read_write(int fd) +{ + char buf[64]; + + TEST_ASSERT(read(fd, buf, sizeof(buf)) < 0, + "read on a guest_mem fd should fail"); + TEST_ASSERT(write(fd, buf, sizeof(buf)) < 0, + "write on a guest_mem fd should fail"); + TEST_ASSERT(pread(fd, buf, sizeof(buf), 0) < 0, + "pread on a guest_mem fd should fail"); + TEST_ASSERT(pwrite(fd, buf, sizeof(buf), 0) < 0, + "pwrite on a guest_mem fd should fail"); +} + +static void test_mmap(int fd, size_t page_size) +{ + char *mem; + + mem = mmap(NULL, page_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + TEST_ASSERT_EQ(mem, MAP_FAILED); +} + +static void test_file_size(int fd, size_t page_size, size_t total_size) +{ + struct stat sb; + int ret; + + ret = fstat(fd, &sb); + TEST_ASSERT(!ret, "fstat should succeed"); + TEST_ASSERT_EQ(sb.st_size, total_size); + TEST_ASSERT_EQ(sb.st_blksize, page_size); +} + +static void test_fallocate(int fd, size_t page_size, size_t total_size) +{ + int ret; + + ret = fallocate(fd, FALLOC_FL_KEEP_SIZE, 0, total_size); + TEST_ASSERT(!ret, "fallocate with aligned offset and size should succeed"); + + ret = fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, + page_size - 1, page_size); + TEST_ASSERT(ret, "fallocate with unaligned offset should fail"); + + ret = fallocate(fd, FALLOC_FL_KEEP_SIZE, total_size, page_size); + TEST_ASSERT(ret, "fallocate beginning at total_size should fail"); + + ret = fallocate(fd, FALLOC_FL_KEEP_SIZE, total_size + page_size, page_size); + TEST_ASSERT(ret, "fallocate beginning after total_size should fail"); + + ret = fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, + total_size, page_size); + TEST_ASSERT(!ret, "fallocate(PUNCH_HOLE) at total_size should succeed"); + + ret = fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, + total_size + page_size, page_size); + TEST_ASSERT(!ret, "fallocate(PUNCH_HOLE) after total_size should succeed"); + + ret = fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, + page_size, page_size - 1); + TEST_ASSERT(ret, "fallocate with unaligned size should fail"); + + ret = fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, + page_size, page_size); + TEST_ASSERT(!ret, "fallocate(PUNCH_HOLE) with aligned offset and size should succeed"); + + ret = fallocate(fd, FALLOC_FL_KEEP_SIZE, page_size, page_size); + TEST_ASSERT(!ret, "fallocate to restore punched hole should succeed"); +} + +static void test_invalid_punch_hole(int fd, size_t page_size, size_t total_size) +{ + struct { + off_t offset; + off_t len; + } testcases[] = { + {0, 1}, + {0, page_size - 1}, + {0, page_size + 1}, + + {1, 1}, + {1, page_size - 1}, + {1, page_size}, + {1, page_size + 1}, + + {page_size, 1}, + {page_size, page_size - 1}, + {page_size, page_size + 1}, + }; + int ret, i; + + for (i = 0; i < ARRAY_SIZE(testcases); i++) { + ret = fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, + testcases[i].offset, testcases[i].len); + TEST_ASSERT(ret == -1 && errno == EINVAL, + "PUNCH_HOLE with !PAGE_SIZE offset (%lx) and/or length (%lx) should fail", + testcases[i].offset, testcases[i].len); + } +} + +static void test_create_guest_memfd_invalid(struct kvm_vm *vm) +{ + size_t page_size = getpagesize(); + uint64_t flag; + size_t size; + int fd; + + for (size = 1; size < page_size; size++) { + fd = __vm_create_guest_memfd(vm, size, 0); + TEST_ASSERT(fd == -1 && errno == EINVAL, + "guest_memfd() with non-page-aligned page size '0x%lx' should fail with EINVAL", + size); + } + + for (flag = 0; flag; flag <<= 1) { + fd = __vm_create_guest_memfd(vm, page_size, flag); + TEST_ASSERT(fd == -1 && errno == EINVAL, + "guest_memfd() with flag '0x%lx' should fail with EINVAL", + flag); + } +} + +static void test_create_guest_memfd_multiple(struct kvm_vm *vm) +{ + int fd1, fd2, ret; + struct stat st1, st2; + + fd1 = __vm_create_guest_memfd(vm, 4096, 0); + TEST_ASSERT(fd1 != -1, "memfd creation should succeed"); + + ret = fstat(fd1, &st1); + TEST_ASSERT(ret != -1, "memfd fstat should succeed"); + TEST_ASSERT(st1.st_size == 4096, "memfd st_size should match requested size"); + + fd2 = __vm_create_guest_memfd(vm, 8192, 0); + TEST_ASSERT(fd2 != -1, "memfd creation should succeed"); + + ret = fstat(fd2, &st2); + TEST_ASSERT(ret != -1, "memfd fstat should succeed"); + TEST_ASSERT(st2.st_size == 8192, "second memfd st_size should match requested size"); + + ret = fstat(fd1, &st1); + TEST_ASSERT(ret != -1, "memfd fstat should succeed"); + TEST_ASSERT(st1.st_size == 4096, "first memfd st_size should still match requested size"); + TEST_ASSERT(st1.st_ino != st2.st_ino, "different memfd should have different inode numbers"); +} + +int main(int argc, char *argv[]) +{ + size_t page_size; + size_t total_size; + int fd; + struct kvm_vm *vm; + + TEST_REQUIRE(kvm_has_cap(KVM_CAP_GUEST_MEMFD)); + + page_size = getpagesize(); + total_size = page_size * 4; + + vm = vm_create_barebones(); + + test_create_guest_memfd_invalid(vm); + test_create_guest_memfd_multiple(vm); + + fd = vm_create_guest_memfd(vm, total_size, 0); + + test_file_read_write(fd); + test_mmap(fd, page_size); + test_file_size(fd, page_size, total_size); + test_fallocate(fd, page_size, total_size); + test_invalid_punch_hole(fd, page_size, total_size); + + close(fd); +} diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h index c42d683102c7..cf20e44e86f2 100644 --- a/tools/testing/selftests/kvm/include/aarch64/processor.h +++ b/tools/testing/selftests/kvm/include/aarch64/processor.h @@ -119,8 +119,8 @@ enum { /* Access flag update enable/disable */ #define TCR_EL1_HA (1ULL << 39) -void aarch64_get_supported_page_sizes(uint32_t ipa, - bool *ps4k, bool *ps16k, bool *ps64k); +void aarch64_get_supported_page_sizes(uint32_t ipa, uint32_t *ipa4k, + uint32_t *ipa16k, uint32_t *ipa64k); void vm_init_descriptor_tables(struct kvm_vm *vm); void vcpu_init_descriptor_tables(struct kvm_vcpu *vcpu); diff --git a/tools/testing/selftests/kvm/include/guest_modes.h b/tools/testing/selftests/kvm/include/guest_modes.h index b691df33e64e..63f5167397cc 100644 --- a/tools/testing/selftests/kvm/include/guest_modes.h +++ b/tools/testing/selftests/kvm/include/guest_modes.h @@ -11,8 +11,8 @@ struct guest_mode { extern struct guest_mode guest_modes[NUM_VM_MODES]; -#define guest_mode_append(mode, supported, enabled) ({ \ - guest_modes[mode] = (struct guest_mode){ supported, enabled }; \ +#define guest_mode_append(mode, enabled) ({ \ + guest_modes[mode] = (struct guest_mode){ (enabled), (enabled) }; \ }) void guest_modes_append_default(void); diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h index a18db6a7b3cf..9e5afc472c14 100644 --- a/tools/testing/selftests/kvm/include/kvm_util_base.h +++ b/tools/testing/selftests/kvm/include/kvm_util_base.h @@ -44,7 +44,7 @@ typedef uint64_t vm_paddr_t; /* Virtual Machine (Guest) physical address */ typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */ struct userspace_mem_region { - struct kvm_userspace_memory_region region; + struct kvm_userspace_memory_region2 region; struct sparsebit *unused_phy_pages; int fd; off_t offset; @@ -129,6 +129,7 @@ struct vcpu_reg_sublist { const char *name; long capability; int feature; + int feature_type; bool finalize; __u64 *regs; __u64 regs_n; @@ -171,6 +172,7 @@ static inline struct userspace_mem_region *vm_get_mem_region(struct kvm_vm *vm, enum vm_guest_mode { VM_MODE_P52V48_4K, + VM_MODE_P52V48_16K, VM_MODE_P52V48_64K, VM_MODE_P48V48_4K, VM_MODE_P48V48_16K, @@ -188,6 +190,23 @@ enum vm_guest_mode { NUM_VM_MODES, }; +struct vm_shape { + enum vm_guest_mode mode; + unsigned int type; +}; + +#define VM_TYPE_DEFAULT 0 + +#define VM_SHAPE(__mode) \ +({ \ + struct vm_shape shape = { \ + .mode = (__mode), \ + .type = VM_TYPE_DEFAULT \ + }; \ + \ + shape; \ +}) + #if defined(__aarch64__) extern enum vm_guest_mode vm_mode_default; @@ -220,6 +239,8 @@ extern enum vm_guest_mode vm_mode_default; #endif +#define VM_SHAPE_DEFAULT VM_SHAPE(VM_MODE_DEFAULT) + #define MIN_PAGE_SIZE (1U << MIN_PAGE_SHIFT) #define PTES_PER_MIN_PAGE ptes_per_page(MIN_PAGE_SIZE) @@ -248,6 +269,13 @@ static inline bool kvm_has_cap(long cap) #define __KVM_SYSCALL_ERROR(_name, _ret) \ "%s failed, rc: %i errno: %i (%s)", (_name), (_ret), errno, strerror(errno) +/* + * Use the "inner", double-underscore macro when reporting errors from within + * other macros so that the name of ioctl() and not its literal numeric value + * is printed on error. The "outer" macro is strongly preferred when reporting + * errors "directly", i.e. without an additional layer of macros, as it reduces + * the probability of passing in the wrong string. + */ #define __KVM_IOCTL_ERROR(_name, _ret) __KVM_SYSCALL_ERROR(_name, _ret) #define KVM_IOCTL_ERROR(_ioctl, _ret) __KVM_IOCTL_ERROR(#_ioctl, _ret) @@ -260,17 +288,13 @@ static inline bool kvm_has_cap(long cap) #define __kvm_ioctl(kvm_fd, cmd, arg) \ kvm_do_ioctl(kvm_fd, cmd, arg) - -#define _kvm_ioctl(kvm_fd, cmd, name, arg) \ +#define kvm_ioctl(kvm_fd, cmd, arg) \ ({ \ int ret = __kvm_ioctl(kvm_fd, cmd, arg); \ \ - TEST_ASSERT(!ret, __KVM_IOCTL_ERROR(name, ret)); \ + TEST_ASSERT(!ret, __KVM_IOCTL_ERROR(#cmd, ret)); \ }) -#define kvm_ioctl(kvm_fd, cmd, arg) \ - _kvm_ioctl(kvm_fd, cmd, #cmd, arg) - static __always_inline void static_assert_is_vm(struct kvm_vm *vm) { } #define __vm_ioctl(vm, cmd, arg) \ @@ -279,17 +303,42 @@ static __always_inline void static_assert_is_vm(struct kvm_vm *vm) { } kvm_do_ioctl((vm)->fd, cmd, arg); \ }) -#define _vm_ioctl(vm, cmd, name, arg) \ +/* + * Assert that a VM or vCPU ioctl() succeeded, with extra magic to detect if + * the ioctl() failed because KVM killed/bugged the VM. To detect a dead VM, + * probe KVM_CAP_USER_MEMORY, which (a) has been supported by KVM since before + * selftests existed and (b) should never outright fail, i.e. is supposed to + * return 0 or 1. If KVM kills a VM, KVM returns -EIO for all ioctl()s for the + * VM and its vCPUs, including KVM_CHECK_EXTENSION. + */ +#define __TEST_ASSERT_VM_VCPU_IOCTL(cond, name, ret, vm) \ +do { \ + int __errno = errno; \ + \ + static_assert_is_vm(vm); \ + \ + if (cond) \ + break; \ + \ + if (errno == EIO && \ + __vm_ioctl(vm, KVM_CHECK_EXTENSION, (void *)KVM_CAP_USER_MEMORY) < 0) { \ + TEST_ASSERT(errno == EIO, "KVM killed the VM, should return -EIO"); \ + TEST_FAIL("KVM killed/bugged the VM, check the kernel log for clues"); \ + } \ + errno = __errno; \ + TEST_ASSERT(cond, __KVM_IOCTL_ERROR(name, ret)); \ +} while (0) + +#define TEST_ASSERT_VM_VCPU_IOCTL(cond, cmd, ret, vm) \ + __TEST_ASSERT_VM_VCPU_IOCTL(cond, #cmd, ret, vm) + +#define vm_ioctl(vm, cmd, arg) \ ({ \ int ret = __vm_ioctl(vm, cmd, arg); \ \ - TEST_ASSERT(!ret, __KVM_IOCTL_ERROR(name, ret)); \ + __TEST_ASSERT_VM_VCPU_IOCTL(!ret, #cmd, ret, vm); \ }) -#define vm_ioctl(vm, cmd, arg) \ - _vm_ioctl(vm, cmd, #cmd, arg) - - static __always_inline void static_assert_is_vcpu(struct kvm_vcpu *vcpu) { } #define __vcpu_ioctl(vcpu, cmd, arg) \ @@ -298,16 +347,13 @@ static __always_inline void static_assert_is_vcpu(struct kvm_vcpu *vcpu) { } kvm_do_ioctl((vcpu)->fd, cmd, arg); \ }) -#define _vcpu_ioctl(vcpu, cmd, name, arg) \ +#define vcpu_ioctl(vcpu, cmd, arg) \ ({ \ int ret = __vcpu_ioctl(vcpu, cmd, arg); \ \ - TEST_ASSERT(!ret, __KVM_IOCTL_ERROR(name, ret)); \ + __TEST_ASSERT_VM_VCPU_IOCTL(!ret, #cmd, ret, (vcpu)->vm); \ }) -#define vcpu_ioctl(vcpu, cmd, arg) \ - _vcpu_ioctl(vcpu, cmd, #cmd, arg) - /* * Looks up and returns the value corresponding to the capability * (KVM_CAP_*) given by cap. @@ -316,7 +362,7 @@ static inline int vm_check_cap(struct kvm_vm *vm, long cap) { int ret = __vm_ioctl(vm, KVM_CHECK_EXTENSION, (void *)cap); - TEST_ASSERT(ret >= 0, KVM_IOCTL_ERROR(KVM_CHECK_EXTENSION, ret)); + TEST_ASSERT_VM_VCPU_IOCTL(ret >= 0, KVM_CHECK_EXTENSION, ret, vm); return ret; } @@ -333,6 +379,54 @@ static inline void vm_enable_cap(struct kvm_vm *vm, uint32_t cap, uint64_t arg0) vm_ioctl(vm, KVM_ENABLE_CAP, &enable_cap); } +static inline void vm_set_memory_attributes(struct kvm_vm *vm, uint64_t gpa, + uint64_t size, uint64_t attributes) +{ + struct kvm_memory_attributes attr = { + .attributes = attributes, + .address = gpa, + .size = size, + .flags = 0, + }; + + /* + * KVM_SET_MEMORY_ATTRIBUTES overwrites _all_ attributes. These flows + * need significant enhancements to support multiple attributes. + */ + TEST_ASSERT(!attributes || attributes == KVM_MEMORY_ATTRIBUTE_PRIVATE, + "Update me to support multiple attributes!"); + + vm_ioctl(vm, KVM_SET_MEMORY_ATTRIBUTES, &attr); +} + + +static inline void vm_mem_set_private(struct kvm_vm *vm, uint64_t gpa, + uint64_t size) +{ + vm_set_memory_attributes(vm, gpa, size, KVM_MEMORY_ATTRIBUTE_PRIVATE); +} + +static inline void vm_mem_set_shared(struct kvm_vm *vm, uint64_t gpa, + uint64_t size) +{ + vm_set_memory_attributes(vm, gpa, size, 0); +} + +void vm_guest_mem_fallocate(struct kvm_vm *vm, uint64_t gpa, uint64_t size, + bool punch_hole); + +static inline void vm_guest_mem_punch_hole(struct kvm_vm *vm, uint64_t gpa, + uint64_t size) +{ + vm_guest_mem_fallocate(vm, gpa, size, true); +} + +static inline void vm_guest_mem_allocate(struct kvm_vm *vm, uint64_t gpa, + uint64_t size) +{ + vm_guest_mem_fallocate(vm, gpa, size, false); +} + void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size); const char *vm_guest_mode_string(uint32_t i); @@ -375,7 +469,7 @@ static inline int vm_get_stats_fd(struct kvm_vm *vm) { int fd = __vm_ioctl(vm, KVM_GET_STATS_FD, NULL); - TEST_ASSERT(fd >= 0, KVM_IOCTL_ERROR(KVM_GET_STATS_FD, fd)); + TEST_ASSERT_VM_VCPU_IOCTL(fd >= 0, KVM_GET_STATS_FD, fd, vm); return fd; } @@ -431,14 +525,44 @@ static inline uint64_t vm_get_stat(struct kvm_vm *vm, const char *stat_name) void vm_create_irqchip(struct kvm_vm *vm); +static inline int __vm_create_guest_memfd(struct kvm_vm *vm, uint64_t size, + uint64_t flags) +{ + struct kvm_create_guest_memfd guest_memfd = { + .size = size, + .flags = flags, + }; + + return __vm_ioctl(vm, KVM_CREATE_GUEST_MEMFD, &guest_memfd); +} + +static inline int vm_create_guest_memfd(struct kvm_vm *vm, uint64_t size, + uint64_t flags) +{ + int fd = __vm_create_guest_memfd(vm, size, flags); + + TEST_ASSERT(fd >= 0, KVM_IOCTL_ERROR(KVM_CREATE_GUEST_MEMFD, fd)); + return fd; +} + void vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags, uint64_t gpa, uint64_t size, void *hva); int __vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags, uint64_t gpa, uint64_t size, void *hva); +void vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags, + uint64_t gpa, uint64_t size, void *hva, + uint32_t guest_memfd, uint64_t guest_memfd_offset); +int __vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags, + uint64_t gpa, uint64_t size, void *hva, + uint32_t guest_memfd, uint64_t guest_memfd_offset); + void vm_userspace_mem_region_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, uint64_t guest_paddr, uint32_t slot, uint64_t npages, uint32_t flags); +void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, + uint64_t guest_paddr, uint32_t slot, uint64_t npages, + uint32_t flags, int guest_memfd_fd, uint64_t guest_memfd_offset); void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags); void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa); @@ -587,7 +711,7 @@ static inline int vcpu_get_stats_fd(struct kvm_vcpu *vcpu) { int fd = __vcpu_ioctl(vcpu, KVM_GET_STATS_FD, NULL); - TEST_ASSERT(fd >= 0, KVM_IOCTL_ERROR(KVM_GET_STATS_FD, fd)); + TEST_ASSERT_VM_VCPU_IOCTL(fd >= 0, KVM_CHECK_EXTENSION, fd, vcpu->vm); return fd; } @@ -713,21 +837,33 @@ vm_paddr_t vm_alloc_page_table(struct kvm_vm *vm); * __vm_create() does NOT create vCPUs, @nr_runnable_vcpus is used purely to * calculate the amount of memory needed for per-vCPU data, e.g. stacks. */ -struct kvm_vm *____vm_create(enum vm_guest_mode mode); -struct kvm_vm *__vm_create(enum vm_guest_mode mode, uint32_t nr_runnable_vcpus, +struct kvm_vm *____vm_create(struct vm_shape shape); +struct kvm_vm *__vm_create(struct vm_shape shape, uint32_t nr_runnable_vcpus, uint64_t nr_extra_pages); static inline struct kvm_vm *vm_create_barebones(void) { - return ____vm_create(VM_MODE_DEFAULT); + return ____vm_create(VM_SHAPE_DEFAULT); } +#ifdef __x86_64__ +static inline struct kvm_vm *vm_create_barebones_protected_vm(void) +{ + const struct vm_shape shape = { + .mode = VM_MODE_DEFAULT, + .type = KVM_X86_SW_PROTECTED_VM, + }; + + return ____vm_create(shape); +} +#endif + static inline struct kvm_vm *vm_create(uint32_t nr_runnable_vcpus) { - return __vm_create(VM_MODE_DEFAULT, nr_runnable_vcpus, 0); + return __vm_create(VM_SHAPE_DEFAULT, nr_runnable_vcpus, 0); } -struct kvm_vm *__vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus, +struct kvm_vm *__vm_create_with_vcpus(struct vm_shape shape, uint32_t nr_vcpus, uint64_t extra_mem_pages, void *guest_code, struct kvm_vcpu *vcpus[]); @@ -735,17 +871,27 @@ static inline struct kvm_vm *vm_create_with_vcpus(uint32_t nr_vcpus, void *guest_code, struct kvm_vcpu *vcpus[]) { - return __vm_create_with_vcpus(VM_MODE_DEFAULT, nr_vcpus, 0, + return __vm_create_with_vcpus(VM_SHAPE_DEFAULT, nr_vcpus, 0, guest_code, vcpus); } + +struct kvm_vm *__vm_create_shape_with_one_vcpu(struct vm_shape shape, + struct kvm_vcpu **vcpu, + uint64_t extra_mem_pages, + void *guest_code); + /* * Create a VM with a single vCPU with reasonable defaults and @extra_mem_pages * additional pages of guest memory. Returns the VM and vCPU (via out param). */ -struct kvm_vm *__vm_create_with_one_vcpu(struct kvm_vcpu **vcpu, - uint64_t extra_mem_pages, - void *guest_code); +static inline struct kvm_vm *__vm_create_with_one_vcpu(struct kvm_vcpu **vcpu, + uint64_t extra_mem_pages, + void *guest_code) +{ + return __vm_create_shape_with_one_vcpu(VM_SHAPE_DEFAULT, vcpu, + extra_mem_pages, guest_code); +} static inline struct kvm_vm *vm_create_with_one_vcpu(struct kvm_vcpu **vcpu, void *guest_code) @@ -753,6 +899,13 @@ static inline struct kvm_vm *vm_create_with_one_vcpu(struct kvm_vcpu **vcpu, return __vm_create_with_one_vcpu(vcpu, 0, guest_code); } +static inline struct kvm_vm *vm_create_shape_with_one_vcpu(struct vm_shape shape, + struct kvm_vcpu **vcpu, + void *guest_code) +{ + return __vm_create_shape_with_one_vcpu(shape, vcpu, 0, guest_code); +} + struct kvm_vcpu *vm_recreate_with_one_vcpu(struct kvm_vm *vm); void kvm_pin_this_task_to_pcpu(uint32_t pcpu); @@ -776,10 +929,6 @@ vm_adjust_num_guest_pages(enum vm_guest_mode mode, unsigned int num_guest_pages) return n; } -struct kvm_userspace_memory_region * -kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start, - uint64_t end); - #define sync_global_to_guest(vm, g) ({ \ typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \ memcpy(_p, &(g), sizeof(g)); \ diff --git a/tools/testing/selftests/kvm/include/riscv/processor.h b/tools/testing/selftests/kvm/include/riscv/processor.h index 5b62a3d2aa9b..a0f9efe5a2a8 100644 --- a/tools/testing/selftests/kvm/include/riscv/processor.h +++ b/tools/testing/selftests/kvm/include/riscv/processor.h @@ -10,10 +10,10 @@ #include "kvm_util.h" #include <linux/stringify.h> -static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t idx, - uint64_t size) +static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t subtype, + uint64_t idx, uint64_t size) { - return KVM_REG_RISCV | type | idx | size; + return KVM_REG_RISCV | type | subtype | idx | size; } #if __riscv_xlen == 64 @@ -22,24 +22,30 @@ static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t idx, #define KVM_REG_SIZE_ULONG KVM_REG_SIZE_U32 #endif -#define RISCV_CONFIG_REG(name) __kvm_reg_id(KVM_REG_RISCV_CONFIG, \ - KVM_REG_RISCV_CONFIG_REG(name), \ - KVM_REG_SIZE_ULONG) +#define RISCV_CONFIG_REG(name) __kvm_reg_id(KVM_REG_RISCV_CONFIG, 0, \ + KVM_REG_RISCV_CONFIG_REG(name), \ + KVM_REG_SIZE_ULONG) -#define RISCV_CORE_REG(name) __kvm_reg_id(KVM_REG_RISCV_CORE, \ - KVM_REG_RISCV_CORE_REG(name), \ - KVM_REG_SIZE_ULONG) +#define RISCV_CORE_REG(name) __kvm_reg_id(KVM_REG_RISCV_CORE, 0, \ + KVM_REG_RISCV_CORE_REG(name), \ + KVM_REG_SIZE_ULONG) -#define RISCV_CSR_REG(name) __kvm_reg_id(KVM_REG_RISCV_CSR, \ - KVM_REG_RISCV_CSR_REG(name), \ - KVM_REG_SIZE_ULONG) +#define RISCV_GENERAL_CSR_REG(name) __kvm_reg_id(KVM_REG_RISCV_CSR, \ + KVM_REG_RISCV_CSR_GENERAL, \ + KVM_REG_RISCV_CSR_REG(name), \ + KVM_REG_SIZE_ULONG) -#define RISCV_TIMER_REG(name) __kvm_reg_id(KVM_REG_RISCV_TIMER, \ - KVM_REG_RISCV_TIMER_REG(name), \ - KVM_REG_SIZE_U64) +#define RISCV_TIMER_REG(name) __kvm_reg_id(KVM_REG_RISCV_TIMER, 0, \ + KVM_REG_RISCV_TIMER_REG(name), \ + KVM_REG_SIZE_U64) -#define RISCV_ISA_EXT_REG(idx) __kvm_reg_id(KVM_REG_RISCV_ISA_EXT, \ - idx, KVM_REG_SIZE_ULONG) +#define RISCV_ISA_EXT_REG(idx) __kvm_reg_id(KVM_REG_RISCV_ISA_EXT, \ + KVM_REG_RISCV_ISA_SINGLE, \ + idx, KVM_REG_SIZE_ULONG) + +#define RISCV_SBI_EXT_REG(idx) __kvm_reg_id(KVM_REG_RISCV_SBI_EXT, \ + KVM_REG_RISCV_SBI_SINGLE, \ + idx, KVM_REG_SIZE_ULONG) /* L3 index Bit[47:39] */ #define PGTBL_L3_INDEX_MASK 0x0000FF8000000000ULL @@ -102,6 +108,17 @@ static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t idx, #define SATP_ASID_SHIFT 44 #define SATP_ASID_MASK _AC(0xFFFF, UL) +/* SBI return error codes */ +#define SBI_SUCCESS 0 +#define SBI_ERR_FAILURE -1 +#define SBI_ERR_NOT_SUPPORTED -2 +#define SBI_ERR_INVALID_PARAM -3 +#define SBI_ERR_DENIED -4 +#define SBI_ERR_INVALID_ADDRESS -5 +#define SBI_ERR_ALREADY_AVAILABLE -6 +#define SBI_ERR_ALREADY_STARTED -7 +#define SBI_ERR_ALREADY_STOPPED -8 + #define SBI_EXT_EXPERIMENTAL_START 0x08000000 #define SBI_EXT_EXPERIMENTAL_END 0x08FFFFFF @@ -109,6 +126,15 @@ static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t idx, #define KVM_RISCV_SELFTESTS_SBI_UCALL 0 #define KVM_RISCV_SELFTESTS_SBI_UNEXP 1 +enum sbi_ext_id { + SBI_EXT_BASE = 0x10, + SBI_EXT_STA = 0x535441, +}; + +enum sbi_ext_base_fid { + SBI_EXT_BASE_PROBE_EXT = 3, +}; + struct sbiret { long error; long value; @@ -119,4 +145,6 @@ struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0, unsigned long arg3, unsigned long arg4, unsigned long arg5); +bool guest_sbi_probe_extension(int extid, long *out_val); + #endif /* SELFTEST_KVM_PROCESSOR_H */ diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index 8e5f413a593d..71a41fa924b7 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -142,6 +142,11 @@ static inline bool backing_src_is_shared(enum vm_mem_backing_src_type t) return vm_mem_backing_src_alias(t)->flag & MAP_SHARED; } +static inline bool backing_src_can_be_huge(enum vm_mem_backing_src_type t) +{ + return t != VM_MEM_SRC_ANONYMOUS && t != VM_MEM_SRC_SHMEM; +} + /* Aligns x up to the next multiple of size. Size must be a power of 2. */ static inline uint64_t align_up(uint64_t x, uint64_t size) { @@ -186,7 +191,7 @@ static inline uint32_t atoi_non_negative(const char *name, const char *num_str) } int guest_vsnprintf(char *buf, int n, const char *fmt, va_list args); -int guest_snprintf(char *buf, int n, const char *fmt, ...); +__printf(3, 4) int guest_snprintf(char *buf, int n, const char *fmt, ...); char *strdup_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2), nonnull(1))); diff --git a/tools/testing/selftests/kvm/include/ucall_common.h b/tools/testing/selftests/kvm/include/ucall_common.h index ce33d306c2cb..d9d6581b8d4f 100644 --- a/tools/testing/selftests/kvm/include/ucall_common.h +++ b/tools/testing/selftests/kvm/include/ucall_common.h @@ -34,9 +34,10 @@ void ucall_arch_do_ucall(vm_vaddr_t uc); void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu); void ucall(uint64_t cmd, int nargs, ...); -void ucall_fmt(uint64_t cmd, const char *fmt, ...); -void ucall_assert(uint64_t cmd, const char *exp, const char *file, - unsigned int line, const char *fmt, ...); +__printf(2, 3) void ucall_fmt(uint64_t cmd, const char *fmt, ...); +__printf(5, 6) void ucall_assert(uint64_t cmd, const char *exp, + const char *file, unsigned int line, + const char *fmt, ...); uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc); void ucall_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa); int ucall_nr_pages_required(uint64_t page_size); @@ -52,6 +53,17 @@ int ucall_nr_pages_required(uint64_t page_size); #define GUEST_SYNC_ARGS(stage, arg1, arg2, arg3, arg4) \ ucall(UCALL_SYNC, 6, "hello", stage, arg1, arg2, arg3, arg4) #define GUEST_SYNC(stage) ucall(UCALL_SYNC, 2, "hello", stage) +#define GUEST_SYNC1(arg0) ucall(UCALL_SYNC, 1, arg0) +#define GUEST_SYNC2(arg0, arg1) ucall(UCALL_SYNC, 2, arg0, arg1) +#define GUEST_SYNC3(arg0, arg1, arg2) \ + ucall(UCALL_SYNC, 3, arg0, arg1, arg2) +#define GUEST_SYNC4(arg0, arg1, arg2, arg3) \ + ucall(UCALL_SYNC, 4, arg0, arg1, arg2, arg3) +#define GUEST_SYNC5(arg0, arg1, arg2, arg3, arg4) \ + ucall(UCALL_SYNC, 5, arg0, arg1, arg2, arg3, arg4) +#define GUEST_SYNC6(arg0, arg1, arg2, arg3, arg4, arg5) \ + ucall(UCALL_SYNC, 6, arg0, arg1, arg2, arg3, arg4, arg5) + #define GUEST_PRINTF(_fmt, _args...) ucall_fmt(UCALL_PRINTF, _fmt, ##_args) #define GUEST_DONE() ucall(UCALL_DONE, 0) diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 25bc61dac5fb..a84863503fcb 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -15,6 +15,7 @@ #include <asm/msr-index.h> #include <asm/prctl.h> +#include <linux/kvm_para.h> #include <linux/stringify.h> #include "../kvm_util.h" @@ -1194,6 +1195,20 @@ uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2, uint64_t __xen_hypercall(uint64_t nr, uint64_t a0, void *a1); void xen_hypercall(uint64_t nr, uint64_t a0, void *a1); +static inline uint64_t __kvm_hypercall_map_gpa_range(uint64_t gpa, + uint64_t size, uint64_t flags) +{ + return kvm_hypercall(KVM_HC_MAP_GPA_RANGE, gpa, size >> PAGE_SHIFT, flags, 0); +} + +static inline void kvm_hypercall_map_gpa_range(uint64_t gpa, uint64_t size, + uint64_t flags) +{ + uint64_t ret = __kvm_hypercall_map_gpa_range(gpa, size, flags); + + GUEST_ASSERT(!ret); +} + void __vm_xsave_require_permission(uint64_t xfeature, const char *name); #define vm_xsave_require_permission(xfeature) \ diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c index 69f26d80c821..e37dc9c21888 100644 --- a/tools/testing/selftests/kvm/kvm_page_table_test.c +++ b/tools/testing/selftests/kvm/kvm_page_table_test.c @@ -254,7 +254,7 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg) /* Create a VM with enough guest pages */ guest_num_pages = test_mem_size / guest_page_size; - vm = __vm_create_with_vcpus(mode, nr_vcpus, guest_num_pages, + vm = __vm_create_with_vcpus(VM_SHAPE(mode), nr_vcpus, guest_num_pages, guest_code, test_args.vcpus); /* Align down GPA of the testing memslot */ diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c index 6fe12e985ba5..41c776b642c0 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/processor.c +++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c @@ -12,6 +12,7 @@ #include "kvm_util.h" #include "processor.h" #include <linux/bitfield.h> +#include <linux/sizes.h> #define DEFAULT_ARM64_GUEST_STACK_VADDR_MIN 0xac0000 @@ -58,13 +59,25 @@ static uint64_t pte_index(struct kvm_vm *vm, vm_vaddr_t gva) return (gva >> vm->page_shift) & mask; } +static inline bool use_lpa2_pte_format(struct kvm_vm *vm) +{ + return (vm->page_size == SZ_4K || vm->page_size == SZ_16K) && + (vm->pa_bits > 48 || vm->va_bits > 48); +} + static uint64_t addr_pte(struct kvm_vm *vm, uint64_t pa, uint64_t attrs) { uint64_t pte; - pte = pa & GENMASK(47, vm->page_shift); - if (vm->page_shift == 16) - pte |= FIELD_GET(GENMASK(51, 48), pa) << 12; + if (use_lpa2_pte_format(vm)) { + pte = pa & GENMASK(49, vm->page_shift); + pte |= FIELD_GET(GENMASK(51, 50), pa) << 8; + attrs &= ~GENMASK(9, 8); + } else { + pte = pa & GENMASK(47, vm->page_shift); + if (vm->page_shift == 16) + pte |= FIELD_GET(GENMASK(51, 48), pa) << 12; + } pte |= attrs; return pte; @@ -74,9 +87,14 @@ static uint64_t pte_addr(struct kvm_vm *vm, uint64_t pte) { uint64_t pa; - pa = pte & GENMASK(47, vm->page_shift); - if (vm->page_shift == 16) - pa |= FIELD_GET(GENMASK(15, 12), pte) << 48; + if (use_lpa2_pte_format(vm)) { + pa = pte & GENMASK(49, vm->page_shift); + pa |= FIELD_GET(GENMASK(9, 8), pte) << 50; + } else { + pa = pte & GENMASK(47, vm->page_shift); + if (vm->page_shift == 16) + pa |= FIELD_GET(GENMASK(15, 12), pte) << 48; + } return pa; } @@ -266,9 +284,6 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init) /* Configure base granule size */ switch (vm->mode) { - case VM_MODE_P52V48_4K: - TEST_FAIL("AArch64 does not support 4K sized pages " - "with 52-bit physical address ranges"); case VM_MODE_PXXV48_4K: TEST_FAIL("AArch64 does not support 4K sized pages " "with ANY-bit physical address ranges"); @@ -278,12 +293,14 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init) case VM_MODE_P36V48_64K: tcr_el1 |= 1ul << 14; /* TG0 = 64KB */ break; + case VM_MODE_P52V48_16K: case VM_MODE_P48V48_16K: case VM_MODE_P40V48_16K: case VM_MODE_P36V48_16K: case VM_MODE_P36V47_16K: tcr_el1 |= 2ul << 14; /* TG0 = 16KB */ break; + case VM_MODE_P52V48_4K: case VM_MODE_P48V48_4K: case VM_MODE_P40V48_4K: case VM_MODE_P36V48_4K: @@ -297,6 +314,8 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init) /* Configure output size */ switch (vm->mode) { + case VM_MODE_P52V48_4K: + case VM_MODE_P52V48_16K: case VM_MODE_P52V48_64K: tcr_el1 |= 6ul << 32; /* IPS = 52 bits */ ttbr0_el1 |= FIELD_GET(GENMASK(51, 48), vm->pgd) << 2; @@ -325,6 +344,8 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init) /* TCR_EL1 |= IRGN0:WBWA | ORGN0:WBWA | SH0:Inner-Shareable */; tcr_el1 |= (1 << 8) | (1 << 10) | (3 << 12); tcr_el1 |= (64 - vm->va_bits) /* T0SZ */; + if (use_lpa2_pte_format(vm)) + tcr_el1 |= (1ul << 59) /* DS */; vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_SCTLR_EL1), sctlr_el1); vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TCR_EL1), tcr_el1); @@ -492,12 +513,24 @@ uint32_t guest_get_vcpuid(void) return read_sysreg(tpidr_el1); } -void aarch64_get_supported_page_sizes(uint32_t ipa, - bool *ps4k, bool *ps16k, bool *ps64k) +static uint32_t max_ipa_for_page_size(uint32_t vm_ipa, uint32_t gran, + uint32_t not_sup_val, uint32_t ipa52_min_val) +{ + if (gran == not_sup_val) + return 0; + else if (gran >= ipa52_min_val && vm_ipa >= 52) + return 52; + else + return min(vm_ipa, 48U); +} + +void aarch64_get_supported_page_sizes(uint32_t ipa, uint32_t *ipa4k, + uint32_t *ipa16k, uint32_t *ipa64k) { struct kvm_vcpu_init preferred_init; int kvm_fd, vm_fd, vcpu_fd, err; uint64_t val; + uint32_t gran; struct kvm_one_reg reg = { .id = KVM_ARM64_SYS_REG(SYS_ID_AA64MMFR0_EL1), .addr = (uint64_t)&val, @@ -518,9 +551,17 @@ void aarch64_get_supported_page_sizes(uint32_t ipa, err = ioctl(vcpu_fd, KVM_GET_ONE_REG, ®); TEST_ASSERT(err == 0, KVM_IOCTL_ERROR(KVM_GET_ONE_REG, vcpu_fd)); - *ps4k = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN4), val) != 0xf; - *ps64k = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN64), val) == 0; - *ps16k = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN16), val) != 0; + gran = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN4), val); + *ipa4k = max_ipa_for_page_size(ipa, gran, ID_AA64MMFR0_EL1_TGRAN4_NI, + ID_AA64MMFR0_EL1_TGRAN4_52_BIT); + + gran = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN64), val); + *ipa64k = max_ipa_for_page_size(ipa, gran, ID_AA64MMFR0_EL1_TGRAN64_NI, + ID_AA64MMFR0_EL1_TGRAN64_IMP); + + gran = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_EL1_TGRAN16), val); + *ipa16k = max_ipa_for_page_size(ipa, gran, ID_AA64MMFR0_EL1_TGRAN16_NI, + ID_AA64MMFR0_EL1_TGRAN16_52_BIT); close(vcpu_fd); close(vm_fd); diff --git a/tools/testing/selftests/kvm/lib/guest_modes.c b/tools/testing/selftests/kvm/lib/guest_modes.c index 1df3ce4b16fd..b04901e55138 100644 --- a/tools/testing/selftests/kvm/lib/guest_modes.c +++ b/tools/testing/selftests/kvm/lib/guest_modes.c @@ -14,37 +14,33 @@ struct guest_mode guest_modes[NUM_VM_MODES]; void guest_modes_append_default(void) { #ifndef __aarch64__ - guest_mode_append(VM_MODE_DEFAULT, true, true); + guest_mode_append(VM_MODE_DEFAULT, true); #else { unsigned int limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE); - bool ps4k, ps16k, ps64k; + uint32_t ipa4k, ipa16k, ipa64k; int i; - aarch64_get_supported_page_sizes(limit, &ps4k, &ps16k, &ps64k); + aarch64_get_supported_page_sizes(limit, &ipa4k, &ipa16k, &ipa64k); - vm_mode_default = NUM_VM_MODES; + guest_mode_append(VM_MODE_P52V48_4K, ipa4k >= 52); + guest_mode_append(VM_MODE_P52V48_16K, ipa16k >= 52); + guest_mode_append(VM_MODE_P52V48_64K, ipa64k >= 52); - if (limit >= 52) - guest_mode_append(VM_MODE_P52V48_64K, ps64k, ps64k); - if (limit >= 48) { - guest_mode_append(VM_MODE_P48V48_4K, ps4k, ps4k); - guest_mode_append(VM_MODE_P48V48_16K, ps16k, ps16k); - guest_mode_append(VM_MODE_P48V48_64K, ps64k, ps64k); - } - if (limit >= 40) { - guest_mode_append(VM_MODE_P40V48_4K, ps4k, ps4k); - guest_mode_append(VM_MODE_P40V48_16K, ps16k, ps16k); - guest_mode_append(VM_MODE_P40V48_64K, ps64k, ps64k); - if (ps4k) - vm_mode_default = VM_MODE_P40V48_4K; - } - if (limit >= 36) { - guest_mode_append(VM_MODE_P36V48_4K, ps4k, ps4k); - guest_mode_append(VM_MODE_P36V48_16K, ps16k, ps16k); - guest_mode_append(VM_MODE_P36V48_64K, ps64k, ps64k); - guest_mode_append(VM_MODE_P36V47_16K, ps16k, ps16k); - } + guest_mode_append(VM_MODE_P48V48_4K, ipa4k >= 48); + guest_mode_append(VM_MODE_P48V48_16K, ipa16k >= 48); + guest_mode_append(VM_MODE_P48V48_64K, ipa64k >= 48); + + guest_mode_append(VM_MODE_P40V48_4K, ipa4k >= 40); + guest_mode_append(VM_MODE_P40V48_16K, ipa16k >= 40); + guest_mode_append(VM_MODE_P40V48_64K, ipa64k >= 40); + + guest_mode_append(VM_MODE_P36V48_4K, ipa4k >= 36); + guest_mode_append(VM_MODE_P36V48_16K, ipa16k >= 36); + guest_mode_append(VM_MODE_P36V48_64K, ipa64k >= 36); + guest_mode_append(VM_MODE_P36V47_16K, ipa16k >= 36); + + vm_mode_default = ipa4k >= 40 ? VM_MODE_P40V48_4K : NUM_VM_MODES; /* * Pick the first supported IPA size if the default @@ -72,7 +68,7 @@ void guest_modes_append_default(void) close(kvm_fd); /* Starting with z13 we have 47bits of physical address */ if (info.ibc >= 0x30) - guest_mode_append(VM_MODE_P47V64_4K, true, true); + guest_mode_append(VM_MODE_P47V64_4K, true); } #endif #ifdef __riscv @@ -80,9 +76,9 @@ void guest_modes_append_default(void) unsigned int sz = kvm_check_cap(KVM_CAP_VM_GPA_BITS); if (sz >= 52) - guest_mode_append(VM_MODE_P52V48_4K, true, true); + guest_mode_append(VM_MODE_P52V48_4K, true); if (sz >= 48) - guest_mode_append(VM_MODE_P48V48_4K, true, true); + guest_mode_append(VM_MODE_P48V48_4K, true); } #endif } diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 7a8af1821f5d..e066d584c656 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -148,6 +148,7 @@ const char *vm_guest_mode_string(uint32_t i) { static const char * const strings[] = { [VM_MODE_P52V48_4K] = "PA-bits:52, VA-bits:48, 4K pages", + [VM_MODE_P52V48_16K] = "PA-bits:52, VA-bits:48, 16K pages", [VM_MODE_P52V48_64K] = "PA-bits:52, VA-bits:48, 64K pages", [VM_MODE_P48V48_4K] = "PA-bits:48, VA-bits:48, 4K pages", [VM_MODE_P48V48_16K] = "PA-bits:48, VA-bits:48, 16K pages", @@ -173,6 +174,7 @@ const char *vm_guest_mode_string(uint32_t i) const struct vm_guest_mode_params vm_guest_mode_params[] = { [VM_MODE_P52V48_4K] = { 52, 48, 0x1000, 12 }, + [VM_MODE_P52V48_16K] = { 52, 48, 0x4000, 14 }, [VM_MODE_P52V48_64K] = { 52, 48, 0x10000, 16 }, [VM_MODE_P48V48_4K] = { 48, 48, 0x1000, 12 }, [VM_MODE_P48V48_16K] = { 48, 48, 0x4000, 14 }, @@ -209,7 +211,7 @@ __weak void vm_vaddr_populate_bitmap(struct kvm_vm *vm) (1ULL << (vm->va_bits - 1)) >> vm->page_shift); } -struct kvm_vm *____vm_create(enum vm_guest_mode mode) +struct kvm_vm *____vm_create(struct vm_shape shape) { struct kvm_vm *vm; @@ -221,13 +223,13 @@ struct kvm_vm *____vm_create(enum vm_guest_mode mode) vm->regions.hva_tree = RB_ROOT; hash_init(vm->regions.slot_hash); - vm->mode = mode; - vm->type = 0; + vm->mode = shape.mode; + vm->type = shape.type; - vm->pa_bits = vm_guest_mode_params[mode].pa_bits; - vm->va_bits = vm_guest_mode_params[mode].va_bits; - vm->page_size = vm_guest_mode_params[mode].page_size; - vm->page_shift = vm_guest_mode_params[mode].page_shift; + vm->pa_bits = vm_guest_mode_params[vm->mode].pa_bits; + vm->va_bits = vm_guest_mode_params[vm->mode].va_bits; + vm->page_size = vm_guest_mode_params[vm->mode].page_size; + vm->page_shift = vm_guest_mode_params[vm->mode].page_shift; /* Setup mode specific traits. */ switch (vm->mode) { @@ -251,6 +253,7 @@ struct kvm_vm *____vm_create(enum vm_guest_mode mode) case VM_MODE_P36V48_64K: vm->pgtable_levels = 3; break; + case VM_MODE_P52V48_16K: case VM_MODE_P48V48_16K: case VM_MODE_P40V48_16K: case VM_MODE_P36V48_16K: @@ -265,7 +268,7 @@ struct kvm_vm *____vm_create(enum vm_guest_mode mode) /* * Ignore KVM support for 5-level paging (vm->va_bits == 57), * it doesn't take effect unless a CR4.LA57 is set, which it - * isn't for this VM_MODE. + * isn't for this mode (48-bit virtual address space). */ TEST_ASSERT(vm->va_bits == 48 || vm->va_bits == 57, "Linear address width (%d bits) not supported", @@ -285,10 +288,11 @@ struct kvm_vm *____vm_create(enum vm_guest_mode mode) vm->pgtable_levels = 5; break; default: - TEST_FAIL("Unknown guest mode, mode: 0x%x", mode); + TEST_FAIL("Unknown guest mode: 0x%x", vm->mode); } #ifdef __aarch64__ + TEST_ASSERT(!vm->type, "ARM doesn't support test-provided types"); if (vm->pa_bits != 40) vm->type = KVM_VM_TYPE_ARM_IPA_SIZE(vm->pa_bits); #endif @@ -347,19 +351,19 @@ static uint64_t vm_nr_pages_required(enum vm_guest_mode mode, return vm_adjust_num_guest_pages(mode, nr_pages); } -struct kvm_vm *__vm_create(enum vm_guest_mode mode, uint32_t nr_runnable_vcpus, +struct kvm_vm *__vm_create(struct vm_shape shape, uint32_t nr_runnable_vcpus, uint64_t nr_extra_pages) { - uint64_t nr_pages = vm_nr_pages_required(mode, nr_runnable_vcpus, + uint64_t nr_pages = vm_nr_pages_required(shape.mode, nr_runnable_vcpus, nr_extra_pages); struct userspace_mem_region *slot0; struct kvm_vm *vm; int i; - pr_debug("%s: mode='%s' pages='%ld'\n", __func__, - vm_guest_mode_string(mode), nr_pages); + pr_debug("%s: mode='%s' type='%d', pages='%ld'\n", __func__, + vm_guest_mode_string(shape.mode), shape.type, nr_pages); - vm = ____vm_create(mode); + vm = ____vm_create(shape); vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, 0, 0, nr_pages, 0); for (i = 0; i < NR_MEM_REGIONS; i++) @@ -400,7 +404,7 @@ struct kvm_vm *__vm_create(enum vm_guest_mode mode, uint32_t nr_runnable_vcpus, * extra_mem_pages is only used to calculate the maximum page table size, * no real memory allocation for non-slot0 memory in this function. */ -struct kvm_vm *__vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus, +struct kvm_vm *__vm_create_with_vcpus(struct vm_shape shape, uint32_t nr_vcpus, uint64_t extra_mem_pages, void *guest_code, struct kvm_vcpu *vcpus[]) { @@ -409,7 +413,7 @@ struct kvm_vm *__vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus TEST_ASSERT(!nr_vcpus || vcpus, "Must provide vCPU array"); - vm = __vm_create(mode, nr_vcpus, extra_mem_pages); + vm = __vm_create(shape, nr_vcpus, extra_mem_pages); for (i = 0; i < nr_vcpus; ++i) vcpus[i] = vm_vcpu_add(vm, i, guest_code); @@ -417,15 +421,15 @@ struct kvm_vm *__vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus return vm; } -struct kvm_vm *__vm_create_with_one_vcpu(struct kvm_vcpu **vcpu, - uint64_t extra_mem_pages, - void *guest_code) +struct kvm_vm *__vm_create_shape_with_one_vcpu(struct vm_shape shape, + struct kvm_vcpu **vcpu, + uint64_t extra_mem_pages, + void *guest_code) { struct kvm_vcpu *vcpus[1]; struct kvm_vm *vm; - vm = __vm_create_with_vcpus(VM_MODE_DEFAULT, 1, extra_mem_pages, - guest_code, vcpus); + vm = __vm_create_with_vcpus(shape, 1, extra_mem_pages, guest_code, vcpus); *vcpu = vcpus[0]; return vm; @@ -453,8 +457,9 @@ void kvm_vm_restart(struct kvm_vm *vmp) vm_create_irqchip(vmp); hash_for_each(vmp->regions.slot_hash, ctr, region, slot_node) { - int ret = ioctl(vmp->fd, KVM_SET_USER_MEMORY_REGION, ®ion->region); - TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n" + int ret = ioctl(vmp->fd, KVM_SET_USER_MEMORY_REGION2, ®ion->region); + + TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION2 IOCTL failed,\n" " rc: %i errno: %i\n" " slot: %u flags: 0x%x\n" " guest_phys_addr: 0x%llx size: 0x%llx", @@ -590,35 +595,6 @@ userspace_mem_region_find(struct kvm_vm *vm, uint64_t start, uint64_t end) return NULL; } -/* - * KVM Userspace Memory Region Find - * - * Input Args: - * vm - Virtual Machine - * start - Starting VM physical address - * end - Ending VM physical address, inclusive. - * - * Output Args: None - * - * Return: - * Pointer to overlapping region, NULL if no such region. - * - * Public interface to userspace_mem_region_find. Allows tests to look up - * the memslot datastructure for a given range of guest physical memory. - */ -struct kvm_userspace_memory_region * -kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start, - uint64_t end) -{ - struct userspace_mem_region *region; - - region = userspace_mem_region_find(vm, start, end); - if (!region) - return NULL; - - return ®ion->region; -} - __weak void vcpu_arch_free(struct kvm_vcpu *vcpu) { @@ -686,7 +662,7 @@ static void __vm_mem_region_delete(struct kvm_vm *vm, } region->region.memory_size = 0; - vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION, ®ion->region); + vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, ®ion->region); sparsebit_free(®ion->unused_phy_pages); ret = munmap(region->mmap_start, region->mmap_size); @@ -697,6 +673,8 @@ static void __vm_mem_region_delete(struct kvm_vm *vm, TEST_ASSERT(!ret, __KVM_SYSCALL_ERROR("munmap()", ret)); close(region->fd); } + if (region->region.guest_memfd >= 0) + close(region->region.guest_memfd); free(region); } @@ -898,36 +876,44 @@ void vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags, errno, strerror(errno)); } -/* - * VM Userspace Memory Region Add - * - * Input Args: - * vm - Virtual Machine - * src_type - Storage source for this region. - * NULL to use anonymous memory. - * guest_paddr - Starting guest physical address - * slot - KVM region slot - * npages - Number of physical pages - * flags - KVM memory region flags (e.g. KVM_MEM_LOG_DIRTY_PAGES) - * - * Output Args: None - * - * Return: None - * - * Allocates a memory area of the number of pages specified by npages - * and maps it to the VM specified by vm, at a starting physical address - * given by guest_paddr. The region is created with a KVM region slot - * given by slot, which must be unique and < KVM_MEM_SLOTS_NUM. The - * region is created with the flags given by flags. - */ -void vm_userspace_mem_region_add(struct kvm_vm *vm, - enum vm_mem_backing_src_type src_type, - uint64_t guest_paddr, uint32_t slot, uint64_t npages, - uint32_t flags) +int __vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags, + uint64_t gpa, uint64_t size, void *hva, + uint32_t guest_memfd, uint64_t guest_memfd_offset) +{ + struct kvm_userspace_memory_region2 region = { + .slot = slot, + .flags = flags, + .guest_phys_addr = gpa, + .memory_size = size, + .userspace_addr = (uintptr_t)hva, + .guest_memfd = guest_memfd, + .guest_memfd_offset = guest_memfd_offset, + }; + + return ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION2, ®ion); +} + +void vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags, + uint64_t gpa, uint64_t size, void *hva, + uint32_t guest_memfd, uint64_t guest_memfd_offset) +{ + int ret = __vm_set_user_memory_region2(vm, slot, flags, gpa, size, hva, + guest_memfd, guest_memfd_offset); + + TEST_ASSERT(!ret, "KVM_SET_USER_MEMORY_REGION2 failed, errno = %d (%s)", + errno, strerror(errno)); +} + + +/* FIXME: This thing needs to be ripped apart and rewritten. */ +void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, + uint64_t guest_paddr, uint32_t slot, uint64_t npages, + uint32_t flags, int guest_memfd, uint64_t guest_memfd_offset) { int ret; struct userspace_mem_region *region; size_t backing_src_pagesz = get_backing_src_pagesz(src_type); + size_t mem_size = npages * vm->page_size; size_t alignment; TEST_ASSERT(vm_adjust_num_guest_pages(vm->mode, npages) == npages, @@ -980,7 +966,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, /* Allocate and initialize new mem region structure. */ region = calloc(1, sizeof(*region)); TEST_ASSERT(region != NULL, "Insufficient Memory"); - region->mmap_size = npages * vm->page_size; + region->mmap_size = mem_size; #ifdef __s390x__ /* On s390x, the host address must be aligned to 1M (due to PGSTEs) */ @@ -1027,14 +1013,38 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, /* As needed perform madvise */ if ((src_type == VM_MEM_SRC_ANONYMOUS || src_type == VM_MEM_SRC_ANONYMOUS_THP) && thp_configured()) { - ret = madvise(region->host_mem, npages * vm->page_size, + ret = madvise(region->host_mem, mem_size, src_type == VM_MEM_SRC_ANONYMOUS ? MADV_NOHUGEPAGE : MADV_HUGEPAGE); TEST_ASSERT(ret == 0, "madvise failed, addr: %p length: 0x%lx src_type: %s", - region->host_mem, npages * vm->page_size, + region->host_mem, mem_size, vm_mem_backing_src_alias(src_type)->name); } region->backing_src_type = src_type; + + if (flags & KVM_MEM_GUEST_MEMFD) { + if (guest_memfd < 0) { + uint32_t guest_memfd_flags = 0; + TEST_ASSERT(!guest_memfd_offset, + "Offset must be zero when creating new guest_memfd"); + guest_memfd = vm_create_guest_memfd(vm, mem_size, guest_memfd_flags); + } else { + /* + * Install a unique fd for each memslot so that the fd + * can be closed when the region is deleted without + * needing to track if the fd is owned by the framework + * or by the caller. + */ + guest_memfd = dup(guest_memfd); + TEST_ASSERT(guest_memfd >= 0, __KVM_SYSCALL_ERROR("dup()", guest_memfd)); + } + + region->region.guest_memfd = guest_memfd; + region->region.guest_memfd_offset = guest_memfd_offset; + } else { + region->region.guest_memfd = -1; + } + region->unused_phy_pages = sparsebit_alloc(); sparsebit_set_num(region->unused_phy_pages, guest_paddr >> vm->page_shift, npages); @@ -1043,13 +1053,14 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, region->region.guest_phys_addr = guest_paddr; region->region.memory_size = npages * vm->page_size; region->region.userspace_addr = (uintptr_t) region->host_mem; - ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION, ®ion->region); - TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n" + ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, ®ion->region); + TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION2 IOCTL failed,\n" " rc: %i errno: %i\n" " slot: %u flags: 0x%x\n" - " guest_phys_addr: 0x%lx size: 0x%lx", + " guest_phys_addr: 0x%lx size: 0x%lx guest_memfd: %d\n", ret, errno, slot, flags, - guest_paddr, (uint64_t) region->region.memory_size); + guest_paddr, (uint64_t) region->region.memory_size, + region->region.guest_memfd); /* Add to quick lookup data structures */ vm_userspace_mem_region_gpa_insert(&vm->regions.gpa_tree, region); @@ -1070,6 +1081,14 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, } } +void vm_userspace_mem_region_add(struct kvm_vm *vm, + enum vm_mem_backing_src_type src_type, + uint64_t guest_paddr, uint32_t slot, + uint64_t npages, uint32_t flags) +{ + vm_mem_add(vm, src_type, guest_paddr, slot, npages, flags, -1, 0); +} + /* * Memslot to region * @@ -1126,9 +1145,9 @@ void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags) region->region.flags = flags; - ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION, ®ion->region); + ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, ®ion->region); - TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n" + TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION2 IOCTL failed,\n" " rc: %i errno: %i slot: %u flags: 0x%x", ret, errno, slot, flags); } @@ -1156,9 +1175,9 @@ void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa) region->region.guest_phys_addr = new_gpa; - ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION, ®ion->region); + ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, ®ion->region); - TEST_ASSERT(!ret, "KVM_SET_USER_MEMORY_REGION failed\n" + TEST_ASSERT(!ret, "KVM_SET_USER_MEMORY_REGION2 failed\n" "ret: %i errno: %i slot: %u new_gpa: 0x%lx", ret, errno, slot, new_gpa); } @@ -1181,6 +1200,34 @@ void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot) __vm_mem_region_delete(vm, memslot2region(vm, slot), true); } +void vm_guest_mem_fallocate(struct kvm_vm *vm, uint64_t base, uint64_t size, + bool punch_hole) +{ + const int mode = FALLOC_FL_KEEP_SIZE | (punch_hole ? FALLOC_FL_PUNCH_HOLE : 0); + struct userspace_mem_region *region; + uint64_t end = base + size; + uint64_t gpa, len; + off_t fd_offset; + int ret; + + for (gpa = base; gpa < end; gpa += len) { + uint64_t offset; + + region = userspace_mem_region_find(vm, gpa, gpa); + TEST_ASSERT(region && region->region.flags & KVM_MEM_GUEST_MEMFD, + "Private memory region not found for GPA 0x%lx", gpa); + + offset = gpa - region->region.guest_phys_addr; + fd_offset = region->region.guest_memfd_offset + offset; + len = min_t(uint64_t, end - gpa, region->region.memory_size - offset); + + ret = fallocate(region->region.guest_memfd, mode, fd_offset, len); + TEST_ASSERT(!ret, "fallocate() failed to %s at %lx (len = %lu), fd = %d, mode = %x, offset = %lx\n", + punch_hole ? "punch hole" : "allocate", gpa, len, + region->region.guest_memfd, mode, fd_offset); + } +} + /* Returns the size of a vCPU's kvm_run structure. */ static int vcpu_mmap_sz(void) { @@ -1227,7 +1274,7 @@ struct kvm_vcpu *__vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id) vcpu->vm = vm; vcpu->id = vcpu_id; vcpu->fd = __vm_ioctl(vm, KVM_CREATE_VCPU, (void *)(unsigned long)vcpu_id); - TEST_ASSERT(vcpu->fd >= 0, KVM_IOCTL_ERROR(KVM_CREATE_VCPU, vcpu->fd)); + TEST_ASSERT_VM_VCPU_IOCTL(vcpu->fd >= 0, KVM_CREATE_VCPU, vcpu->fd, vm); TEST_ASSERT(vcpu_mmap_sz() >= sizeof(*vcpu->run), "vcpu mmap size " "smaller than expected, vcpu_mmap_sz: %i expected_min: %zi", diff --git a/tools/testing/selftests/kvm/lib/memstress.c b/tools/testing/selftests/kvm/lib/memstress.c index df457452d146..d05487e5a371 100644 --- a/tools/testing/selftests/kvm/lib/memstress.c +++ b/tools/testing/selftests/kvm/lib/memstress.c @@ -168,7 +168,8 @@ struct kvm_vm *memstress_create_vm(enum vm_guest_mode mode, int nr_vcpus, * The memory is also added to memslot 0, but that's a benign side * effect as KVM allows aliasing HVAs in meslots. */ - vm = __vm_create_with_vcpus(mode, nr_vcpus, slot0_pages + guest_num_pages, + vm = __vm_create_with_vcpus(VM_SHAPE(mode), nr_vcpus, + slot0_pages + guest_num_pages, memstress_guest_code, vcpus); args->vm = vm; diff --git a/tools/testing/selftests/kvm/lib/riscv/processor.c b/tools/testing/selftests/kvm/lib/riscv/processor.c index d146ca71e0c0..7ca736fb4194 100644 --- a/tools/testing/selftests/kvm/lib/riscv/processor.c +++ b/tools/testing/selftests/kvm/lib/riscv/processor.c @@ -201,7 +201,7 @@ void riscv_vcpu_mmu_setup(struct kvm_vcpu *vcpu) satp = (vm->pgd >> PGTBL_PAGE_SIZE_SHIFT) & SATP_PPN; satp |= SATP_MODE_48; - vcpu_set_reg(vcpu, RISCV_CSR_REG(satp), satp); + vcpu_set_reg(vcpu, RISCV_GENERAL_CSR_REG(satp), satp); } void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, uint8_t indent) @@ -315,7 +315,7 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, vcpu_set_reg(vcpu, RISCV_CORE_REG(regs.pc), (unsigned long)guest_code); /* Setup default exception vector of guest */ - vcpu_set_reg(vcpu, RISCV_CSR_REG(stvec), (unsigned long)guest_unexp_trap); + vcpu_set_reg(vcpu, RISCV_GENERAL_CSR_REG(stvec), (unsigned long)guest_unexp_trap); return vcpu; } @@ -367,3 +367,48 @@ void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...) void assert_on_unhandled_exception(struct kvm_vcpu *vcpu) { } + +struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0, + unsigned long arg1, unsigned long arg2, + unsigned long arg3, unsigned long arg4, + unsigned long arg5) +{ + register uintptr_t a0 asm ("a0") = (uintptr_t)(arg0); + register uintptr_t a1 asm ("a1") = (uintptr_t)(arg1); + register uintptr_t a2 asm ("a2") = (uintptr_t)(arg2); + register uintptr_t a3 asm ("a3") = (uintptr_t)(arg3); + register uintptr_t a4 asm ("a4") = (uintptr_t)(arg4); + register uintptr_t a5 asm ("a5") = (uintptr_t)(arg5); + register uintptr_t a6 asm ("a6") = (uintptr_t)(fid); + register uintptr_t a7 asm ("a7") = (uintptr_t)(ext); + struct sbiret ret; + + asm volatile ( + "ecall" + : "+r" (a0), "+r" (a1) + : "r" (a2), "r" (a3), "r" (a4), "r" (a5), "r" (a6), "r" (a7) + : "memory"); + ret.error = a0; + ret.value = a1; + + return ret; +} + +bool guest_sbi_probe_extension(int extid, long *out_val) +{ + struct sbiret ret; + + ret = sbi_ecall(SBI_EXT_BASE, SBI_EXT_BASE_PROBE_EXT, extid, + 0, 0, 0, 0, 0); + + __GUEST_ASSERT(!ret.error || ret.error == SBI_ERR_NOT_SUPPORTED, + "ret.error=%ld, ret.value=%ld\n", ret.error, ret.value); + + if (ret.error == SBI_ERR_NOT_SUPPORTED) + return false; + + if (out_val) + *out_val = ret.value; + + return true; +} diff --git a/tools/testing/selftests/kvm/lib/riscv/ucall.c b/tools/testing/selftests/kvm/lib/riscv/ucall.c index fe6d1004f018..14ee17151a59 100644 --- a/tools/testing/selftests/kvm/lib/riscv/ucall.c +++ b/tools/testing/selftests/kvm/lib/riscv/ucall.c @@ -10,32 +10,6 @@ #include "kvm_util.h" #include "processor.h" -struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0, - unsigned long arg1, unsigned long arg2, - unsigned long arg3, unsigned long arg4, - unsigned long arg5) -{ - register uintptr_t a0 asm ("a0") = (uintptr_t)(arg0); - register uintptr_t a1 asm ("a1") = (uintptr_t)(arg1); - register uintptr_t a2 asm ("a2") = (uintptr_t)(arg2); - register uintptr_t a3 asm ("a3") = (uintptr_t)(arg3); - register uintptr_t a4 asm ("a4") = (uintptr_t)(arg4); - register uintptr_t a5 asm ("a5") = (uintptr_t)(arg5); - register uintptr_t a6 asm ("a6") = (uintptr_t)(fid); - register uintptr_t a7 asm ("a7") = (uintptr_t)(ext); - struct sbiret ret; - - asm volatile ( - "ecall" - : "+r" (a0), "+r" (a1) - : "r" (a2), "r" (a3), "r" (a4), "r" (a5), "r" (a6), "r" (a7) - : "memory"); - ret.error = a0; - ret.value = a1; - - return ret; -} - void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu) { struct kvm_run *run = vcpu->run; diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c index 25de4b8bc347..6652108816db 100644 --- a/tools/testing/selftests/kvm/riscv/get-reg-list.c +++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c @@ -12,6 +12,11 @@ #define REG_MASK (KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK) +enum { + VCPU_FEATURE_ISA_EXT = 0, + VCPU_FEATURE_SBI_EXT, +}; + static bool isa_ext_cant_disable[KVM_RISCV_ISA_EXT_MAX]; bool filter_reg(__u64 reg) @@ -28,31 +33,47 @@ bool filter_reg(__u64 reg) * * Note: The below list is alphabetically sorted. */ - case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_A: - case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_C: - case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_D: - case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_F: - case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_H: - case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_I: - case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_M: - case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_V: - case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SMSTATEEN: - case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SSAIA: - case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SSTC: - case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SVINVAL: - case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SVNAPOT: - case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SVPBMT: - case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZBA: - case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZBB: - case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZBS: - case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICBOM: - case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICBOZ: - case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICNTR: - case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICOND: - case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICSR: - case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZIFENCEI: - case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZIHINTPAUSE: - case KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZIHPM: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_A: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_C: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_D: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_F: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_H: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_I: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_M: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_V: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SMSTATEEN: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SSAIA: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SSTC: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVINVAL: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVNAPOT: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVPBMT: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBA: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBB: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBS: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOM: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOZ: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICNTR: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICOND: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICSR: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZIFENCEI: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZIHINTPAUSE: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZIHPM: + /* + * Like ISA_EXT registers, SBI_EXT registers are only visible when the + * host supports them and disabling them does not affect the visibility + * of the SBI_EXT register itself. + */ + case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_V01: + case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_TIME: + case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_IPI: + case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_RFENCE: + case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_SRST: + case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_HSM: + case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_PMU: + case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_DBCN: + case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_STA: + case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_EXPERIMENTAL: + case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_VENDOR: return true; /* AIA registers are always available when Ssaia can't be disabled */ case KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(siselect): @@ -75,12 +96,12 @@ bool check_reject_set(int err) return err == EINVAL; } -static inline bool vcpu_has_ext(struct kvm_vcpu *vcpu, int ext) +static bool vcpu_has_ext(struct kvm_vcpu *vcpu, uint64_t ext_id) { int ret; unsigned long value; - ret = __vcpu_get_reg(vcpu, RISCV_ISA_EXT_REG(ext), &value); + ret = __vcpu_get_reg(vcpu, ext_id, &value); return (ret) ? false : !!value; } @@ -88,6 +109,7 @@ void finalize_vcpu(struct kvm_vcpu *vcpu, struct vcpu_reg_list *c) { unsigned long isa_ext_state[KVM_RISCV_ISA_EXT_MAX] = { 0 }; struct vcpu_reg_sublist *s; + uint64_t feature; int rc; for (int i = 0; i < KVM_RISCV_ISA_EXT_MAX; i++) @@ -103,15 +125,31 @@ void finalize_vcpu(struct kvm_vcpu *vcpu, struct vcpu_reg_list *c) isa_ext_cant_disable[i] = true; } + for (int i = 0; i < KVM_RISCV_SBI_EXT_MAX; i++) { + rc = __vcpu_set_reg(vcpu, RISCV_SBI_EXT_REG(i), 0); + TEST_ASSERT(!rc || (rc == -1 && errno == ENOENT), "Unexpected error"); + } + for_each_sublist(c, s) { if (!s->feature) continue; + switch (s->feature_type) { + case VCPU_FEATURE_ISA_EXT: + feature = RISCV_ISA_EXT_REG(s->feature); + break; + case VCPU_FEATURE_SBI_EXT: + feature = RISCV_SBI_EXT_REG(s->feature); + break; + default: + TEST_FAIL("Unknown feature type"); + } + /* Try to enable the desired extension */ - __vcpu_set_reg(vcpu, RISCV_ISA_EXT_REG(s->feature), 1); + __vcpu_set_reg(vcpu, feature, 1); /* Double check whether the desired extension was enabled */ - __TEST_REQUIRE(vcpu_has_ext(vcpu, s->feature), + __TEST_REQUIRE(vcpu_has_ext(vcpu, feature), "%s not available, skipping tests\n", s->name); } } @@ -335,15 +373,10 @@ static const char *fp_d_id_to_str(const char *prefix, __u64 id) } #define KVM_ISA_EXT_ARR(ext) \ -[KVM_RISCV_ISA_EXT_##ext] = "KVM_RISCV_ISA_EXT_" #ext +[KVM_RISCV_ISA_EXT_##ext] = "KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_" #ext -static const char *isa_ext_id_to_str(const char *prefix, __u64 id) +static const char *isa_ext_single_id_to_str(__u64 reg_off) { - /* reg_off is the offset into unsigned long kvm_isa_ext_arr[] */ - __u64 reg_off = id & ~(REG_MASK | KVM_REG_RISCV_ISA_EXT); - - assert((id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_ISA_EXT); - static const char * const kvm_isa_ext_reg_name[] = { KVM_ISA_EXT_ARR(A), KVM_ISA_EXT_ARR(C), @@ -373,11 +406,48 @@ static const char *isa_ext_id_to_str(const char *prefix, __u64 id) }; if (reg_off >= ARRAY_SIZE(kvm_isa_ext_reg_name)) - return strdup_printf("%lld /* UNKNOWN */", reg_off); + return strdup_printf("KVM_REG_RISCV_ISA_SINGLE | %lld /* UNKNOWN */", reg_off); return kvm_isa_ext_reg_name[reg_off]; } +static const char *isa_ext_multi_id_to_str(__u64 reg_subtype, __u64 reg_off) +{ + const char *unknown = ""; + + if (reg_off > KVM_REG_RISCV_ISA_MULTI_REG_LAST) + unknown = " /* UNKNOWN */"; + + switch (reg_subtype) { + case KVM_REG_RISCV_ISA_MULTI_EN: + return strdup_printf("KVM_REG_RISCV_ISA_MULTI_EN | %lld%s", reg_off, unknown); + case KVM_REG_RISCV_ISA_MULTI_DIS: + return strdup_printf("KVM_REG_RISCV_ISA_MULTI_DIS | %lld%s", reg_off, unknown); + } + + return strdup_printf("%lld | %lld /* UNKNOWN */", reg_subtype, reg_off); +} + +static const char *isa_ext_id_to_str(const char *prefix, __u64 id) +{ + __u64 reg_off = id & ~(REG_MASK | KVM_REG_RISCV_ISA_EXT); + __u64 reg_subtype = reg_off & KVM_REG_RISCV_SUBTYPE_MASK; + + assert((id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_ISA_EXT); + + reg_off &= ~KVM_REG_RISCV_SUBTYPE_MASK; + + switch (reg_subtype) { + case KVM_REG_RISCV_ISA_SINGLE: + return isa_ext_single_id_to_str(reg_off); + case KVM_REG_RISCV_ISA_MULTI_EN: + case KVM_REG_RISCV_ISA_MULTI_DIS: + return isa_ext_multi_id_to_str(reg_subtype, reg_off); + } + + return strdup_printf("%lld | %lld /* UNKNOWN */", reg_subtype, reg_off); +} + #define KVM_SBI_EXT_ARR(ext) \ [ext] = "KVM_REG_RISCV_SBI_SINGLE | " #ext @@ -392,6 +462,7 @@ static const char *sbi_ext_single_id_to_str(__u64 reg_off) KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_SRST), KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_HSM), KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_PMU), + KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_STA), KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_EXPERIMENTAL), KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_VENDOR), KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_DBCN), @@ -440,6 +511,32 @@ static const char *sbi_ext_id_to_str(const char *prefix, __u64 id) return strdup_printf("%lld | %lld /* UNKNOWN */", reg_subtype, reg_off); } +static const char *sbi_sta_id_to_str(__u64 reg_off) +{ + switch (reg_off) { + case 0: return "KVM_REG_RISCV_SBI_STA | KVM_REG_RISCV_SBI_STA_REG(shmem_lo)"; + case 1: return "KVM_REG_RISCV_SBI_STA | KVM_REG_RISCV_SBI_STA_REG(shmem_hi)"; + } + return strdup_printf("KVM_REG_RISCV_SBI_STA | %lld /* UNKNOWN */", reg_off); +} + +static const char *sbi_id_to_str(const char *prefix, __u64 id) +{ + __u64 reg_off = id & ~(REG_MASK | KVM_REG_RISCV_SBI_STATE); + __u64 reg_subtype = reg_off & KVM_REG_RISCV_SUBTYPE_MASK; + + assert((id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_SBI_STATE); + + reg_off &= ~KVM_REG_RISCV_SUBTYPE_MASK; + + switch (reg_subtype) { + case KVM_REG_RISCV_SBI_STA: + return sbi_sta_id_to_str(reg_off); + } + + return strdup_printf("%lld | %lld /* UNKNOWN */", reg_subtype, reg_off); +} + void print_reg(const char *prefix, __u64 id) { const char *reg_size = NULL; @@ -496,6 +593,10 @@ void print_reg(const char *prefix, __u64 id) printf("\tKVM_REG_RISCV | %s | KVM_REG_RISCV_SBI_EXT | %s,\n", reg_size, sbi_ext_id_to_str(prefix, id)); break; + case KVM_REG_RISCV_SBI_STATE: + printf("\tKVM_REG_RISCV | %s | KVM_REG_RISCV_SBI_STATE | %s,\n", + reg_size, sbi_id_to_str(prefix, id)); + break; default: printf("\tKVM_REG_RISCV | %s | 0x%llx /* UNKNOWN */,\n", reg_size, id & ~REG_MASK); @@ -561,18 +662,6 @@ static __u64 base_regs[] = { KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_TIMER | KVM_REG_RISCV_TIMER_REG(time), KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_TIMER | KVM_REG_RISCV_TIMER_REG(compare), KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_TIMER | KVM_REG_RISCV_TIMER_REG(state), - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_V01, - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_TIME, - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_IPI, - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_RFENCE, - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_SRST, - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_HSM, - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_PMU, - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_EXPERIMENTAL, - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_VENDOR, - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_DBCN, - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_MULTI_EN | 0, - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_MULTI_DIS | 0, }; /* @@ -583,66 +672,31 @@ static __u64 base_skips_set[] = { KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_TIMER | KVM_REG_RISCV_TIMER_REG(state), }; -static __u64 h_regs[] = { - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_H, +static __u64 sbi_base_regs[] = { + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_V01, + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_TIME, + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_IPI, + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_RFENCE, + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_SRST, + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_HSM, + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_EXPERIMENTAL, + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_VENDOR, +}; + +static __u64 sbi_sta_regs[] = { + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_STA, + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_STATE | KVM_REG_RISCV_SBI_STA | KVM_REG_RISCV_SBI_STA_REG(shmem_lo), + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_SBI_STATE | KVM_REG_RISCV_SBI_STA | KVM_REG_RISCV_SBI_STA_REG(shmem_hi), }; static __u64 zicbom_regs[] = { KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(zicbom_block_size), - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICBOM, + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOM, }; static __u64 zicboz_regs[] = { KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CONFIG | KVM_REG_RISCV_CONFIG_REG(zicboz_block_size), - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICBOZ, -}; - -static __u64 svpbmt_regs[] = { - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SVPBMT, -}; - -static __u64 sstc_regs[] = { - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SSTC, -}; - -static __u64 svinval_regs[] = { - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SVINVAL, -}; - -static __u64 zihintpause_regs[] = { - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZIHINTPAUSE, -}; - -static __u64 zba_regs[] = { - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZBA, -}; - -static __u64 zbb_regs[] = { - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZBB, -}; - -static __u64 zbs_regs[] = { - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZBS, -}; - -static __u64 zicntr_regs[] = { - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICNTR, -}; - -static __u64 zicond_regs[] = { - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICOND, -}; - -static __u64 zicsr_regs[] = { - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZICSR, -}; - -static __u64 zifencei_regs[] = { - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZIFENCEI, -}; - -static __u64 zihpm_regs[] = { - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_ZIHPM, + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOZ, }; static __u64 aia_regs[] = { @@ -653,12 +707,12 @@ static __u64 aia_regs[] = { KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(siph), KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(iprio1h), KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_AIA | KVM_REG_RISCV_CSR_AIA_REG(iprio2h), - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SSAIA, + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SSAIA, }; static __u64 smstateen_regs[] = { KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_CSR | KVM_REG_RISCV_CSR_SMSTATEEN | KVM_REG_RISCV_CSR_SMSTATEEN_REG(sstateen0), - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_SMSTATEEN, + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SMSTATEEN, }; static __u64 fp_f_regs[] = { @@ -695,7 +749,7 @@ static __u64 fp_f_regs[] = { KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[30]), KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(f[31]), KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_F | KVM_REG_RISCV_FP_F_REG(fcsr), - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_F, + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_F, }; static __u64 fp_d_regs[] = { @@ -732,224 +786,142 @@ static __u64 fp_d_regs[] = { KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[30]), KVM_REG_RISCV | KVM_REG_SIZE_U64 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(f[31]), KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_D | KVM_REG_RISCV_FP_D_REG(fcsr), - KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_RISCV_ISA_EXT_D, + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_D, }; -#define BASE_SUBLIST \ +#define SUBLIST_BASE \ {"base", .regs = base_regs, .regs_n = ARRAY_SIZE(base_regs), \ .skips_set = base_skips_set, .skips_set_n = ARRAY_SIZE(base_skips_set),} -#define H_REGS_SUBLIST \ - {"h", .feature = KVM_RISCV_ISA_EXT_H, .regs = h_regs, .regs_n = ARRAY_SIZE(h_regs),} -#define ZICBOM_REGS_SUBLIST \ +#define SUBLIST_SBI_BASE \ + {"sbi-base", .feature_type = VCPU_FEATURE_SBI_EXT, .feature = KVM_RISCV_SBI_EXT_V01, \ + .regs = sbi_base_regs, .regs_n = ARRAY_SIZE(sbi_base_regs),} +#define SUBLIST_SBI_STA \ + {"sbi-sta", .feature_type = VCPU_FEATURE_SBI_EXT, .feature = KVM_RISCV_SBI_EXT_STA, \ + .regs = sbi_sta_regs, .regs_n = ARRAY_SIZE(sbi_sta_regs),} +#define SUBLIST_ZICBOM \ {"zicbom", .feature = KVM_RISCV_ISA_EXT_ZICBOM, .regs = zicbom_regs, .regs_n = ARRAY_SIZE(zicbom_regs),} -#define ZICBOZ_REGS_SUBLIST \ +#define SUBLIST_ZICBOZ \ {"zicboz", .feature = KVM_RISCV_ISA_EXT_ZICBOZ, .regs = zicboz_regs, .regs_n = ARRAY_SIZE(zicboz_regs),} -#define SVPBMT_REGS_SUBLIST \ - {"svpbmt", .feature = KVM_RISCV_ISA_EXT_SVPBMT, .regs = svpbmt_regs, .regs_n = ARRAY_SIZE(svpbmt_regs),} -#define SSTC_REGS_SUBLIST \ - {"sstc", .feature = KVM_RISCV_ISA_EXT_SSTC, .regs = sstc_regs, .regs_n = ARRAY_SIZE(sstc_regs),} -#define SVINVAL_REGS_SUBLIST \ - {"svinval", .feature = KVM_RISCV_ISA_EXT_SVINVAL, .regs = svinval_regs, .regs_n = ARRAY_SIZE(svinval_regs),} -#define ZIHINTPAUSE_REGS_SUBLIST \ - {"zihintpause", .feature = KVM_RISCV_ISA_EXT_ZIHINTPAUSE, .regs = zihintpause_regs, .regs_n = ARRAY_SIZE(zihintpause_regs),} -#define ZBA_REGS_SUBLIST \ - {"zba", .feature = KVM_RISCV_ISA_EXT_ZBA, .regs = zba_regs, .regs_n = ARRAY_SIZE(zba_regs),} -#define ZBB_REGS_SUBLIST \ - {"zbb", .feature = KVM_RISCV_ISA_EXT_ZBB, .regs = zbb_regs, .regs_n = ARRAY_SIZE(zbb_regs),} -#define ZBS_REGS_SUBLIST \ - {"zbs", .feature = KVM_RISCV_ISA_EXT_ZBS, .regs = zbs_regs, .regs_n = ARRAY_SIZE(zbs_regs),} -#define ZICNTR_REGS_SUBLIST \ - {"zicntr", .feature = KVM_RISCV_ISA_EXT_ZICNTR, .regs = zicntr_regs, .regs_n = ARRAY_SIZE(zicntr_regs),} -#define ZICOND_REGS_SUBLIST \ - {"zicond", .feature = KVM_RISCV_ISA_EXT_ZICOND, .regs = zicond_regs, .regs_n = ARRAY_SIZE(zicond_regs),} -#define ZICSR_REGS_SUBLIST \ - {"zicsr", .feature = KVM_RISCV_ISA_EXT_ZICSR, .regs = zicsr_regs, .regs_n = ARRAY_SIZE(zicsr_regs),} -#define ZIFENCEI_REGS_SUBLIST \ - {"zifencei", .feature = KVM_RISCV_ISA_EXT_ZIFENCEI, .regs = zifencei_regs, .regs_n = ARRAY_SIZE(zifencei_regs),} -#define ZIHPM_REGS_SUBLIST \ - {"zihpm", .feature = KVM_RISCV_ISA_EXT_ZIHPM, .regs = zihpm_regs, .regs_n = ARRAY_SIZE(zihpm_regs),} -#define AIA_REGS_SUBLIST \ +#define SUBLIST_AIA \ {"aia", .feature = KVM_RISCV_ISA_EXT_SSAIA, .regs = aia_regs, .regs_n = ARRAY_SIZE(aia_regs),} -#define SMSTATEEN_REGS_SUBLIST \ +#define SUBLIST_SMSTATEEN \ {"smstateen", .feature = KVM_RISCV_ISA_EXT_SMSTATEEN, .regs = smstateen_regs, .regs_n = ARRAY_SIZE(smstateen_regs),} -#define FP_F_REGS_SUBLIST \ +#define SUBLIST_FP_F \ {"fp_f", .feature = KVM_RISCV_ISA_EXT_F, .regs = fp_f_regs, \ .regs_n = ARRAY_SIZE(fp_f_regs),} -#define FP_D_REGS_SUBLIST \ +#define SUBLIST_FP_D \ {"fp_d", .feature = KVM_RISCV_ISA_EXT_D, .regs = fp_d_regs, \ .regs_n = ARRAY_SIZE(fp_d_regs),} -static struct vcpu_reg_list h_config = { - .sublists = { - BASE_SUBLIST, - H_REGS_SUBLIST, - {0}, - }, -}; - -static struct vcpu_reg_list zicbom_config = { - .sublists = { - BASE_SUBLIST, - ZICBOM_REGS_SUBLIST, - {0}, - }, -}; - -static struct vcpu_reg_list zicboz_config = { - .sublists = { - BASE_SUBLIST, - ZICBOZ_REGS_SUBLIST, - {0}, - }, -}; - -static struct vcpu_reg_list svpbmt_config = { - .sublists = { - BASE_SUBLIST, - SVPBMT_REGS_SUBLIST, - {0}, - }, -}; - -static struct vcpu_reg_list sstc_config = { - .sublists = { - BASE_SUBLIST, - SSTC_REGS_SUBLIST, - {0}, - }, -}; - -static struct vcpu_reg_list svinval_config = { - .sublists = { - BASE_SUBLIST, - SVINVAL_REGS_SUBLIST, - {0}, - }, -}; - -static struct vcpu_reg_list zihintpause_config = { - .sublists = { - BASE_SUBLIST, - ZIHINTPAUSE_REGS_SUBLIST, - {0}, - }, -}; - -static struct vcpu_reg_list zba_config = { - .sublists = { - BASE_SUBLIST, - ZBA_REGS_SUBLIST, - {0}, - }, -}; - -static struct vcpu_reg_list zbb_config = { - .sublists = { - BASE_SUBLIST, - ZBB_REGS_SUBLIST, - {0}, - }, -}; - -static struct vcpu_reg_list zbs_config = { - .sublists = { - BASE_SUBLIST, - ZBS_REGS_SUBLIST, - {0}, - }, -}; - -static struct vcpu_reg_list zicntr_config = { - .sublists = { - BASE_SUBLIST, - ZICNTR_REGS_SUBLIST, - {0}, - }, -}; - -static struct vcpu_reg_list zicond_config = { - .sublists = { - BASE_SUBLIST, - ZICOND_REGS_SUBLIST, - {0}, - }, -}; - -static struct vcpu_reg_list zicsr_config = { - .sublists = { - BASE_SUBLIST, - ZICSR_REGS_SUBLIST, - {0}, - }, -}; - -static struct vcpu_reg_list zifencei_config = { - .sublists = { - BASE_SUBLIST, - ZIFENCEI_REGS_SUBLIST, - {0}, - }, -}; - -static struct vcpu_reg_list zihpm_config = { - .sublists = { - BASE_SUBLIST, - ZIHPM_REGS_SUBLIST, - {0}, - }, -}; - -static struct vcpu_reg_list aia_config = { - .sublists = { - BASE_SUBLIST, - AIA_REGS_SUBLIST, - {0}, - }, -}; - -static struct vcpu_reg_list smstateen_config = { - .sublists = { - BASE_SUBLIST, - SMSTATEEN_REGS_SUBLIST, - {0}, - }, -}; - -static struct vcpu_reg_list fp_f_config = { - .sublists = { - BASE_SUBLIST, - FP_F_REGS_SUBLIST, - {0}, - }, -}; - -static struct vcpu_reg_list fp_d_config = { - .sublists = { - BASE_SUBLIST, - FP_D_REGS_SUBLIST, - {0}, - }, -}; +#define KVM_ISA_EXT_SIMPLE_CONFIG(ext, extu) \ +static __u64 regs_##ext[] = { \ + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | \ + KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | \ + KVM_RISCV_ISA_EXT_##extu, \ +}; \ +static struct vcpu_reg_list config_##ext = { \ + .sublists = { \ + SUBLIST_BASE, \ + { \ + .name = #ext, \ + .feature = KVM_RISCV_ISA_EXT_##extu, \ + .regs = regs_##ext, \ + .regs_n = ARRAY_SIZE(regs_##ext), \ + }, \ + {0}, \ + }, \ +} \ + +#define KVM_SBI_EXT_SIMPLE_CONFIG(ext, extu) \ +static __u64 regs_sbi_##ext[] = { \ + KVM_REG_RISCV | KVM_REG_SIZE_ULONG | \ + KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | \ + KVM_RISCV_SBI_EXT_##extu, \ +}; \ +static struct vcpu_reg_list config_sbi_##ext = { \ + .sublists = { \ + SUBLIST_BASE, \ + { \ + .name = "sbi-"#ext, \ + .feature_type = VCPU_FEATURE_SBI_EXT, \ + .feature = KVM_RISCV_SBI_EXT_##extu, \ + .regs = regs_sbi_##ext, \ + .regs_n = ARRAY_SIZE(regs_sbi_##ext), \ + }, \ + {0}, \ + }, \ +} \ + +#define KVM_ISA_EXT_SUBLIST_CONFIG(ext, extu) \ +static struct vcpu_reg_list config_##ext = { \ + .sublists = { \ + SUBLIST_BASE, \ + SUBLIST_##extu, \ + {0}, \ + }, \ +} \ + +#define KVM_SBI_EXT_SUBLIST_CONFIG(ext, extu) \ +static struct vcpu_reg_list config_sbi_##ext = { \ + .sublists = { \ + SUBLIST_BASE, \ + SUBLIST_SBI_##extu, \ + {0}, \ + }, \ +} \ + +/* Note: The below list is alphabetically sorted. */ + +KVM_SBI_EXT_SUBLIST_CONFIG(base, BASE); +KVM_SBI_EXT_SUBLIST_CONFIG(sta, STA); +KVM_SBI_EXT_SIMPLE_CONFIG(pmu, PMU); +KVM_SBI_EXT_SIMPLE_CONFIG(dbcn, DBCN); + +KVM_ISA_EXT_SUBLIST_CONFIG(aia, AIA); +KVM_ISA_EXT_SUBLIST_CONFIG(fp_f, FP_F); +KVM_ISA_EXT_SUBLIST_CONFIG(fp_d, FP_D); +KVM_ISA_EXT_SIMPLE_CONFIG(h, H); +KVM_ISA_EXT_SUBLIST_CONFIG(smstateen, SMSTATEEN); +KVM_ISA_EXT_SIMPLE_CONFIG(sstc, SSTC); +KVM_ISA_EXT_SIMPLE_CONFIG(svinval, SVINVAL); +KVM_ISA_EXT_SIMPLE_CONFIG(svnapot, SVNAPOT); +KVM_ISA_EXT_SIMPLE_CONFIG(svpbmt, SVPBMT); +KVM_ISA_EXT_SIMPLE_CONFIG(zba, ZBA); +KVM_ISA_EXT_SIMPLE_CONFIG(zbb, ZBB); +KVM_ISA_EXT_SIMPLE_CONFIG(zbs, ZBS); +KVM_ISA_EXT_SUBLIST_CONFIG(zicbom, ZICBOM); +KVM_ISA_EXT_SUBLIST_CONFIG(zicboz, ZICBOZ); +KVM_ISA_EXT_SIMPLE_CONFIG(zicntr, ZICNTR); +KVM_ISA_EXT_SIMPLE_CONFIG(zicond, ZICOND); +KVM_ISA_EXT_SIMPLE_CONFIG(zicsr, ZICSR); +KVM_ISA_EXT_SIMPLE_CONFIG(zifencei, ZIFENCEI); +KVM_ISA_EXT_SIMPLE_CONFIG(zihintpause, ZIHINTPAUSE); +KVM_ISA_EXT_SIMPLE_CONFIG(zihpm, ZIHPM); struct vcpu_reg_list *vcpu_configs[] = { - &h_config, - &zicbom_config, - &zicboz_config, - &svpbmt_config, - &sstc_config, - &svinval_config, - &zihintpause_config, - &zba_config, - &zbb_config, - &zbs_config, - &zicntr_config, - &zicond_config, - &zicsr_config, - &zifencei_config, - &zihpm_config, - &aia_config, - &smstateen_config, - &fp_f_config, - &fp_d_config, + &config_sbi_base, + &config_sbi_sta, + &config_sbi_pmu, + &config_sbi_dbcn, + &config_aia, + &config_fp_f, + &config_fp_d, + &config_h, + &config_smstateen, + &config_sstc, + &config_svinval, + &config_svnapot, + &config_svpbmt, + &config_zba, + &config_zbb, + &config_zbs, + &config_zicbom, + &config_zicboz, + &config_zicntr, + &config_zicond, + &config_zicsr, + &config_zifencei, + &config_zihintpause, + &config_zihpm, }; int vcpu_configs_n = ARRAY_SIZE(vcpu_configs); diff --git a/tools/testing/selftests/kvm/s390x/cmma_test.c b/tools/testing/selftests/kvm/s390x/cmma_test.c index c8e0a6495a63..626a2b8a2037 100644 --- a/tools/testing/selftests/kvm/s390x/cmma_test.c +++ b/tools/testing/selftests/kvm/s390x/cmma_test.c @@ -94,11 +94,6 @@ static void guest_dirty_test_data(void) ); } -static struct kvm_vm *create_vm(void) -{ - return ____vm_create(VM_MODE_DEFAULT); -} - static void create_main_memslot(struct kvm_vm *vm) { int i; @@ -157,7 +152,7 @@ static struct kvm_vm *create_vm_two_memslots(void) { struct kvm_vm *vm; - vm = create_vm(); + vm = vm_create_barebones(); create_memslots(vm); @@ -276,7 +271,7 @@ static void assert_exit_was_hypercall(struct kvm_vcpu *vcpu) static void test_migration_mode(void) { - struct kvm_vm *vm = create_vm(); + struct kvm_vm *vm = vm_create_barebones(); struct kvm_vcpu *vcpu; u64 orig_psw; int rc; @@ -670,7 +665,7 @@ struct testdef { */ static int machine_has_cmma(void) { - struct kvm_vm *vm = create_vm(); + struct kvm_vm *vm = vm_create_barebones(); int r; r = !__kvm_has_device_attr(vm->fd, KVM_S390_VM_MEM_CTRL, KVM_S390_VM_MEM_ENABLE_CMMA); diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c index b32960189f5f..075b80dbe237 100644 --- a/tools/testing/selftests/kvm/set_memory_region_test.c +++ b/tools/testing/selftests/kvm/set_memory_region_test.c @@ -157,17 +157,17 @@ static void guest_code_move_memory_region(void) */ val = guest_spin_on_val(0); __GUEST_ASSERT(val == 1 || val == MMIO_VAL, - "Expected '1' or MMIO ('%llx'), got '%llx'", MMIO_VAL, val); + "Expected '1' or MMIO ('%lx'), got '%lx'", MMIO_VAL, val); /* Spin until the misaligning memory region move completes. */ val = guest_spin_on_val(MMIO_VAL); __GUEST_ASSERT(val == 1 || val == 0, - "Expected '0' or '1' (no MMIO), got '%llx'", val); + "Expected '0' or '1' (no MMIO), got '%lx'", val); /* Spin until the memory region starts to get re-aligned. */ val = guest_spin_on_val(0); __GUEST_ASSERT(val == 1 || val == MMIO_VAL, - "Expected '1' or MMIO ('%llx'), got '%llx'", MMIO_VAL, val); + "Expected '1' or MMIO ('%lx'), got '%lx'", MMIO_VAL, val); /* Spin until the re-aligning memory region move completes. */ val = guest_spin_on_val(MMIO_VAL); @@ -326,6 +326,55 @@ static void test_zero_memory_regions(void) } #endif /* __x86_64__ */ +static void test_invalid_memory_region_flags(void) +{ + uint32_t supported_flags = KVM_MEM_LOG_DIRTY_PAGES; + const uint32_t v2_only_flags = KVM_MEM_GUEST_MEMFD; + struct kvm_vm *vm; + int r, i; + +#if defined __aarch64__ || defined __x86_64__ + supported_flags |= KVM_MEM_READONLY; +#endif + +#ifdef __x86_64__ + if (kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM)) + vm = vm_create_barebones_protected_vm(); + else +#endif + vm = vm_create_barebones(); + + if (kvm_check_cap(KVM_CAP_MEMORY_ATTRIBUTES) & KVM_MEMORY_ATTRIBUTE_PRIVATE) + supported_flags |= KVM_MEM_GUEST_MEMFD; + + for (i = 0; i < 32; i++) { + if ((supported_flags & BIT(i)) && !(v2_only_flags & BIT(i))) + continue; + + r = __vm_set_user_memory_region(vm, 0, BIT(i), + 0, MEM_REGION_SIZE, NULL); + + TEST_ASSERT(r && errno == EINVAL, + "KVM_SET_USER_MEMORY_REGION should have failed on v2 only flag 0x%lx", BIT(i)); + + if (supported_flags & BIT(i)) + continue; + + r = __vm_set_user_memory_region2(vm, 0, BIT(i), + 0, MEM_REGION_SIZE, NULL, 0, 0); + TEST_ASSERT(r && errno == EINVAL, + "KVM_SET_USER_MEMORY_REGION2 should have failed on unsupported flag 0x%lx", BIT(i)); + } + + if (supported_flags & KVM_MEM_GUEST_MEMFD) { + r = __vm_set_user_memory_region2(vm, 0, + KVM_MEM_LOG_DIRTY_PAGES | KVM_MEM_GUEST_MEMFD, + 0, MEM_REGION_SIZE, NULL, 0, 0); + TEST_ASSERT(r && errno == EINVAL, + "KVM_SET_USER_MEMORY_REGION2 should have failed, dirty logging private memory is unsupported"); + } +} + /* * Test it can be added memory slots up to KVM_CAP_NR_MEMSLOTS, then any * tentative to add further slots should fail. @@ -385,13 +434,105 @@ static void test_add_max_memory_regions(void) kvm_vm_free(vm); } + +#ifdef __x86_64__ +static void test_invalid_guest_memfd(struct kvm_vm *vm, int memfd, + size_t offset, const char *msg) +{ + int r = __vm_set_user_memory_region2(vm, MEM_REGION_SLOT, KVM_MEM_GUEST_MEMFD, + MEM_REGION_GPA, MEM_REGION_SIZE, + 0, memfd, offset); + TEST_ASSERT(r == -1 && errno == EINVAL, "%s", msg); +} + +static void test_add_private_memory_region(void) +{ + struct kvm_vm *vm, *vm2; + int memfd, i; + + pr_info("Testing ADD of KVM_MEM_GUEST_MEMFD memory regions\n"); + + vm = vm_create_barebones_protected_vm(); + + test_invalid_guest_memfd(vm, vm->kvm_fd, 0, "KVM fd should fail"); + test_invalid_guest_memfd(vm, vm->fd, 0, "VM's fd should fail"); + + memfd = kvm_memfd_alloc(MEM_REGION_SIZE, false); + test_invalid_guest_memfd(vm, memfd, 0, "Regular memfd() should fail"); + close(memfd); + + vm2 = vm_create_barebones_protected_vm(); + memfd = vm_create_guest_memfd(vm2, MEM_REGION_SIZE, 0); + test_invalid_guest_memfd(vm, memfd, 0, "Other VM's guest_memfd() should fail"); + + vm_set_user_memory_region2(vm2, MEM_REGION_SLOT, KVM_MEM_GUEST_MEMFD, + MEM_REGION_GPA, MEM_REGION_SIZE, 0, memfd, 0); + close(memfd); + kvm_vm_free(vm2); + + memfd = vm_create_guest_memfd(vm, MEM_REGION_SIZE, 0); + for (i = 1; i < PAGE_SIZE; i++) + test_invalid_guest_memfd(vm, memfd, i, "Unaligned offset should fail"); + + vm_set_user_memory_region2(vm, MEM_REGION_SLOT, KVM_MEM_GUEST_MEMFD, + MEM_REGION_GPA, MEM_REGION_SIZE, 0, memfd, 0); + close(memfd); + + kvm_vm_free(vm); +} + +static void test_add_overlapping_private_memory_regions(void) +{ + struct kvm_vm *vm; + int memfd; + int r; + + pr_info("Testing ADD of overlapping KVM_MEM_GUEST_MEMFD memory regions\n"); + + vm = vm_create_barebones_protected_vm(); + + memfd = vm_create_guest_memfd(vm, MEM_REGION_SIZE * 4, 0); + + vm_set_user_memory_region2(vm, MEM_REGION_SLOT, KVM_MEM_GUEST_MEMFD, + MEM_REGION_GPA, MEM_REGION_SIZE * 2, 0, memfd, 0); + + vm_set_user_memory_region2(vm, MEM_REGION_SLOT + 1, KVM_MEM_GUEST_MEMFD, + MEM_REGION_GPA * 2, MEM_REGION_SIZE * 2, + 0, memfd, MEM_REGION_SIZE * 2); + + /* + * Delete the first memslot, and then attempt to recreate it except + * with a "bad" offset that results in overlap in the guest_memfd(). + */ + vm_set_user_memory_region2(vm, MEM_REGION_SLOT, KVM_MEM_GUEST_MEMFD, + MEM_REGION_GPA, 0, NULL, -1, 0); + + /* Overlap the front half of the other slot. */ + r = __vm_set_user_memory_region2(vm, MEM_REGION_SLOT, KVM_MEM_GUEST_MEMFD, + MEM_REGION_GPA * 2 - MEM_REGION_SIZE, + MEM_REGION_SIZE * 2, + 0, memfd, 0); + TEST_ASSERT(r == -1 && errno == EEXIST, "%s", + "Overlapping guest_memfd() bindings should fail with EEXIST"); + + /* And now the back half of the other slot. */ + r = __vm_set_user_memory_region2(vm, MEM_REGION_SLOT, KVM_MEM_GUEST_MEMFD, + MEM_REGION_GPA * 2 + MEM_REGION_SIZE, + MEM_REGION_SIZE * 2, + 0, memfd, 0); + TEST_ASSERT(r == -1 && errno == EEXIST, "%s", + "Overlapping guest_memfd() bindings should fail with EEXIST"); + + close(memfd); + kvm_vm_free(vm); +} +#endif + int main(int argc, char *argv[]) { #ifdef __x86_64__ int i, loops; -#endif -#ifdef __x86_64__ /* * FIXME: the zero-memslot test fails on aarch64 and s390x because * KVM_RUN fails with ENOEXEC or EFAULT. @@ -399,9 +540,19 @@ int main(int argc, char *argv[]) test_zero_memory_regions(); #endif + test_invalid_memory_region_flags(); + test_add_max_memory_regions(); #ifdef __x86_64__ + if (kvm_has_cap(KVM_CAP_GUEST_MEMFD) && + (kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM))) { + test_add_private_memory_region(); + test_add_overlapping_private_memory_regions(); + } else { + pr_info("Skipping tests for KVM_MEM_GUEST_MEMFD memory regions\n"); + } + if (argc > 1) loops = atoi_positive("Number of iterations", argv[1]); else diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c index 171adfb2a6cb..bae0c5026f82 100644 --- a/tools/testing/selftests/kvm/steal_time.c +++ b/tools/testing/selftests/kvm/steal_time.c @@ -11,7 +11,9 @@ #include <pthread.h> #include <linux/kernel.h> #include <asm/kvm.h> +#ifndef __riscv #include <asm/kvm_para.h> +#endif #include "test_util.h" #include "kvm_util.h" @@ -203,6 +205,103 @@ static void steal_time_dump(struct kvm_vm *vm, uint32_t vcpu_idx) pr_info(" st_time: %ld\n", st->st_time); } +#elif defined(__riscv) + +/* SBI STA shmem must have 64-byte alignment */ +#define STEAL_TIME_SIZE ((sizeof(struct sta_struct) + 63) & ~63) + +static vm_paddr_t st_gpa[NR_VCPUS]; + +struct sta_struct { + uint32_t sequence; + uint32_t flags; + uint64_t steal; + uint8_t preempted; + uint8_t pad[47]; +} __packed; + +static void sta_set_shmem(vm_paddr_t gpa, unsigned long flags) +{ + unsigned long lo = (unsigned long)gpa; +#if __riscv_xlen == 32 + unsigned long hi = (unsigned long)(gpa >> 32); +#else + unsigned long hi = gpa == -1 ? -1 : 0; +#endif + struct sbiret ret = sbi_ecall(SBI_EXT_STA, 0, lo, hi, flags, 0, 0, 0); + + GUEST_ASSERT(ret.value == 0 && ret.error == 0); +} + +static void check_status(struct sta_struct *st) +{ + GUEST_ASSERT(!(READ_ONCE(st->sequence) & 1)); + GUEST_ASSERT(READ_ONCE(st->flags) == 0); + GUEST_ASSERT(READ_ONCE(st->preempted) == 0); +} + +static void guest_code(int cpu) +{ + struct sta_struct *st = st_gva[cpu]; + uint32_t sequence; + long out_val = 0; + bool probe; + + probe = guest_sbi_probe_extension(SBI_EXT_STA, &out_val); + GUEST_ASSERT(probe && out_val == 1); + + sta_set_shmem(st_gpa[cpu], 0); + GUEST_SYNC(0); + + check_status(st); + WRITE_ONCE(guest_stolen_time[cpu], st->steal); + sequence = READ_ONCE(st->sequence); + check_status(st); + GUEST_SYNC(1); + + check_status(st); + GUEST_ASSERT(sequence < READ_ONCE(st->sequence)); + WRITE_ONCE(guest_stolen_time[cpu], st->steal); + check_status(st); + GUEST_DONE(); +} + +static bool is_steal_time_supported(struct kvm_vcpu *vcpu) +{ + uint64_t id = RISCV_SBI_EXT_REG(KVM_RISCV_SBI_EXT_STA); + unsigned long enabled; + + vcpu_get_reg(vcpu, id, &enabled); + TEST_ASSERT(enabled == 0 || enabled == 1, "Expected boolean result"); + + return enabled; +} + +static void steal_time_init(struct kvm_vcpu *vcpu, uint32_t i) +{ + /* ST_GPA_BASE is identity mapped */ + st_gva[i] = (void *)(ST_GPA_BASE + i * STEAL_TIME_SIZE); + st_gpa[i] = addr_gva2gpa(vcpu->vm, (vm_vaddr_t)st_gva[i]); + sync_global_to_guest(vcpu->vm, st_gva[i]); + sync_global_to_guest(vcpu->vm, st_gpa[i]); +} + +static void steal_time_dump(struct kvm_vm *vm, uint32_t vcpu_idx) +{ + struct sta_struct *st = addr_gva2hva(vm, (ulong)st_gva[vcpu_idx]); + int i; + + pr_info("VCPU%d:\n", vcpu_idx); + pr_info(" sequence: %d\n", st->sequence); + pr_info(" flags: %d\n", st->flags); + pr_info(" steal: %"PRIu64"\n", st->steal); + pr_info(" preempted: %d\n", st->preempted); + pr_info(" pad: "); + for (i = 0; i < 47; ++i) + pr_info("%d", st->pad[i]); + pr_info("\n"); +} + #endif static void *do_steal_time(void *arg) diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c index f25749eaa6a8..f5e1e98f04f9 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c @@ -211,6 +211,8 @@ int main(void) vm_vaddr_t tsc_page_gva; int stage; + TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_TIME)); + vm = vm_create_with_one_vcpu(&vcpu, guest_main); vcpu_set_hv_cpuid(vcpu); diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c b/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c index 7bde0c4dfdbd..4c7257ecd2a6 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c @@ -240,11 +240,12 @@ int main(int argc, char *argv[]) struct ucall uc; int stage; - vm = vm_create_with_one_vcpu(&vcpu, guest_code); - TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX)); TEST_REQUIRE(kvm_has_cap(KVM_CAP_NESTED_STATE)); TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)); + TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_DIRECT_TLBFLUSH)); + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); hcall_page = vm_vaddr_alloc_pages(vm, 1); memset(addr_gva2hva(vm, hcall_page), 0x0, getpagesize()); diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c b/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c index e036db1f32b9..949e08e98f31 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c @@ -43,6 +43,8 @@ int main(void) uint64_t *outval; struct ucall uc; + TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_CPUID)); + /* Verify if extended hypercalls are supported */ if (!kvm_cpuid_has(kvm_get_supported_hv_cpuid(), HV_ENABLE_EXTENDED_HYPERCALLS)) { diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86_64/hyperv_features.c index 9f28aa276c4e..4f4193fc74ff 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_features.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_features.c @@ -55,18 +55,18 @@ static void guest_msr(struct msr_data *msr) if (msr->fault_expected) __GUEST_ASSERT(vector == GP_VECTOR, "Expected #GP on %sMSR(0x%x), got vector '0x%x'", - msr->idx, msr->write ? "WR" : "RD", vector); + msr->write ? "WR" : "RD", msr->idx, vector); else __GUEST_ASSERT(!vector, "Expected success on %sMSR(0x%x), got vector '0x%x'", - msr->idx, msr->write ? "WR" : "RD", vector); + msr->write ? "WR" : "RD", msr->idx, vector); if (vector || is_write_only_msr(msr->idx)) goto done; if (msr->write) __GUEST_ASSERT(!vector, - "WRMSR(0x%x) to '0x%llx', RDMSR read '0x%llx'", + "WRMSR(0x%x) to '0x%lx', RDMSR read '0x%lx'", msr->idx, msr->write_val, msr_val); /* Invariant TSC bit appears when TSC invariant control MSR is written to */ @@ -102,11 +102,11 @@ static void guest_hcall(vm_vaddr_t pgs_gpa, struct hcall_data *hcall) vector = __hyperv_hypercall(hcall->control, input, output, &res); if (hcall->ud_expected) { __GUEST_ASSERT(vector == UD_VECTOR, - "Expected #UD for control '%u', got vector '0x%x'", + "Expected #UD for control '%lu', got vector '0x%x'", hcall->control, vector); } else { __GUEST_ASSERT(!vector, - "Expected no exception for control '%u', got vector '0x%x'", + "Expected no exception for control '%lu', got vector '0x%x'", hcall->control, vector); GUEST_ASSERT_EQ(res, hcall->expect); } @@ -690,6 +690,8 @@ static void guest_test_hcalls_access(void) int main(void) { + TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_ENFORCE_CPUID)); + pr_info("Testing access to Hyper-V specific MSRs\n"); guest_test_msrs_access(); diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c b/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c index 6feb5ddb031d..65e5f4c05068 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c @@ -248,6 +248,8 @@ int main(int argc, char *argv[]) int stage = 1, r; struct ucall uc; + TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_SEND_IPI)); + vm = vm_create_with_one_vcpu(&vcpu[0], sender_guest_code); /* Hypercall input/output */ diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c index 6c1278562090..c9b18707edc0 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c @@ -158,6 +158,7 @@ int main(int argc, char *argv[]) int stage; TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM)); + TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_DIRECT_TLBFLUSH)); /* Create VM */ vm = vm_create_with_one_vcpu(&vcpu, guest_code); diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c b/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c index 4758b6ef5618..c4443f71f8dd 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c @@ -590,6 +590,8 @@ int main(int argc, char *argv[]) struct ucall uc; int stage = 1, r, i; + TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_TLBFLUSH)); + vm = vm_create_with_one_vcpu(&vcpu[0], sender_guest_code); /* Test data page */ diff --git a/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c b/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c deleted file mode 100644 index ce1ccc4c1503..000000000000 --- a/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c +++ /dev/null @@ -1,121 +0,0 @@ -/* - * mmio_warning_test - * - * Copyright (C) 2019, Google LLC. - * - * This work is licensed under the terms of the GNU GPL, version 2. - * - * Test that we don't get a kernel warning when we call KVM_RUN after a - * triple fault occurs. To get the triple fault to occur we call KVM_RUN - * on a VCPU that hasn't been properly setup. - * - */ - -#define _GNU_SOURCE -#include <fcntl.h> -#include <kvm_util.h> -#include <linux/kvm.h> -#include <processor.h> -#include <pthread.h> -#include <stdio.h> -#include <stdlib.h> -#include <string.h> -#include <sys/ioctl.h> -#include <sys/mman.h> -#include <sys/stat.h> -#include <sys/types.h> -#include <sys/wait.h> -#include <test_util.h> -#include <unistd.h> - -#define NTHREAD 4 -#define NPROCESS 5 - -struct thread_context { - int kvmcpu; - struct kvm_run *run; -}; - -void *thr(void *arg) -{ - struct thread_context *tc = (struct thread_context *)arg; - int res; - int kvmcpu = tc->kvmcpu; - struct kvm_run *run = tc->run; - - res = ioctl(kvmcpu, KVM_RUN, 0); - pr_info("ret1=%d exit_reason=%d suberror=%d\n", - res, run->exit_reason, run->internal.suberror); - - return 0; -} - -void test(void) -{ - int i, kvm, kvmvm, kvmcpu; - pthread_t th[NTHREAD]; - struct kvm_run *run; - struct thread_context tc; - - kvm = open("/dev/kvm", O_RDWR); - TEST_ASSERT(kvm != -1, "failed to open /dev/kvm"); - kvmvm = __kvm_ioctl(kvm, KVM_CREATE_VM, NULL); - TEST_ASSERT(kvmvm > 0, KVM_IOCTL_ERROR(KVM_CREATE_VM, kvmvm)); - kvmcpu = ioctl(kvmvm, KVM_CREATE_VCPU, 0); - TEST_ASSERT(kvmcpu != -1, KVM_IOCTL_ERROR(KVM_CREATE_VCPU, kvmcpu)); - run = (struct kvm_run *)mmap(0, 4096, PROT_READ|PROT_WRITE, MAP_SHARED, - kvmcpu, 0); - tc.kvmcpu = kvmcpu; - tc.run = run; - srand(getpid()); - for (i = 0; i < NTHREAD; i++) { - pthread_create(&th[i], NULL, thr, (void *)(uintptr_t)&tc); - usleep(rand() % 10000); - } - for (i = 0; i < NTHREAD; i++) - pthread_join(th[i], NULL); -} - -int get_warnings_count(void) -{ - int warnings; - FILE *f; - - f = popen("dmesg | grep \"WARNING:\" | wc -l", "r"); - if (fscanf(f, "%d", &warnings) < 1) - warnings = 0; - pclose(f); - - return warnings; -} - -int main(void) -{ - int warnings_before, warnings_after; - - TEST_REQUIRE(host_cpu_is_intel); - - TEST_REQUIRE(!vm_is_unrestricted_guest(NULL)); - - warnings_before = get_warnings_count(); - - for (int i = 0; i < NPROCESS; ++i) { - int status; - int pid = fork(); - - if (pid < 0) - exit(1); - if (pid == 0) { - test(); - exit(0); - } - while (waitpid(pid, &status, __WALL) != pid) - ; - } - - warnings_after = get_warnings_count(); - TEST_ASSERT(warnings_before == warnings_after, - "Warnings found in kernel. Run 'dmesg' to inspect them."); - - return 0; -} diff --git a/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c b/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c index 80aa3d8b18f8..853802641e1e 100644 --- a/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c +++ b/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c @@ -27,10 +27,12 @@ do { \ \ if (fault_wanted) \ __GUEST_ASSERT((vector) == UD_VECTOR, \ - "Expected #UD on " insn " for testcase '0x%x', got '0x%x'", vector); \ + "Expected #UD on " insn " for testcase '0x%x', got '0x%x'", \ + testcase, vector); \ else \ __GUEST_ASSERT(!(vector), \ - "Expected success on " insn " for testcase '0x%x', got '0x%x'", vector); \ + "Expected success on " insn " for testcase '0x%x', got '0x%x'", \ + testcase, vector); \ } while (0) static void guest_monitor_wait(int testcase) diff --git a/tools/testing/selftests/kvm/x86_64/private_mem_conversions_test.c b/tools/testing/selftests/kvm/x86_64/private_mem_conversions_test.c new file mode 100644 index 000000000000..65ad38b6be1f --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/private_mem_conversions_test.c @@ -0,0 +1,482 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022, Google LLC. + */ +#define _GNU_SOURCE /* for program_invocation_short_name */ +#include <fcntl.h> +#include <limits.h> +#include <pthread.h> +#include <sched.h> +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> + +#include <linux/compiler.h> +#include <linux/kernel.h> +#include <linux/kvm_para.h> +#include <linux/memfd.h> +#include <linux/sizes.h> + +#include <test_util.h> +#include <kvm_util.h> +#include <processor.h> + +#define BASE_DATA_SLOT 10 +#define BASE_DATA_GPA ((uint64_t)(1ull << 32)) +#define PER_CPU_DATA_SIZE ((uint64_t)(SZ_2M + PAGE_SIZE)) + +/* Horrific macro so that the line info is captured accurately :-( */ +#define memcmp_g(gpa, pattern, size) \ +do { \ + uint8_t *mem = (uint8_t *)gpa; \ + size_t i; \ + \ + for (i = 0; i < size; i++) \ + __GUEST_ASSERT(mem[i] == pattern, \ + "Guest expected 0x%x at offset %lu (gpa 0x%lx), got 0x%x", \ + pattern, i, gpa + i, mem[i]); \ +} while (0) + +static void memcmp_h(uint8_t *mem, uint64_t gpa, uint8_t pattern, size_t size) +{ + size_t i; + + for (i = 0; i < size; i++) + TEST_ASSERT(mem[i] == pattern, + "Host expected 0x%x at gpa 0x%lx, got 0x%x", + pattern, gpa + i, mem[i]); +} + +/* + * Run memory conversion tests with explicit conversion: + * Execute KVM hypercall to map/unmap gpa range which will cause userspace exit + * to back/unback private memory. Subsequent accesses by guest to the gpa range + * will not cause exit to userspace. + * + * Test memory conversion scenarios with following steps: + * 1) Access private memory using private access and verify that memory contents + * are not visible to userspace. + * 2) Convert memory to shared using explicit conversions and ensure that + * userspace is able to access the shared regions. + * 3) Convert memory back to private using explicit conversions and ensure that + * userspace is again not able to access converted private regions. + */ + +#define GUEST_STAGE(o, s) { .offset = o, .size = s } + +enum ucall_syncs { + SYNC_SHARED, + SYNC_PRIVATE, +}; + +static void guest_sync_shared(uint64_t gpa, uint64_t size, + uint8_t current_pattern, uint8_t new_pattern) +{ + GUEST_SYNC5(SYNC_SHARED, gpa, size, current_pattern, new_pattern); +} + +static void guest_sync_private(uint64_t gpa, uint64_t size, uint8_t pattern) +{ + GUEST_SYNC4(SYNC_PRIVATE, gpa, size, pattern); +} + +/* Arbitrary values, KVM doesn't care about the attribute flags. */ +#define MAP_GPA_SET_ATTRIBUTES BIT(0) +#define MAP_GPA_SHARED BIT(1) +#define MAP_GPA_DO_FALLOCATE BIT(2) + +static void guest_map_mem(uint64_t gpa, uint64_t size, bool map_shared, + bool do_fallocate) +{ + uint64_t flags = MAP_GPA_SET_ATTRIBUTES; + + if (map_shared) + flags |= MAP_GPA_SHARED; + if (do_fallocate) + flags |= MAP_GPA_DO_FALLOCATE; + kvm_hypercall_map_gpa_range(gpa, size, flags); +} + +static void guest_map_shared(uint64_t gpa, uint64_t size, bool do_fallocate) +{ + guest_map_mem(gpa, size, true, do_fallocate); +} + +static void guest_map_private(uint64_t gpa, uint64_t size, bool do_fallocate) +{ + guest_map_mem(gpa, size, false, do_fallocate); +} + +struct { + uint64_t offset; + uint64_t size; +} static const test_ranges[] = { + GUEST_STAGE(0, PAGE_SIZE), + GUEST_STAGE(0, SZ_2M), + GUEST_STAGE(PAGE_SIZE, PAGE_SIZE), + GUEST_STAGE(PAGE_SIZE, SZ_2M), + GUEST_STAGE(SZ_2M, PAGE_SIZE), +}; + +static void guest_test_explicit_conversion(uint64_t base_gpa, bool do_fallocate) +{ + const uint8_t def_p = 0xaa; + const uint8_t init_p = 0xcc; + uint64_t j; + int i; + + /* Memory should be shared by default. */ + memset((void *)base_gpa, def_p, PER_CPU_DATA_SIZE); + memcmp_g(base_gpa, def_p, PER_CPU_DATA_SIZE); + guest_sync_shared(base_gpa, PER_CPU_DATA_SIZE, def_p, init_p); + + memcmp_g(base_gpa, init_p, PER_CPU_DATA_SIZE); + + for (i = 0; i < ARRAY_SIZE(test_ranges); i++) { + uint64_t gpa = base_gpa + test_ranges[i].offset; + uint64_t size = test_ranges[i].size; + uint8_t p1 = 0x11; + uint8_t p2 = 0x22; + uint8_t p3 = 0x33; + uint8_t p4 = 0x44; + + /* + * Set the test region to pattern one to differentiate it from + * the data range as a whole (contains the initial pattern). + */ + memset((void *)gpa, p1, size); + + /* + * Convert to private, set and verify the private data, and + * then verify that the rest of the data (map shared) still + * holds the initial pattern, and that the host always sees the + * shared memory (initial pattern). Unlike shared memory, + * punching a hole in private memory is destructive, i.e. + * previous values aren't guaranteed to be preserved. + */ + guest_map_private(gpa, size, do_fallocate); + + if (size > PAGE_SIZE) { + memset((void *)gpa, p2, PAGE_SIZE); + goto skip; + } + + memset((void *)gpa, p2, size); + guest_sync_private(gpa, size, p1); + + /* + * Verify that the private memory was set to pattern two, and + * that shared memory still holds the initial pattern. + */ + memcmp_g(gpa, p2, size); + if (gpa > base_gpa) + memcmp_g(base_gpa, init_p, gpa - base_gpa); + if (gpa + size < base_gpa + PER_CPU_DATA_SIZE) + memcmp_g(gpa + size, init_p, + (base_gpa + PER_CPU_DATA_SIZE) - (gpa + size)); + + /* + * Convert odd-number page frames back to shared to verify KVM + * also correctly handles holes in private ranges. + */ + for (j = 0; j < size; j += PAGE_SIZE) { + if ((j >> PAGE_SHIFT) & 1) { + guest_map_shared(gpa + j, PAGE_SIZE, do_fallocate); + guest_sync_shared(gpa + j, PAGE_SIZE, p1, p3); + + memcmp_g(gpa + j, p3, PAGE_SIZE); + } else { + guest_sync_private(gpa + j, PAGE_SIZE, p1); + } + } + +skip: + /* + * Convert the entire region back to shared, explicitly write + * pattern three to fill in the even-number frames before + * asking the host to verify (and write pattern four). + */ + guest_map_shared(gpa, size, do_fallocate); + memset((void *)gpa, p3, size); + guest_sync_shared(gpa, size, p3, p4); + memcmp_g(gpa, p4, size); + + /* Reset the shared memory back to the initial pattern. */ + memset((void *)gpa, init_p, size); + + /* + * Free (via PUNCH_HOLE) *all* private memory so that the next + * iteration starts from a clean slate, e.g. with respect to + * whether or not there are pages/folios in guest_mem. + */ + guest_map_shared(base_gpa, PER_CPU_DATA_SIZE, true); + } +} + +static void guest_punch_hole(uint64_t gpa, uint64_t size) +{ + /* "Mapping" memory shared via fallocate() is done via PUNCH_HOLE. */ + uint64_t flags = MAP_GPA_SHARED | MAP_GPA_DO_FALLOCATE; + + kvm_hypercall_map_gpa_range(gpa, size, flags); +} + +/* + * Test that PUNCH_HOLE actually frees memory by punching holes without doing a + * proper conversion. Freeing (PUNCH_HOLE) should zap SPTEs, and reallocating + * (subsequent fault) should zero memory. + */ +static void guest_test_punch_hole(uint64_t base_gpa, bool precise) +{ + const uint8_t init_p = 0xcc; + int i; + + /* + * Convert the entire range to private, this testcase is all about + * punching holes in guest_memfd, i.e. shared mappings aren't needed. + */ + guest_map_private(base_gpa, PER_CPU_DATA_SIZE, false); + + for (i = 0; i < ARRAY_SIZE(test_ranges); i++) { + uint64_t gpa = base_gpa + test_ranges[i].offset; + uint64_t size = test_ranges[i].size; + + /* + * Free all memory before each iteration, even for the !precise + * case where the memory will be faulted back in. Freeing and + * reallocating should obviously work, and freeing all memory + * minimizes the probability of cross-testcase influence. + */ + guest_punch_hole(base_gpa, PER_CPU_DATA_SIZE); + + /* Fault-in and initialize memory, and verify the pattern. */ + if (precise) { + memset((void *)gpa, init_p, size); + memcmp_g(gpa, init_p, size); + } else { + memset((void *)base_gpa, init_p, PER_CPU_DATA_SIZE); + memcmp_g(base_gpa, init_p, PER_CPU_DATA_SIZE); + } + + /* + * Punch a hole at the target range and verify that reads from + * the guest succeed and return zeroes. + */ + guest_punch_hole(gpa, size); + memcmp_g(gpa, 0, size); + } +} + +static void guest_code(uint64_t base_gpa) +{ + /* + * Run the conversion test twice, with and without doing fallocate() on + * the guest_memfd backing when converting between shared and private. + */ + guest_test_explicit_conversion(base_gpa, false); + guest_test_explicit_conversion(base_gpa, true); + + /* + * Run the PUNCH_HOLE test twice too, once with the entire guest_memfd + * faulted in, once with only the target range faulted in. + */ + guest_test_punch_hole(base_gpa, false); + guest_test_punch_hole(base_gpa, true); + GUEST_DONE(); +} + +static void handle_exit_hypercall(struct kvm_vcpu *vcpu) +{ + struct kvm_run *run = vcpu->run; + uint64_t gpa = run->hypercall.args[0]; + uint64_t size = run->hypercall.args[1] * PAGE_SIZE; + bool set_attributes = run->hypercall.args[2] & MAP_GPA_SET_ATTRIBUTES; + bool map_shared = run->hypercall.args[2] & MAP_GPA_SHARED; + bool do_fallocate = run->hypercall.args[2] & MAP_GPA_DO_FALLOCATE; + struct kvm_vm *vm = vcpu->vm; + + TEST_ASSERT(run->hypercall.nr == KVM_HC_MAP_GPA_RANGE, + "Wanted MAP_GPA_RANGE (%u), got '%llu'", + KVM_HC_MAP_GPA_RANGE, run->hypercall.nr); + + if (do_fallocate) + vm_guest_mem_fallocate(vm, gpa, size, map_shared); + + if (set_attributes) + vm_set_memory_attributes(vm, gpa, size, + map_shared ? 0 : KVM_MEMORY_ATTRIBUTE_PRIVATE); + run->hypercall.ret = 0; +} + +static bool run_vcpus; + +static void *__test_mem_conversions(void *__vcpu) +{ + struct kvm_vcpu *vcpu = __vcpu; + struct kvm_run *run = vcpu->run; + struct kvm_vm *vm = vcpu->vm; + struct ucall uc; + + while (!READ_ONCE(run_vcpus)) + ; + + for ( ;; ) { + vcpu_run(vcpu); + + if (run->exit_reason == KVM_EXIT_HYPERCALL) { + handle_exit_hypercall(vcpu); + continue; + } + + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Wanted KVM_EXIT_IO, got exit reason: %u (%s)", + run->exit_reason, exit_reason_str(run->exit_reason)); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + case UCALL_SYNC: { + uint64_t gpa = uc.args[1]; + size_t size = uc.args[2]; + size_t i; + + TEST_ASSERT(uc.args[0] == SYNC_SHARED || + uc.args[0] == SYNC_PRIVATE, + "Unknown sync command '%ld'", uc.args[0]); + + for (i = 0; i < size; i += vm->page_size) { + size_t nr_bytes = min_t(size_t, vm->page_size, size - i); + uint8_t *hva = addr_gpa2hva(vm, gpa + i); + + /* In all cases, the host should observe the shared data. */ + memcmp_h(hva, gpa + i, uc.args[3], nr_bytes); + + /* For shared, write the new pattern to guest memory. */ + if (uc.args[0] == SYNC_SHARED) + memset(hva, uc.args[4], nr_bytes); + } + break; + } + case UCALL_DONE: + return NULL; + default: + TEST_FAIL("Unknown ucall 0x%lx.", uc.cmd); + } + } +} + +static void test_mem_conversions(enum vm_mem_backing_src_type src_type, uint32_t nr_vcpus, + uint32_t nr_memslots) +{ + /* + * Allocate enough memory so that each vCPU's chunk of memory can be + * naturally aligned with respect to the size of the backing store. + */ + const size_t alignment = max_t(size_t, SZ_2M, get_backing_src_pagesz(src_type)); + const size_t per_cpu_size = align_up(PER_CPU_DATA_SIZE, alignment); + const size_t memfd_size = per_cpu_size * nr_vcpus; + const size_t slot_size = memfd_size / nr_memslots; + struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; + pthread_t threads[KVM_MAX_VCPUS]; + struct kvm_vm *vm; + int memfd, i, r; + + const struct vm_shape shape = { + .mode = VM_MODE_DEFAULT, + .type = KVM_X86_SW_PROTECTED_VM, + }; + + TEST_ASSERT(slot_size * nr_memslots == memfd_size, + "The memfd size (0x%lx) needs to be cleanly divisible by the number of memslots (%u)", + memfd_size, nr_memslots); + vm = __vm_create_with_vcpus(shape, nr_vcpus, 0, guest_code, vcpus); + + vm_enable_cap(vm, KVM_CAP_EXIT_HYPERCALL, (1 << KVM_HC_MAP_GPA_RANGE)); + + memfd = vm_create_guest_memfd(vm, memfd_size, 0); + + for (i = 0; i < nr_memslots; i++) + vm_mem_add(vm, src_type, BASE_DATA_GPA + slot_size * i, + BASE_DATA_SLOT + i, slot_size / vm->page_size, + KVM_MEM_GUEST_MEMFD, memfd, slot_size * i); + + for (i = 0; i < nr_vcpus; i++) { + uint64_t gpa = BASE_DATA_GPA + i * per_cpu_size; + + vcpu_args_set(vcpus[i], 1, gpa); + + /* + * Map only what is needed so that an out-of-bounds access + * results #PF => SHUTDOWN instead of data corruption. + */ + virt_map(vm, gpa, gpa, PER_CPU_DATA_SIZE / vm->page_size); + + pthread_create(&threads[i], NULL, __test_mem_conversions, vcpus[i]); + } + + WRITE_ONCE(run_vcpus, true); + + for (i = 0; i < nr_vcpus; i++) + pthread_join(threads[i], NULL); + + kvm_vm_free(vm); + + /* + * Allocate and free memory from the guest_memfd after closing the VM + * fd. The guest_memfd is gifted a reference to its owning VM, i.e. + * should prevent the VM from being fully destroyed until the last + * reference to the guest_memfd is also put. + */ + r = fallocate(memfd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, 0, memfd_size); + TEST_ASSERT(!r, __KVM_SYSCALL_ERROR("fallocate()", r)); + + r = fallocate(memfd, FALLOC_FL_KEEP_SIZE, 0, memfd_size); + TEST_ASSERT(!r, __KVM_SYSCALL_ERROR("fallocate()", r)); +} + +static void usage(const char *cmd) +{ + puts(""); + printf("usage: %s [-h] [-m nr_memslots] [-s mem_type] [-n nr_vcpus]\n", cmd); + puts(""); + backing_src_help("-s"); + puts(""); + puts(" -n: specify the number of vcpus (default: 1)"); + puts(""); + puts(" -m: specify the number of memslots (default: 1)"); + puts(""); +} + +int main(int argc, char *argv[]) +{ + enum vm_mem_backing_src_type src_type = DEFAULT_VM_MEM_SRC; + uint32_t nr_memslots = 1; + uint32_t nr_vcpus = 1; + int opt; + + TEST_REQUIRE(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM)); + + while ((opt = getopt(argc, argv, "hm:s:n:")) != -1) { + switch (opt) { + case 's': + src_type = parse_backing_src_type(optarg); + break; + case 'n': + nr_vcpus = atoi_positive("nr_vcpus", optarg); + break; + case 'm': + nr_memslots = atoi_positive("nr_memslots", optarg); + break; + case 'h': + default: + usage(argv[0]); + exit(0); + } + } + + test_mem_conversions(src_type, nr_vcpus, nr_memslots); + + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/private_mem_kvm_exits_test.c b/tools/testing/selftests/kvm/x86_64/private_mem_kvm_exits_test.c new file mode 100644 index 000000000000..13e72fcec8dd --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/private_mem_kvm_exits_test.c @@ -0,0 +1,120 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2023, Google LLC. + */ +#include <linux/kvm.h> +#include <pthread.h> +#include <stdint.h> + +#include "kvm_util.h" +#include "processor.h" +#include "test_util.h" + +/* Arbitrarily selected to avoid overlaps with anything else */ +#define EXITS_TEST_GVA 0xc0000000 +#define EXITS_TEST_GPA EXITS_TEST_GVA +#define EXITS_TEST_NPAGES 1 +#define EXITS_TEST_SIZE (EXITS_TEST_NPAGES * PAGE_SIZE) +#define EXITS_TEST_SLOT 10 + +static uint64_t guest_repeatedly_read(void) +{ + volatile uint64_t value; + + while (true) + value = *((uint64_t *) EXITS_TEST_GVA); + + return value; +} + +static uint32_t run_vcpu_get_exit_reason(struct kvm_vcpu *vcpu) +{ + int r; + + r = _vcpu_run(vcpu); + if (r) { + TEST_ASSERT(errno == EFAULT, KVM_IOCTL_ERROR(KVM_RUN, r)); + TEST_ASSERT_EQ(vcpu->run->exit_reason, KVM_EXIT_MEMORY_FAULT); + } + return vcpu->run->exit_reason; +} + +const struct vm_shape protected_vm_shape = { + .mode = VM_MODE_DEFAULT, + .type = KVM_X86_SW_PROTECTED_VM, +}; + +static void test_private_access_memslot_deleted(void) +{ + struct kvm_vm *vm; + struct kvm_vcpu *vcpu; + pthread_t vm_thread; + void *thread_return; + uint32_t exit_reason; + + vm = vm_create_shape_with_one_vcpu(protected_vm_shape, &vcpu, + guest_repeatedly_read); + + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, + EXITS_TEST_GPA, EXITS_TEST_SLOT, + EXITS_TEST_NPAGES, + KVM_MEM_GUEST_MEMFD); + + virt_map(vm, EXITS_TEST_GVA, EXITS_TEST_GPA, EXITS_TEST_NPAGES); + + /* Request to access page privately */ + vm_mem_set_private(vm, EXITS_TEST_GPA, EXITS_TEST_SIZE); + + pthread_create(&vm_thread, NULL, + (void *(*)(void *))run_vcpu_get_exit_reason, + (void *)vcpu); + + vm_mem_region_delete(vm, EXITS_TEST_SLOT); + + pthread_join(vm_thread, &thread_return); + exit_reason = (uint32_t)(uint64_t)thread_return; + + TEST_ASSERT_EQ(exit_reason, KVM_EXIT_MEMORY_FAULT); + TEST_ASSERT_EQ(vcpu->run->memory_fault.flags, KVM_MEMORY_EXIT_FLAG_PRIVATE); + TEST_ASSERT_EQ(vcpu->run->memory_fault.gpa, EXITS_TEST_GPA); + TEST_ASSERT_EQ(vcpu->run->memory_fault.size, EXITS_TEST_SIZE); + + kvm_vm_free(vm); +} + +static void test_private_access_memslot_not_private(void) +{ + struct kvm_vm *vm; + struct kvm_vcpu *vcpu; + uint32_t exit_reason; + + vm = vm_create_shape_with_one_vcpu(protected_vm_shape, &vcpu, + guest_repeatedly_read); + + /* Add a non-private memslot (flags = 0) */ + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, + EXITS_TEST_GPA, EXITS_TEST_SLOT, + EXITS_TEST_NPAGES, 0); + + virt_map(vm, EXITS_TEST_GVA, EXITS_TEST_GPA, EXITS_TEST_NPAGES); + + /* Request to access page privately */ + vm_mem_set_private(vm, EXITS_TEST_GPA, EXITS_TEST_SIZE); + + exit_reason = run_vcpu_get_exit_reason(vcpu); + + TEST_ASSERT_EQ(exit_reason, KVM_EXIT_MEMORY_FAULT); + TEST_ASSERT_EQ(vcpu->run->memory_fault.flags, KVM_MEMORY_EXIT_FLAG_PRIVATE); + TEST_ASSERT_EQ(vcpu->run->memory_fault.gpa, EXITS_TEST_GPA); + TEST_ASSERT_EQ(vcpu->run->memory_fault.size, EXITS_TEST_SIZE); + + kvm_vm_free(vm); +} + +int main(int argc, char *argv[]) +{ + TEST_REQUIRE(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM)); + + test_private_access_memslot_deleted(); + test_private_access_memslot_not_private(); +} diff --git a/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c b/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c index 7ee44496cf97..0c7ce3d4e83a 100644 --- a/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c +++ b/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c @@ -103,7 +103,7 @@ static void l1_guest_code(struct svm_test_data *svm, uint64_t is_nmi, uint64_t i run_guest(vmcb, svm->vmcb_gpa); __GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL, - "Expected VMMCAL #VMEXIT, got '0x%x', info1 = '0x%llx, info2 = '0x%llx'", + "Expected VMMCAL #VMEXIT, got '0x%x', info1 = '0x%lx, info2 = '0x%lx'", vmcb->control.exit_code, vmcb->control.exit_info_1, vmcb->control.exit_info_2); @@ -133,7 +133,7 @@ static void l1_guest_code(struct svm_test_data *svm, uint64_t is_nmi, uint64_t i run_guest(vmcb, svm->vmcb_gpa); __GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_HLT, - "Expected HLT #VMEXIT, got '0x%x', info1 = '0x%llx, info2 = '0x%llx'", + "Expected HLT #VMEXIT, got '0x%x', info1 = '0x%lx, info2 = '0x%lx'", vmcb->control.exit_code, vmcb->control.exit_info_1, vmcb->control.exit_info_2); diff --git a/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c b/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c index 85f34ca7e49e..0ed32ec903d0 100644 --- a/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c +++ b/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c @@ -271,7 +271,7 @@ int main(int argc, char *argv[]) kvm_check_cap(KVM_CAP_MCE); - vm = __vm_create(VM_MODE_DEFAULT, 3, 0); + vm = __vm_create(VM_SHAPE_DEFAULT, 3, 0); kvm_ioctl(vm->kvm_fd, KVM_X86_GET_MCE_CAP_SUPPORTED, &supported_mcg_caps); diff --git a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c index ebbcb0a3f743..2a8d4ac2f020 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c @@ -56,7 +56,7 @@ static void guest_test_perf_capabilities_gp(uint64_t val) uint8_t vector = wrmsr_safe(MSR_IA32_PERF_CAPABILITIES, val); __GUEST_ASSERT(vector == GP_VECTOR, - "Expected #GP for value '0x%llx', got vector '0x%x'", + "Expected #GP for value '0x%lx', got vector '0x%x'", val, vector); } diff --git a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c index 41ea7028a1f8..67a62a5a8895 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c @@ -125,21 +125,25 @@ void test_vmx_nested_state(struct kvm_vcpu *vcpu) /* * Setting vmxon_pa == -1ull and vmcs_pa == -1ull exits early without - * setting the nested state but flags other than eVMCS must be clear. - * The eVMCS flag can be set if the enlightened VMCS capability has - * been enabled. + * setting the nested state. When the eVMCS flag is not set, the + * expected return value is '0'. */ set_default_vmx_state(state, state_sz); + state->flags = 0; state->hdr.vmx.vmxon_pa = -1ull; state->hdr.vmx.vmcs12_pa = -1ull; - test_nested_state_expect_einval(vcpu, state); + test_nested_state(vcpu, state); - state->flags &= KVM_STATE_NESTED_EVMCS; + /* + * When eVMCS is supported, the eVMCS flag can only be set if the + * enlightened VMCS capability has been enabled. + */ if (have_evmcs) { + state->flags = KVM_STATE_NESTED_EVMCS; test_nested_state_expect_einval(vcpu, state); vcpu_enable_evmcs(vcpu); + test_nested_state(vcpu, state); } - test_nested_state(vcpu, state); /* It is invalid to have vmxon_pa == -1ull and SMM flags non-zero. */ state->hdr.vmx.smm.flags = 1; diff --git a/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c b/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c index 77d04a7bdadd..dc6217440db3 100644 --- a/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c +++ b/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c @@ -25,7 +25,7 @@ do { \ \ __GUEST_ASSERT((__supported & (xfeatures)) != (xfeatures) || \ __supported == ((xfeatures) | (dependencies)), \ - "supported = 0x%llx, xfeatures = 0x%llx, dependencies = 0x%llx", \ + "supported = 0x%lx, xfeatures = 0x%llx, dependencies = 0x%llx", \ __supported, (xfeatures), (dependencies)); \ } while (0) @@ -42,7 +42,7 @@ do { \ uint64_t __supported = (supported_xcr0) & (xfeatures); \ \ __GUEST_ASSERT(!__supported || __supported == (xfeatures), \ - "supported = 0x%llx, xfeatures = 0x%llx", \ + "supported = 0x%lx, xfeatures = 0x%llx", \ __supported, (xfeatures)); \ } while (0) @@ -81,7 +81,7 @@ static void guest_code(void) vector = xsetbv_safe(0, supported_xcr0); __GUEST_ASSERT(!vector, - "Expected success on XSETBV(0x%llx), got vector '0x%x'", + "Expected success on XSETBV(0x%lx), got vector '0x%x'", supported_xcr0, vector); for (i = 0; i < 64; i++) { @@ -90,7 +90,7 @@ static void guest_code(void) vector = xsetbv_safe(0, supported_xcr0 | BIT_ULL(i)); __GUEST_ASSERT(vector == GP_VECTOR, - "Expected #GP on XSETBV(0x%llx), supported XCR0 = %llx, got vector '0x%x'", + "Expected #GP on XSETBV(0x%llx), supported XCR0 = %lx, got vector '0x%x'", BIT_ULL(i), supported_xcr0, vector); } diff --git a/tools/testing/selftests/livepatch/functions.sh b/tools/testing/selftests/livepatch/functions.sh index c8416c54b463..b1fd7362c2fe 100644 --- a/tools/testing/selftests/livepatch/functions.sh +++ b/tools/testing/selftests/livepatch/functions.sh @@ -42,17 +42,6 @@ function die() { exit 1 } -# save existing dmesg so we can detect new content -function save_dmesg() { - SAVED_DMESG=$(mktemp --tmpdir -t klp-dmesg-XXXXXX) - dmesg > "$SAVED_DMESG" -} - -# cleanup temporary dmesg file from save_dmesg() -function cleanup_dmesg_file() { - rm -f "$SAVED_DMESG" -} - function push_config() { DYNAMIC_DEBUG=$(grep '^kernel/livepatch' /sys/kernel/debug/dynamic_debug/control | \ awk -F'[: ]' '{print "file " $1 " line " $2 " " $4}') @@ -99,7 +88,6 @@ function set_ftrace_enabled() { function cleanup() { pop_config - cleanup_dmesg_file } # setup_config - save the current config and set a script exit trap that @@ -280,7 +268,15 @@ function set_pre_patch_ret { function start_test { local test="$1" - save_dmesg + # Dump something unique into the dmesg log, then stash the entry + # in LAST_DMESG. The check_result() function will use it to + # find new kernel messages since the test started. + local last_dmesg_msg="livepatch kselftest timestamp: $(date --rfc-3339=ns)" + log "$last_dmesg_msg" + loop_until 'dmesg | grep -q "$last_dmesg_msg"' || + die "buffer busy? can't find canary dmesg message: $last_dmesg_msg" + LAST_DMESG=$(dmesg | grep "$last_dmesg_msg") + echo -n "TEST: $test ... " log "===== TEST: $test =====" } @@ -291,23 +287,24 @@ function check_result { local expect="$*" local result - # Note: when comparing dmesg output, the kernel log timestamps - # help differentiate repeated testing runs. Remove them with a - # post-comparison sed filter. - - result=$(dmesg | comm --nocheck-order -13 "$SAVED_DMESG" - | \ + # Test results include any new dmesg entry since LAST_DMESG, then: + # - include lines matching keywords + # - exclude lines matching keywords + # - filter out dmesg timestamp prefixes + result=$(dmesg | awk -v last_dmesg="$LAST_DMESG" 'p; $0 == last_dmesg { p=1 }' | \ grep -e 'livepatch:' -e 'test_klp' | \ grep -v '\(tainting\|taints\) kernel' | \ sed 's/^\[[ 0-9.]*\] //') if [[ "$expect" == "$result" ]] ; then echo "ok" + elif [[ "$result" == "" ]] ; then + echo -e "not ok\n\nbuffer overrun? can't find canary dmesg entry: $LAST_DMESG\n" + die "livepatch kselftest(s) failed" else echo -e "not ok\n\n$(diff -upr --label expected --label result <(echo "$expect") <(echo "$result"))\n" die "livepatch kselftest(s) failed" fi - - cleanup_dmesg_file } # check_sysfs_rights(modname, rel_path, expected_rights) - check sysfs diff --git a/tools/testing/selftests/mm/charge_reserved_hugetlb.sh b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh index 0899019a7fcb..e14bdd4455f2 100755 --- a/tools/testing/selftests/mm/charge_reserved_hugetlb.sh +++ b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 # Kselftest framework requirement - SKIP code is 4. diff --git a/tools/testing/selftests/mm/hugepage-vmemmap.c b/tools/testing/selftests/mm/hugepage-vmemmap.c index 5b354c209e93..894d28c3dd47 100644 --- a/tools/testing/selftests/mm/hugepage-vmemmap.c +++ b/tools/testing/selftests/mm/hugepage-vmemmap.c @@ -10,10 +10,7 @@ #include <unistd.h> #include <sys/mman.h> #include <fcntl.h> - -#define MAP_LENGTH (2UL * 1024 * 1024) - -#define PAGE_SIZE 4096 +#include "vm_util.h" #define PAGE_COMPOUND_HEAD (1UL << 15) #define PAGE_COMPOUND_TAIL (1UL << 16) @@ -39,6 +36,9 @@ #define MAP_FLAGS (MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB) #endif +static size_t pagesize; +static size_t maplength; + static void write_bytes(char *addr, size_t length) { unsigned long i; @@ -56,7 +56,7 @@ static unsigned long virt_to_pfn(void *addr) if (fd < 0) return -1UL; - lseek(fd, (unsigned long)addr / PAGE_SIZE * sizeof(pagemap), SEEK_SET); + lseek(fd, (unsigned long)addr / pagesize * sizeof(pagemap), SEEK_SET); read(fd, &pagemap, sizeof(pagemap)); close(fd); @@ -86,7 +86,7 @@ static int check_page_flags(unsigned long pfn) * this also verifies kernel has correctly set the fake page_head to tail * while hugetlb_free_vmemmap is enabled. */ - for (i = 1; i < MAP_LENGTH / PAGE_SIZE; i++) { + for (i = 1; i < maplength / pagesize; i++) { read(fd, &pageflags, sizeof(pageflags)); if ((pageflags & TAIL_PAGE_FLAGS) != TAIL_PAGE_FLAGS || (pageflags & HEAD_PAGE_FLAGS) == HEAD_PAGE_FLAGS) { @@ -106,18 +106,25 @@ int main(int argc, char **argv) void *addr; unsigned long pfn; - addr = mmap(MAP_ADDR, MAP_LENGTH, PROT_READ | PROT_WRITE, MAP_FLAGS, -1, 0); + pagesize = psize(); + maplength = default_huge_page_size(); + if (!maplength) { + printf("Unable to determine huge page size\n"); + exit(1); + } + + addr = mmap(MAP_ADDR, maplength, PROT_READ | PROT_WRITE, MAP_FLAGS, -1, 0); if (addr == MAP_FAILED) { perror("mmap"); exit(1); } /* Trigger allocation of HugeTLB page. */ - write_bytes(addr, MAP_LENGTH); + write_bytes(addr, maplength); pfn = virt_to_pfn(addr); if (pfn == -1UL) { - munmap(addr, MAP_LENGTH); + munmap(addr, maplength); perror("virt_to_pfn"); exit(1); } @@ -125,13 +132,13 @@ int main(int argc, char **argv) printf("Returned address is %p whose pfn is %lx\n", addr, pfn); if (check_page_flags(pfn) < 0) { - munmap(addr, MAP_LENGTH); + munmap(addr, maplength); perror("check_page_flags"); exit(1); } /* munmap() length of MAP_HUGETLB memory must be hugepage aligned */ - if (munmap(addr, MAP_LENGTH)) { + if (munmap(addr, maplength)) { perror("munmap"); exit(1); } diff --git a/tools/testing/selftests/mm/ksm_tests.c b/tools/testing/selftests/mm/ksm_tests.c index 380b691d3eb9..b748c48908d9 100644 --- a/tools/testing/selftests/mm/ksm_tests.c +++ b/tools/testing/selftests/mm/ksm_tests.c @@ -566,7 +566,7 @@ static int ksm_merge_hugepages_time(int merge_type, int mapping, int prot, if (map_ptr_orig == MAP_FAILED) err(2, "initial mmap"); - if (madvise(map_ptr, len + HPAGE_SIZE, MADV_HUGEPAGE)) + if (madvise(map_ptr, len, MADV_HUGEPAGE)) err(2, "MADV_HUGEPAGE"); pagemap_fd = open("/proc/self/pagemap", O_RDONLY); diff --git a/tools/testing/selftests/mm/map_hugetlb.c b/tools/testing/selftests/mm/map_hugetlb.c index 193281560b61..86e8f2048a40 100644 --- a/tools/testing/selftests/mm/map_hugetlb.c +++ b/tools/testing/selftests/mm/map_hugetlb.c @@ -15,6 +15,7 @@ #include <unistd.h> #include <sys/mman.h> #include <fcntl.h> +#include "vm_util.h" #define LENGTH (256UL*1024*1024) #define PROTECTION (PROT_READ | PROT_WRITE) @@ -58,10 +59,16 @@ int main(int argc, char **argv) { void *addr; int ret; + size_t hugepage_size; size_t length = LENGTH; int flags = FLAGS; int shift = 0; + hugepage_size = default_huge_page_size(); + /* munmap with fail if the length is not page aligned */ + if (hugepage_size > length) + length = hugepage_size; + if (argc > 1) length = atol(argv[1]) << 20; if (argc > 2) { diff --git a/tools/testing/selftests/mm/mremap_test.c b/tools/testing/selftests/mm/mremap_test.c index 1d4c1589c305..2f8b991f78cb 100644 --- a/tools/testing/selftests/mm/mremap_test.c +++ b/tools/testing/selftests/mm/mremap_test.c @@ -360,7 +360,8 @@ static long long remap_region(struct config c, unsigned int threshold_mb, char pattern_seed) { void *addr, *src_addr, *dest_addr, *dest_preamble_addr; - unsigned long long i; + int d; + unsigned long long t; struct timespec t_start = {0, 0}, t_end = {0, 0}; long long start_ns, end_ns, align_mask, ret, offset; unsigned long long threshold; @@ -378,8 +379,8 @@ static long long remap_region(struct config c, unsigned int threshold_mb, /* Set byte pattern for source block. */ srand(pattern_seed); - for (i = 0; i < threshold; i++) - memset((char *) src_addr + i, (char) rand(), 1); + for (t = 0; t < threshold; t++) + memset((char *) src_addr + t, (char) rand(), 1); /* Mask to zero out lower bits of address for alignment */ align_mask = ~(c.dest_alignment - 1); @@ -420,8 +421,8 @@ static long long remap_region(struct config c, unsigned int threshold_mb, /* Set byte pattern for the dest preamble block. */ srand(pattern_seed); - for (i = 0; i < c.dest_preamble_size; i++) - memset((char *) dest_preamble_addr + i, (char) rand(), 1); + for (d = 0; d < c.dest_preamble_size; d++) + memset((char *) dest_preamble_addr + d, (char) rand(), 1); } clock_gettime(CLOCK_MONOTONIC, &t_start); @@ -437,14 +438,14 @@ static long long remap_region(struct config c, unsigned int threshold_mb, /* Verify byte pattern after remapping */ srand(pattern_seed); - for (i = 0; i < threshold; i++) { + for (t = 0; t < threshold; t++) { char c = (char) rand(); - if (((char *) dest_addr)[i] != c) { + if (((char *) dest_addr)[t] != c) { ksft_print_msg("Data after remap doesn't match at offset %llu\n", - i); + t); ksft_print_msg("Expected: %#x\t Got: %#x\n", c & 0xff, - ((char *) dest_addr)[i] & 0xff); + ((char *) dest_addr)[t] & 0xff); ret = -1; goto clean_up_dest; } @@ -453,14 +454,14 @@ static long long remap_region(struct config c, unsigned int threshold_mb, /* Verify the dest preamble byte pattern after remapping */ if (c.dest_preamble_size) { srand(pattern_seed); - for (i = 0; i < c.dest_preamble_size; i++) { + for (d = 0; d < c.dest_preamble_size; d++) { char c = (char) rand(); - if (((char *) dest_preamble_addr)[i] != c) { + if (((char *) dest_preamble_addr)[d] != c) { ksft_print_msg("Preamble data after remap doesn't match at offset %d\n", - i); + d); ksft_print_msg("Expected: %#x\t Got: %#x\n", c & 0xff, - ((char *) dest_preamble_addr)[i] & 0xff); + ((char *) dest_preamble_addr)[d] & 0xff); ret = -1; goto clean_up_dest; } diff --git a/tools/testing/selftests/mm/va_high_addr_switch.sh b/tools/testing/selftests/mm/va_high_addr_switch.sh index 45cae7cab27e..a0a75f302904 100755 --- a/tools/testing/selftests/mm/va_high_addr_switch.sh +++ b/tools/testing/selftests/mm/va_high_addr_switch.sh @@ -29,9 +29,15 @@ check_supported_x86_64() # See man 1 gzip under '-f'. local pg_table_levels=$(gzip -dcfq "${config}" | grep PGTABLE_LEVELS | cut -d'=' -f 2) + local cpu_supports_pl5=$(awk '/^flags/ {if (/la57/) {print 0;} + else {print 1}; exit}' /proc/cpuinfo 2>/dev/null) + if [[ "${pg_table_levels}" -lt 5 ]]; then echo "$0: PGTABLE_LEVELS=${pg_table_levels}, must be >= 5 to run this test" exit $ksft_skip + elif [[ "${cpu_supports_pl5}" -ne 0 ]]; then + echo "$0: CPU does not have the necessary la57 flag to support page table level 5" + exit $ksft_skip fi } diff --git a/tools/testing/selftests/mm/write_hugetlb_memory.sh b/tools/testing/selftests/mm/write_hugetlb_memory.sh index 70a02301f4c2..3d2d2eb9d6ff 100755 --- a/tools/testing/selftests/mm/write_hugetlb_memory.sh +++ b/tools/testing/selftests/mm/write_hugetlb_memory.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 set -e diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index 8da562a9ae87..19ff75051660 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -1,5 +1,6 @@ CONFIG_USER_NS=y CONFIG_NET_NS=y +CONFIG_BONDING=m CONFIG_BPF_SYSCALL=y CONFIG_TEST_BPF=m CONFIG_NUMA=y @@ -14,9 +15,13 @@ CONFIG_VETH=y CONFIG_NET_IPVTI=y CONFIG_IPV6_VTI=y CONFIG_DUMMY=y +CONFIG_BRIDGE_VLAN_FILTERING=y CONFIG_BRIDGE=y +CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_VLAN_8021Q=y CONFIG_IFB=y +CONFIG_INET_DIAG=y +CONFIG_IP_GRE=m CONFIG_NETFILTER=y CONFIG_NETFILTER_ADVANCED=y CONFIG_NF_CONNTRACK=m @@ -25,15 +30,36 @@ CONFIG_IP6_NF_IPTABLES=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP6_NF_NAT=m CONFIG_IP_NF_NAT=m +CONFIG_IPV6_GRE=m +CONFIG_IPV6_SEG6_LWTUNNEL=y +CONFIG_L2TP_ETH=m +CONFIG_L2TP_IP=m +CONFIG_L2TP=m +CONFIG_L2TP_V3=y +CONFIG_MACSEC=m +CONFIG_MACVLAN=y +CONFIG_MACVTAP=y +CONFIG_MPLS=y +CONFIG_MPTCP=y CONFIG_NF_TABLES=m CONFIG_NF_TABLES_IPV6=y CONFIG_NF_TABLES_IPV4=y CONFIG_NFT_NAT=m +CONFIG_NET_ACT_GACT=m +CONFIG_NET_CLS_BASIC=m +CONFIG_NET_CLS_U32=m +CONFIG_NET_IPGRE_DEMUX=m +CONFIG_NET_IPGRE=m +CONFIG_NET_SCH_FQ_CODEL=m +CONFIG_NET_SCH_HTB=m CONFIG_NET_SCH_FQ=m CONFIG_NET_SCH_ETF=m CONFIG_NET_SCH_NETEM=y +CONFIG_PSAMPLE=m +CONFIG_TCP_MD5SIG=y CONFIG_TEST_BLACKHOLE_DEV=m CONFIG_KALLSYMS=y +CONFIG_TLS=m CONFIG_TRACEPOINTS=y CONFIG_NET_DROP_MONITOR=m CONFIG_NETDEVSIM=m @@ -48,7 +74,9 @@ CONFIG_BAREUDP=m CONFIG_IPV6_IOAM6_LWTUNNEL=y CONFIG_CRYPTO_SM4_GENERIC=y CONFIG_AMT=m +CONFIG_TUN=y CONFIG_VXLAN=m CONFIG_IP_SCTP=m CONFIG_NETFILTER_XT_MATCH_POLICY=m CONFIG_CRYPTO_ARIA=y +CONFIG_XFRM_INTERFACE=m diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 8a61464ab6eb..8a61464ab6eb 100755..100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh diff --git a/tools/testing/selftests/net/rps_default_mask.sh b/tools/testing/selftests/net/rps_default_mask.sh index a26c5624429f..4287a8529890 100755 --- a/tools/testing/selftests/net/rps_default_mask.sh +++ b/tools/testing/selftests/net/rps_default_mask.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 readonly ksft_skip=4 @@ -33,6 +33,10 @@ chk_rps() { rps_mask=$($cmd /sys/class/net/$dev_name/queues/rx-0/rps_cpus) printf "%-60s" "$msg" + + # In case there is more than 32 CPUs we need to remove commas from masks + rps_mask=${rps_mask//,} + expected_rps_mask=${expected_rps_mask//,} if [ $rps_mask -eq $expected_rps_mask ]; then echo "[ ok ]" else diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index a10a32952f21..4667d74579d1 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -28,6 +28,7 @@ ALL_TESTS=" kci_test_neigh_get kci_test_bridge_parent_id kci_test_address_proto + kci_test_enslave_bonding " devdummy="test-dummy0" @@ -1241,6 +1242,31 @@ kci_test_address_proto() return $ret } +kci_test_enslave_bonding() +{ + local bond="bond123" + local ret=0 + + setup_ns testns + if [ $? -ne 0 ]; then + end_test "SKIP bonding tests: cannot add net namespace $testns" + return $ksft_skip + fi + + run_cmd ip -netns $testns link add dev $bond type bond mode balance-rr + run_cmd ip -netns $testns link add dev $devdummy type dummy + run_cmd ip -netns $testns link set dev $devdummy up + run_cmd ip -netns $testns link set dev $devdummy master $bond down + if [ $ret -ne 0 ]; then + end_test "FAIL: initially up interface added to a bond and set down" + ip netns del "$testns" + return 1 + fi + + end_test "PASS: enslave interface in a bond" + ip netns del "$testns" +} + kci_test_rtnl() { local current_test diff --git a/tools/testing/selftests/net/so_incoming_cpu.c b/tools/testing/selftests/net/so_incoming_cpu.c index a14818164102..e9fa14e10732 100644 --- a/tools/testing/selftests/net/so_incoming_cpu.c +++ b/tools/testing/selftests/net/so_incoming_cpu.c @@ -3,19 +3,16 @@ #define _GNU_SOURCE #include <sched.h> +#include <fcntl.h> + #include <netinet/in.h> #include <sys/socket.h> #include <sys/sysinfo.h> #include "../kselftest_harness.h" -#define CLIENT_PER_SERVER 32 /* More sockets, more reliable */ -#define NR_SERVER self->nproc -#define NR_CLIENT (CLIENT_PER_SERVER * NR_SERVER) - FIXTURE(so_incoming_cpu) { - int nproc; int *servers; union { struct sockaddr addr; @@ -56,12 +53,47 @@ FIXTURE_VARIANT_ADD(so_incoming_cpu, after_all_listen) .when_to_set = AFTER_ALL_LISTEN, }; +static void write_sysctl(struct __test_metadata *_metadata, + char *filename, char *string) +{ + int fd, len, ret; + + fd = open(filename, O_WRONLY); + ASSERT_NE(fd, -1); + + len = strlen(string); + ret = write(fd, string, len); + ASSERT_EQ(ret, len); +} + +static void setup_netns(struct __test_metadata *_metadata) +{ + ASSERT_EQ(unshare(CLONE_NEWNET), 0); + ASSERT_EQ(system("ip link set lo up"), 0); + + write_sysctl(_metadata, "/proc/sys/net/ipv4/ip_local_port_range", "10000 60001"); + write_sysctl(_metadata, "/proc/sys/net/ipv4/tcp_tw_reuse", "0"); +} + +#define NR_PORT (60001 - 10000 - 1) +#define NR_CLIENT_PER_SERVER_DEFAULT 32 +static int nr_client_per_server, nr_server, nr_client; + FIXTURE_SETUP(so_incoming_cpu) { - self->nproc = get_nprocs(); - ASSERT_LE(2, self->nproc); + setup_netns(_metadata); + + nr_server = get_nprocs(); + ASSERT_LE(2, nr_server); + + if (NR_CLIENT_PER_SERVER_DEFAULT * nr_server < NR_PORT) + nr_client_per_server = NR_CLIENT_PER_SERVER_DEFAULT; + else + nr_client_per_server = NR_PORT / nr_server; + + nr_client = nr_client_per_server * nr_server; - self->servers = malloc(sizeof(int) * NR_SERVER); + self->servers = malloc(sizeof(int) * nr_server); ASSERT_NE(self->servers, NULL); self->in_addr.sin_family = AF_INET; @@ -74,7 +106,7 @@ FIXTURE_TEARDOWN(so_incoming_cpu) { int i; - for (i = 0; i < NR_SERVER; i++) + for (i = 0; i < nr_server; i++) close(self->servers[i]); free(self->servers); @@ -110,10 +142,10 @@ int create_server(struct __test_metadata *_metadata, if (variant->when_to_set == BEFORE_LISTEN) set_so_incoming_cpu(_metadata, fd, cpu); - /* We don't use CLIENT_PER_SERVER here not to block + /* We don't use nr_client_per_server here not to block * this test at connect() if SO_INCOMING_CPU is broken. */ - ret = listen(fd, NR_CLIENT); + ret = listen(fd, nr_client); ASSERT_EQ(ret, 0); if (variant->when_to_set == AFTER_LISTEN) @@ -128,7 +160,7 @@ void create_servers(struct __test_metadata *_metadata, { int i, ret; - for (i = 0; i < NR_SERVER; i++) { + for (i = 0; i < nr_server; i++) { self->servers[i] = create_server(_metadata, self, variant, i); if (i == 0) { @@ -138,7 +170,7 @@ void create_servers(struct __test_metadata *_metadata, } if (variant->when_to_set == AFTER_ALL_LISTEN) { - for (i = 0; i < NR_SERVER; i++) + for (i = 0; i < nr_server; i++) set_so_incoming_cpu(_metadata, self->servers[i], i); } } @@ -149,7 +181,7 @@ void create_clients(struct __test_metadata *_metadata, cpu_set_t cpu_set; int i, j, fd, ret; - for (i = 0; i < NR_SERVER; i++) { + for (i = 0; i < nr_server; i++) { CPU_ZERO(&cpu_set); CPU_SET(i, &cpu_set); @@ -162,7 +194,7 @@ void create_clients(struct __test_metadata *_metadata, ret = sched_setaffinity(0, sizeof(cpu_set), &cpu_set); ASSERT_EQ(ret, 0); - for (j = 0; j < CLIENT_PER_SERVER; j++) { + for (j = 0; j < nr_client_per_server; j++) { fd = socket(AF_INET, SOCK_STREAM, 0); ASSERT_NE(fd, -1); @@ -180,8 +212,8 @@ void verify_incoming_cpu(struct __test_metadata *_metadata, int i, j, fd, cpu, ret, total = 0; socklen_t len = sizeof(int); - for (i = 0; i < NR_SERVER; i++) { - for (j = 0; j < CLIENT_PER_SERVER; j++) { + for (i = 0; i < nr_server; i++) { + for (j = 0; j < nr_client_per_server; j++) { /* If we see -EAGAIN here, SO_INCOMING_CPU is broken */ fd = accept(self->servers[i], &self->addr, &self->addrlen); ASSERT_NE(fd, -1); @@ -195,7 +227,7 @@ void verify_incoming_cpu(struct __test_metadata *_metadata, } } - ASSERT_EQ(total, NR_CLIENT); + ASSERT_EQ(total, nr_client); TH_LOG("SO_INCOMING_CPU is very likely to be " "working correctly with %d sockets.", total); } diff --git a/tools/testing/selftests/net/tcp_ao/Makefile b/tools/testing/selftests/net/tcp_ao/Makefile index 8e60bae67aa9..522d991e310e 100644 --- a/tools/testing/selftests/net/tcp_ao/Makefile +++ b/tools/testing/selftests/net/tcp_ao/Makefile @@ -52,5 +52,5 @@ $(OUTPUT)/%_ipv6: %.c $(OUTPUT)/icmps-accept_ipv4: CFLAGS+= -DTEST_ICMPS_ACCEPT $(OUTPUT)/icmps-accept_ipv6: CFLAGS+= -DTEST_ICMPS_ACCEPT -$(OUTPUT)/bench-lookups_ipv4: LDFLAGS+= -lm -$(OUTPUT)/bench-lookups_ipv6: LDFLAGS+= -lm +$(OUTPUT)/bench-lookups_ipv4: LDLIBS+= -lm +$(OUTPUT)/bench-lookups_ipv6: LDLIBS+= -lm diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 464853a7f982..7799e042a971 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -707,6 +707,20 @@ TEST_F(tls, splice_from_pipe) EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0); } +TEST_F(tls, splice_more) +{ + unsigned int f = SPLICE_F_NONBLOCK | SPLICE_F_MORE | SPLICE_F_GIFT; + int send_len = TLS_PAYLOAD_MAX_LEN; + char mem_send[TLS_PAYLOAD_MAX_LEN]; + int i, send_pipe = 1; + int p[2]; + + ASSERT_GE(pipe(p), 0); + EXPECT_GE(write(p[1], mem_send, send_len), 0); + for (i = 0; i < 32; i++) + EXPECT_EQ(splice(p[0], NULL, self->fd, NULL, send_pipe, f), 1); +} + TEST_F(tls, splice_from_pipe2) { int send_len = 16000; diff --git a/tools/testing/selftests/rcutorture/bin/mkinitrd.sh b/tools/testing/selftests/rcutorture/bin/mkinitrd.sh index 212c52ca90b5..f3f867129560 100755 --- a/tools/testing/selftests/rcutorture/bin/mkinitrd.sh +++ b/tools/testing/selftests/rcutorture/bin/mkinitrd.sh @@ -67,7 +67,10 @@ ___EOF___ # build using nolibc on supported archs (smaller executable) and fall # back to regular glibc on other ones. if echo -e "#if __x86_64__||__i386__||__i486__||__i586__||__i686__" \ - "||__ARM_EABI__||__aarch64__||__s390x__||__loongarch__\nyes\n#endif" \ + "||__ARM_EABI__||__aarch64__||(__mips__ && _ABIO32)" \ + "||__powerpc__||(__riscv && __riscv_xlen == 64)" \ + "||__s390x__||__loongarch__" \ + "\nyes\n#endif" \ | ${CROSS_COMPILE}gcc -E -nostdlib -xc - \ | grep -q '^yes'; then # architecture supported by nolibc diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE07.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE07.boot index d44609937503..979edbf4c820 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE07.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE07.boot @@ -1 +1,4 @@ nohz_full=2-9 +rcutorture.stall_cpu=14 +rcutorture.stall_cpu_holdoff=90 +rcutorture.fwd_progress=0 diff --git a/tools/testing/selftests/riscv/hwprobe/Makefile b/tools/testing/selftests/riscv/hwprobe/Makefile index f224b84591fb..cec81610a5f2 100644 --- a/tools/testing/selftests/riscv/hwprobe/Makefile +++ b/tools/testing/selftests/riscv/hwprobe/Makefile @@ -4,7 +4,7 @@ CFLAGS += -I$(top_srcdir)/tools/include -TEST_GEN_PROGS := hwprobe cbo +TEST_GEN_PROGS := hwprobe cbo which-cpus include ../../lib.mk @@ -13,3 +13,6 @@ $(OUTPUT)/hwprobe: hwprobe.c sys_hwprobe.S $(OUTPUT)/cbo: cbo.c sys_hwprobe.S $(CC) -static -o$@ $(CFLAGS) $(LDFLAGS) $^ + +$(OUTPUT)/which-cpus: which-cpus.c sys_hwprobe.S + $(CC) -static -o$@ $(CFLAGS) $(LDFLAGS) $^ diff --git a/tools/testing/selftests/riscv/hwprobe/cbo.c b/tools/testing/selftests/riscv/hwprobe/cbo.c index 50a2cc8aef38..c537d52fafc5 100644 --- a/tools/testing/selftests/riscv/hwprobe/cbo.c +++ b/tools/testing/selftests/riscv/hwprobe/cbo.c @@ -36,16 +36,14 @@ static void sigill_handler(int sig, siginfo_t *info, void *context) regs[0] += 4; } -static void cbo_insn(char *base, int fn) -{ - uint32_t insn = MK_CBO(fn); - - asm volatile( - "mv a0, %0\n" - "li a1, %1\n" - ".4byte %2\n" - : : "r" (base), "i" (fn), "i" (insn) : "a0", "a1", "memory"); -} +#define cbo_insn(base, fn) \ +({ \ + asm volatile( \ + "mv a0, %0\n" \ + "li a1, %1\n" \ + ".4byte %2\n" \ + : : "r" (base), "i" (fn), "i" (MK_CBO(fn)) : "a0", "a1", "memory"); \ +}) static void cbo_inval(char *base) { cbo_insn(base, 0); } static void cbo_clean(char *base) { cbo_insn(base, 1); } @@ -97,7 +95,7 @@ static void test_zicboz(void *arg) block_size = pair.value; ksft_test_result(rc == 0 && pair.key == RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE && is_power_of_2(block_size), "Zicboz block size\n"); - ksft_print_msg("Zicboz block size: %ld\n", block_size); + ksft_print_msg("Zicboz block size: %llu\n", block_size); illegal_insn = false; cbo_zero(&mem[block_size]); @@ -121,7 +119,7 @@ static void test_zicboz(void *arg) for (j = 0; j < block_size; ++j) { if (mem[i * block_size + j] != expected) { ksft_test_result_fail("cbo.zero check\n"); - ksft_print_msg("cbo.zero check: mem[%d] != 0x%x\n", + ksft_print_msg("cbo.zero check: mem[%llu] != 0x%x\n", i * block_size + j, expected); return; } @@ -201,7 +199,7 @@ int main(int argc, char **argv) pair.key = RISCV_HWPROBE_KEY_IMA_EXT_0; rc = riscv_hwprobe(&pair, 1, sizeof(cpu_set_t), (unsigned long *)&cpus, 0); if (rc < 0) - ksft_exit_fail_msg("hwprobe() failed with %d\n", rc); + ksft_exit_fail_msg("hwprobe() failed with %ld\n", rc); assert(rc == 0 && pair.key == RISCV_HWPROBE_KEY_IMA_EXT_0); if (pair.value & RISCV_HWPROBE_EXT_ZICBOZ) { diff --git a/tools/testing/selftests/riscv/hwprobe/hwprobe.c b/tools/testing/selftests/riscv/hwprobe/hwprobe.c index c474891df307..fd73c87804f3 100644 --- a/tools/testing/selftests/riscv/hwprobe/hwprobe.c +++ b/tools/testing/selftests/riscv/hwprobe/hwprobe.c @@ -29,7 +29,7 @@ int main(int argc, char **argv) /* Fail if the kernel claims not to recognize a base key. */ if ((i < 4) && (pairs[i].key != i)) ksft_exit_fail_msg("Failed to recognize base key: key != i, " - "key=%ld, i=%ld\n", pairs[i].key, i); + "key=%lld, i=%ld\n", pairs[i].key, i); if (pairs[i].key != RISCV_HWPROBE_KEY_BASE_BEHAVIOR) continue; @@ -37,7 +37,7 @@ int main(int argc, char **argv) if (pairs[i].value & RISCV_HWPROBE_BASE_BEHAVIOR_IMA) continue; - ksft_exit_fail_msg("Unexpected pair: (%ld, %ld)\n", pairs[i].key, pairs[i].value); + ksft_exit_fail_msg("Unexpected pair: (%lld, %llu)\n", pairs[i].key, pairs[i].value); } out = riscv_hwprobe(pairs, 8, 0, 0, 0); @@ -47,7 +47,7 @@ int main(int argc, char **argv) ksft_test_result(out != 0, "Bad CPU set\n"); out = riscv_hwprobe(pairs, 8, 1, 0, 0); - ksft_test_result(out != 0, "NULL CPU set with non-zero count\n"); + ksft_test_result(out != 0, "NULL CPU set with non-zero size\n"); pairs[0].key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR; out = riscv_hwprobe(pairs, 1, 1, &cpus, 0); diff --git a/tools/testing/selftests/riscv/hwprobe/hwprobe.h b/tools/testing/selftests/riscv/hwprobe/hwprobe.h index 721b0ce73a56..e3fccb390c4d 100644 --- a/tools/testing/selftests/riscv/hwprobe/hwprobe.h +++ b/tools/testing/selftests/riscv/hwprobe/hwprobe.h @@ -10,6 +10,6 @@ * contain the call. */ long riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count, - size_t cpu_count, unsigned long *cpus, unsigned int flags); + size_t cpusetsize, unsigned long *cpus, unsigned int flags); #endif diff --git a/tools/testing/selftests/riscv/hwprobe/which-cpus.c b/tools/testing/selftests/riscv/hwprobe/which-cpus.c new file mode 100644 index 000000000000..82c121412dfc --- /dev/null +++ b/tools/testing/selftests/riscv/hwprobe/which-cpus.c @@ -0,0 +1,154 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2023 Ventana Micro Systems Inc. + * + * Test the RISCV_HWPROBE_WHICH_CPUS flag of hwprobe. Also provides a command + * line interface to get the cpu list for arbitrary hwprobe pairs. + */ +#define _GNU_SOURCE +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sched.h> +#include <unistd.h> +#include <assert.h> + +#include "hwprobe.h" +#include "../../kselftest.h" + +static void help(void) +{ + printf("\n" + "which-cpus: [-h] [<key=value> [<key=value> ...]]\n\n" + " Without parameters, tests the RISCV_HWPROBE_WHICH_CPUS flag of hwprobe.\n" + " With parameters, where each parameter is a hwprobe pair written as\n" + " <key=value>, outputs the cpulist for cpus which all match the given set\n" + " of pairs. 'key' and 'value' should be in numeric form, e.g. 4=0x3b\n"); +} + +static void print_cpulist(cpu_set_t *cpus) +{ + int start = 0, end = 0; + + if (!CPU_COUNT(cpus)) { + printf("cpus: None\n"); + return; + } + + printf("cpus:"); + for (int i = 0, c = 0; i < CPU_COUNT(cpus); i++, c++) { + if (start != end && !CPU_ISSET(c, cpus)) + printf("-%d", end); + + while (!CPU_ISSET(c, cpus)) + ++c; + + if (i != 0 && c == end + 1) { + end = c; + continue; + } + + printf("%c%d", i == 0 ? ' ' : ',', c); + start = end = c; + } + if (start != end) + printf("-%d", end); + printf("\n"); +} + +static void do_which_cpus(int argc, char **argv, cpu_set_t *cpus) +{ + struct riscv_hwprobe *pairs; + int nr_pairs = argc - 1; + char *start, *end; + int rc; + + pairs = malloc(nr_pairs * sizeof(struct riscv_hwprobe)); + assert(pairs); + + for (int i = 0; i < nr_pairs; i++) { + start = argv[i + 1]; + pairs[i].key = strtol(start, &end, 0); + assert(end != start && *end == '='); + start = end + 1; + pairs[i].value = strtoul(start, &end, 0); + assert(end != start && *end == '\0'); + } + + rc = riscv_hwprobe(pairs, nr_pairs, sizeof(cpu_set_t), (unsigned long *)cpus, RISCV_HWPROBE_WHICH_CPUS); + assert(rc == 0); + print_cpulist(cpus); + free(pairs); +} + +int main(int argc, char **argv) +{ + struct riscv_hwprobe pairs[2]; + cpu_set_t cpus_aff, cpus; + __u64 ext0_all; + long rc; + + rc = sched_getaffinity(0, sizeof(cpu_set_t), &cpus_aff); + assert(rc == 0); + + if (argc > 1) { + if (!strcmp(argv[1], "-h")) + help(); + else + do_which_cpus(argc, argv, &cpus_aff); + return 0; + } + + ksft_print_header(); + ksft_set_plan(7); + + pairs[0] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR, }; + rc = riscv_hwprobe(pairs, 1, 0, NULL, 0); + assert(rc == 0 && pairs[0].key == RISCV_HWPROBE_KEY_BASE_BEHAVIOR && + pairs[0].value == RISCV_HWPROBE_BASE_BEHAVIOR_IMA); + + pairs[0] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_IMA_EXT_0, }; + rc = riscv_hwprobe(pairs, 1, 0, NULL, 0); + assert(rc == 0 && pairs[0].key == RISCV_HWPROBE_KEY_IMA_EXT_0); + ext0_all = pairs[0].value; + + pairs[0] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR, .value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA, }; + CPU_ZERO(&cpus); + rc = riscv_hwprobe(pairs, 1, 0, (unsigned long *)&cpus, RISCV_HWPROBE_WHICH_CPUS); + ksft_test_result(rc == -EINVAL, "no cpusetsize\n"); + + pairs[0] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR, .value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA, }; + rc = riscv_hwprobe(pairs, 1, sizeof(cpu_set_t), NULL, RISCV_HWPROBE_WHICH_CPUS); + ksft_test_result(rc == -EINVAL, "NULL cpus\n"); + + pairs[0] = (struct riscv_hwprobe){ .key = 0xbadc0de, }; + CPU_ZERO(&cpus); + rc = riscv_hwprobe(pairs, 1, sizeof(cpu_set_t), (unsigned long *)&cpus, RISCV_HWPROBE_WHICH_CPUS); + ksft_test_result(rc == 0 && CPU_COUNT(&cpus) == 0, "unknown key\n"); + + pairs[0] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR, .value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA, }; + pairs[1] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR, .value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA, }; + CPU_ZERO(&cpus); + rc = riscv_hwprobe(pairs, 2, sizeof(cpu_set_t), (unsigned long *)&cpus, RISCV_HWPROBE_WHICH_CPUS); + ksft_test_result(rc == 0, "duplicate keys\n"); + + pairs[0] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR, .value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA, }; + pairs[1] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_IMA_EXT_0, .value = ext0_all, }; + CPU_ZERO(&cpus); + rc = riscv_hwprobe(pairs, 2, sizeof(cpu_set_t), (unsigned long *)&cpus, RISCV_HWPROBE_WHICH_CPUS); + ksft_test_result(rc == 0 && CPU_COUNT(&cpus) == sysconf(_SC_NPROCESSORS_ONLN), "set all cpus\n"); + + pairs[0] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR, .value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA, }; + pairs[1] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_IMA_EXT_0, .value = ext0_all, }; + memcpy(&cpus, &cpus_aff, sizeof(cpu_set_t)); + rc = riscv_hwprobe(pairs, 2, sizeof(cpu_set_t), (unsigned long *)&cpus, RISCV_HWPROBE_WHICH_CPUS); + ksft_test_result(rc == 0 && CPU_EQUAL(&cpus, &cpus_aff), "set all affinity cpus\n"); + + pairs[0] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_BASE_BEHAVIOR, .value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA, }; + pairs[1] = (struct riscv_hwprobe){ .key = RISCV_HWPROBE_KEY_IMA_EXT_0, .value = ~ext0_all, }; + memcpy(&cpus, &cpus_aff, sizeof(cpu_set_t)); + rc = riscv_hwprobe(pairs, 2, sizeof(cpu_set_t), (unsigned long *)&cpus, RISCV_HWPROBE_WHICH_CPUS); + ksft_test_result(rc == 0 && CPU_COUNT(&cpus) == 0, "clear all cpus\n"); + + ksft_finished(); +} diff --git a/tools/testing/selftests/riscv/mm/mmap_test.h b/tools/testing/selftests/riscv/mm/mmap_test.h index 9b8434f62f57..2e0db9c5be6c 100644 --- a/tools/testing/selftests/riscv/mm/mmap_test.h +++ b/tools/testing/selftests/riscv/mm/mmap_test.h @@ -18,6 +18,8 @@ struct addresses { int *on_56_addr; }; +// Only works on 64 bit +#if __riscv_xlen == 64 static inline void do_mmaps(struct addresses *mmap_addresses) { /* @@ -50,6 +52,7 @@ static inline void do_mmaps(struct addresses *mmap_addresses) mmap_addresses->on_56_addr = mmap(on_56_bits, 5 * sizeof(int), prot, flags, 0, 0); } +#endif /* __riscv_xlen == 64 */ static inline int memory_layout(void) { diff --git a/tools/testing/selftests/riscv/vector/v_initval_nolibc.c b/tools/testing/selftests/riscv/vector/v_initval_nolibc.c index 66764edb0d52..1dd94197da30 100644 --- a/tools/testing/selftests/riscv/vector/v_initval_nolibc.c +++ b/tools/testing/selftests/riscv/vector/v_initval_nolibc.c @@ -27,7 +27,7 @@ int main(void) datap = malloc(MAX_VSIZE); if (!datap) { - ksft_test_result_fail("fail to allocate memory for size = %lu\n", MAX_VSIZE); + ksft_test_result_fail("fail to allocate memory for size = %d\n", MAX_VSIZE); exit(-1); } diff --git a/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c b/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c index 2c0d2b1126c1..1f9969bed235 100644 --- a/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c +++ b/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c @@ -1,4 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only + +#include <linux/wait.h> + #define THIS_PROGRAM "./vstate_exec_nolibc" int main(int argc, char **argv) diff --git a/tools/testing/selftests/riscv/vector/vstate_prctl.c b/tools/testing/selftests/riscv/vector/vstate_prctl.c index b348b475be57..27668fb3b6d0 100644 --- a/tools/testing/selftests/riscv/vector/vstate_prctl.c +++ b/tools/testing/selftests/riscv/vector/vstate_prctl.c @@ -1,20 +1,12 @@ // SPDX-License-Identifier: GPL-2.0-only #include <sys/prctl.h> #include <unistd.h> -#include <asm/hwprobe.h> #include <errno.h> #include <sys/wait.h> +#include "../hwprobe/hwprobe.h" #include "../../kselftest.h" -/* - * Rather than relying on having a new enough libc to define this, just do it - * ourselves. This way we don't need to be coupled to a new-enough libc to - * contain the call. - */ -long riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count, - size_t cpu_count, unsigned long *cpus, unsigned int flags); - #define NEXT_PROGRAM "./vstate_exec_nolibc" static int launch_test(int test_inherit) { @@ -68,7 +60,7 @@ int test_and_compare_child(long provided, long expected, int inherit) } rc = launch_test(inherit); if (rc != expected) { - ksft_test_result_fail("Test failed, check %d != %d\n", rc, + ksft_test_result_fail("Test failed, check %d != %ld\n", rc, expected); return -2; } @@ -87,7 +79,7 @@ int main(void) pair.key = RISCV_HWPROBE_KEY_IMA_EXT_0; rc = riscv_hwprobe(&pair, 1, 0, NULL, 0); if (rc < 0) { - ksft_test_result_fail("hwprobe() failed with %d\n", rc); + ksft_test_result_fail("hwprobe() failed with %ld\n", rc); return -1; } diff --git a/tools/testing/selftests/rseq/basic_percpu_ops_test.c b/tools/testing/selftests/rseq/basic_percpu_ops_test.c index 887542961968..2348d2c20d0a 100644 --- a/tools/testing/selftests/rseq/basic_percpu_ops_test.c +++ b/tools/testing/selftests/rseq/basic_percpu_ops_test.c @@ -24,6 +24,11 @@ bool rseq_validate_cpu_id(void) { return rseq_mm_cid_available(); } +static +bool rseq_use_cpu_index(void) +{ + return false; /* Use mm_cid */ +} #else # define RSEQ_PERCPU RSEQ_PERCPU_CPU_ID static @@ -36,6 +41,11 @@ bool rseq_validate_cpu_id(void) { return rseq_current_cpu_raw() >= 0; } +static +bool rseq_use_cpu_index(void) +{ + return true; /* Use cpu_id as index. */ +} #endif struct percpu_lock_entry { @@ -274,7 +284,7 @@ void test_percpu_list(void) /* Generate list entries for every usable cpu. */ sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus); for (i = 0; i < CPU_SETSIZE; i++) { - if (!CPU_ISSET(i, &allowed_cpus)) + if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus)) continue; for (j = 1; j <= 100; j++) { struct percpu_list_node *node; @@ -299,7 +309,7 @@ void test_percpu_list(void) for (i = 0; i < CPU_SETSIZE; i++) { struct percpu_list_node *node; - if (!CPU_ISSET(i, &allowed_cpus)) + if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus)) continue; while ((node = __percpu_list_pop(&list, i))) { diff --git a/tools/testing/selftests/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c index 20403d58345c..2f37961240ca 100644 --- a/tools/testing/selftests/rseq/param_test.c +++ b/tools/testing/selftests/rseq/param_test.c @@ -288,6 +288,11 @@ bool rseq_validate_cpu_id(void) { return rseq_mm_cid_available(); } +static +bool rseq_use_cpu_index(void) +{ + return false; /* Use mm_cid */ +} # ifdef TEST_MEMBARRIER /* * Membarrier does not currently support targeting a mm_cid, so @@ -312,6 +317,11 @@ bool rseq_validate_cpu_id(void) { return rseq_current_cpu_raw() >= 0; } +static +bool rseq_use_cpu_index(void) +{ + return true; /* Use cpu_id as index. */ +} # ifdef TEST_MEMBARRIER static int rseq_membarrier_expedited(int cpu) @@ -715,7 +725,7 @@ void test_percpu_list(void) /* Generate list entries for every usable cpu. */ sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus); for (i = 0; i < CPU_SETSIZE; i++) { - if (!CPU_ISSET(i, &allowed_cpus)) + if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus)) continue; for (j = 1; j <= 100; j++) { struct percpu_list_node *node; @@ -752,7 +762,7 @@ void test_percpu_list(void) for (i = 0; i < CPU_SETSIZE; i++) { struct percpu_list_node *node; - if (!CPU_ISSET(i, &allowed_cpus)) + if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus)) continue; while ((node = __percpu_list_pop(&list, i))) { @@ -902,7 +912,7 @@ void test_percpu_buffer(void) /* Generate list entries for every usable cpu. */ sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus); for (i = 0; i < CPU_SETSIZE; i++) { - if (!CPU_ISSET(i, &allowed_cpus)) + if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus)) continue; /* Worse-case is every item in same CPU. */ buffer.c[i].array = @@ -952,7 +962,7 @@ void test_percpu_buffer(void) for (i = 0; i < CPU_SETSIZE; i++) { struct percpu_buffer_node *node; - if (!CPU_ISSET(i, &allowed_cpus)) + if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus)) continue; while ((node = __percpu_buffer_pop(&buffer, i))) { @@ -1113,7 +1123,7 @@ void test_percpu_memcpy_buffer(void) /* Generate list entries for every usable cpu. */ sched_getaffinity(0, sizeof(allowed_cpus), &allowed_cpus); for (i = 0; i < CPU_SETSIZE; i++) { - if (!CPU_ISSET(i, &allowed_cpus)) + if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus)) continue; /* Worse-case is every item in same CPU. */ buffer.c[i].array = @@ -1160,7 +1170,7 @@ void test_percpu_memcpy_buffer(void) for (i = 0; i < CPU_SETSIZE; i++) { struct percpu_memcpy_buffer_node item; - if (!CPU_ISSET(i, &allowed_cpus)) + if (rseq_use_cpu_index() && !CPU_ISSET(i, &allowed_cpus)) continue; while (__percpu_memcpy_buffer_pop(&buffer, &item, i)) { diff --git a/tools/testing/selftests/seccomp/seccomp_benchmark.c b/tools/testing/selftests/seccomp/seccomp_benchmark.c index 5b5c9d558dee..97b86980b768 100644 --- a/tools/testing/selftests/seccomp/seccomp_benchmark.c +++ b/tools/testing/selftests/seccomp/seccomp_benchmark.c @@ -38,10 +38,10 @@ unsigned long long timing(clockid_t clk_id, unsigned long long samples) i *= 1000000000ULL; i += finish.tv_nsec - start.tv_nsec; - printf("%lu.%09lu - %lu.%09lu = %llu (%.1fs)\n", - finish.tv_sec, finish.tv_nsec, - start.tv_sec, start.tv_nsec, - i, (double)i / 1000000000.0); + ksft_print_msg("%lu.%09lu - %lu.%09lu = %llu (%.1fs)\n", + finish.tv_sec, finish.tv_nsec, + start.tv_sec, start.tv_nsec, + i, (double)i / 1000000000.0); return i; } @@ -53,7 +53,7 @@ unsigned long long calibrate(void) pid_t pid, ret; int seconds = 15; - printf("Calibrating sample size for %d seconds worth of syscalls ...\n", seconds); + ksft_print_msg("Calibrating sample size for %d seconds worth of syscalls ...\n", seconds); samples = 0; pid = getpid(); @@ -98,24 +98,36 @@ bool le(int i_one, int i_two) } long compare(const char *name_one, const char *name_eval, const char *name_two, - unsigned long long one, bool (*eval)(int, int), unsigned long long two) + unsigned long long one, bool (*eval)(int, int), unsigned long long two, + bool skip) { bool good; - printf("\t%s %s %s (%lld %s %lld): ", name_one, name_eval, name_two, - (long long)one, name_eval, (long long)two); + if (skip) { + ksft_test_result_skip("%s %s %s\n", name_one, name_eval, + name_two); + return 0; + } + + ksft_print_msg("\t%s %s %s (%lld %s %lld): ", name_one, name_eval, name_two, + (long long)one, name_eval, (long long)two); if (one > INT_MAX) { - printf("Miscalculation! Measurement went negative: %lld\n", (long long)one); - return 1; + ksft_print_msg("Miscalculation! Measurement went negative: %lld\n", (long long)one); + good = false; + goto out; } if (two > INT_MAX) { - printf("Miscalculation! Measurement went negative: %lld\n", (long long)two); - return 1; + ksft_print_msg("Miscalculation! Measurement went negative: %lld\n", (long long)two); + good = false; + goto out; } good = eval(one, two); printf("%s\n", good ? "✔️" : "❌"); +out: + ksft_test_result(good, "%s %s %s\n", name_one, name_eval, name_two); + return good ? 0 : 1; } @@ -142,15 +154,22 @@ int main(int argc, char *argv[]) unsigned long long samples, calc; unsigned long long native, filter1, filter2, bitmap1, bitmap2; unsigned long long entry, per_filter1, per_filter2; + bool skip = false; setbuf(stdout, NULL); - printf("Running on:\n"); + ksft_print_header(); + ksft_set_plan(7); + + ksft_print_msg("Running on:\n"); + ksft_print_msg(""); system("uname -a"); - printf("Current BPF sysctl settings:\n"); + ksft_print_msg("Current BPF sysctl settings:\n"); /* Avoid using "sysctl" which may not be installed. */ + ksft_print_msg(""); system("grep -H . /proc/sys/net/core/bpf_jit_enable"); + ksft_print_msg(""); system("grep -H . /proc/sys/net/core/bpf_jit_harden"); if (argc > 1) @@ -158,11 +177,11 @@ int main(int argc, char *argv[]) else samples = calibrate(); - printf("Benchmarking %llu syscalls...\n", samples); + ksft_print_msg("Benchmarking %llu syscalls...\n", samples); /* Native call */ native = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples; - printf("getpid native: %llu ns\n", native); + ksft_print_msg("getpid native: %llu ns\n", native); ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); assert(ret == 0); @@ -172,35 +191,37 @@ int main(int argc, char *argv[]) assert(ret == 0); bitmap1 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples; - printf("getpid RET_ALLOW 1 filter (bitmap): %llu ns\n", bitmap1); + ksft_print_msg("getpid RET_ALLOW 1 filter (bitmap): %llu ns\n", bitmap1); /* Second filter resulting in a bitmap */ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &bitmap_prog); assert(ret == 0); bitmap2 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples; - printf("getpid RET_ALLOW 2 filters (bitmap): %llu ns\n", bitmap2); + ksft_print_msg("getpid RET_ALLOW 2 filters (bitmap): %llu ns\n", bitmap2); /* Third filter, can no longer be converted to bitmap */ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog); assert(ret == 0); filter1 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples; - printf("getpid RET_ALLOW 3 filters (full): %llu ns\n", filter1); + ksft_print_msg("getpid RET_ALLOW 3 filters (full): %llu ns\n", filter1); /* Fourth filter, can not be converted to bitmap because of filter 3 */ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &bitmap_prog); assert(ret == 0); filter2 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples; - printf("getpid RET_ALLOW 4 filters (full): %llu ns\n", filter2); + ksft_print_msg("getpid RET_ALLOW 4 filters (full): %llu ns\n", filter2); /* Estimations */ #define ESTIMATE(fmt, var, what) do { \ var = (what); \ - printf("Estimated " fmt ": %llu ns\n", var); \ - if (var > INT_MAX) \ - goto more_samples; \ + ksft_print_msg("Estimated " fmt ": %llu ns\n", var); \ + if (var > INT_MAX) { \ + skip = true; \ + ret |= 1; \ + } \ } while (0) ESTIMATE("total seccomp overhead for 1 bitmapped filter", calc, @@ -218,31 +239,34 @@ int main(int argc, char *argv[]) ESTIMATE("seccomp per-filter overhead (filters / 4)", per_filter2, (filter2 - native - entry) / 4); - printf("Expectations:\n"); - ret |= compare("native", "≤", "1 bitmap", native, le, bitmap1); - bits = compare("native", "≤", "1 filter", native, le, filter1); + ksft_print_msg("Expectations:\n"); + ret |= compare("native", "≤", "1 bitmap", native, le, bitmap1, + skip); + bits = compare("native", "≤", "1 filter", native, le, filter1, + skip); if (bits) - goto more_samples; + skip = true; ret |= compare("per-filter (last 2 diff)", "≈", "per-filter (filters / 4)", - per_filter1, approx, per_filter2); + per_filter1, approx, per_filter2, skip); bits = compare("1 bitmapped", "≈", "2 bitmapped", - bitmap1 - native, approx, bitmap2 - native); + bitmap1 - native, approx, bitmap2 - native, skip); if (bits) { - printf("Skipping constant action bitmap expectations: they appear unsupported.\n"); - goto out; + ksft_print_msg("Skipping constant action bitmap expectations: they appear unsupported.\n"); + skip = true; } - ret |= compare("entry", "≈", "1 bitmapped", entry, approx, bitmap1 - native); - ret |= compare("entry", "≈", "2 bitmapped", entry, approx, bitmap2 - native); + ret |= compare("entry", "≈", "1 bitmapped", entry, approx, + bitmap1 - native, skip); + ret |= compare("entry", "≈", "2 bitmapped", entry, approx, + bitmap2 - native, skip); ret |= compare("native + entry + (per filter * 4)", "≈", "4 filters total", - entry + (per_filter1 * 4) + native, approx, filter2); - if (ret == 0) - goto out; + entry + (per_filter1 * 4) + native, approx, filter2, + skip); -more_samples: - printf("Saw unexpected benchmark result. Try running again with more samples?\n"); -out: - return 0; + if (ret) + ksft_print_msg("Saw unexpected benchmark result. Try running again with more samples?\n"); + + ksft_finished(); } diff --git a/tools/testing/selftests/sgx/Makefile b/tools/testing/selftests/sgx/Makefile index 50aab6b57da3..867f88ce2570 100644 --- a/tools/testing/selftests/sgx/Makefile +++ b/tools/testing/selftests/sgx/Makefile @@ -12,14 +12,16 @@ OBJCOPY := $(CROSS_COMPILE)objcopy endif INCLUDES := -I$(top_srcdir)/tools/include -HOST_CFLAGS := -Wall -Werror -g $(INCLUDES) -fPIC -z noexecstack -ENCL_CFLAGS := -Wall -Werror -static -nostdlib -nostartfiles -fPIC \ +HOST_CFLAGS := -Wall -Werror -g $(INCLUDES) -fPIC +HOST_LDFLAGS := -z noexecstack -lcrypto +ENCL_CFLAGS += -Wall -Werror -static-pie -nostdlib -ffreestanding -fPIE \ -fno-stack-protector -mrdrnd $(INCLUDES) +ENCL_LDFLAGS := -Wl,-T,test_encl.lds,--build-id=none +ifeq ($(CAN_BUILD_X86_64), 1) TEST_CUSTOM_PROGS := $(OUTPUT)/test_sgx TEST_FILES := $(OUTPUT)/test_encl.elf -ifeq ($(CAN_BUILD_X86_64), 1) all: $(TEST_CUSTOM_PROGS) $(OUTPUT)/test_encl.elf endif @@ -28,7 +30,7 @@ $(OUTPUT)/test_sgx: $(OUTPUT)/main.o \ $(OUTPUT)/sigstruct.o \ $(OUTPUT)/call.o \ $(OUTPUT)/sign_key.o - $(CC) $(HOST_CFLAGS) -o $@ $^ -lcrypto + $(CC) $(HOST_CFLAGS) -o $@ $^ $(HOST_LDFLAGS) $(OUTPUT)/main.o: main.c $(CC) $(HOST_CFLAGS) -c $< -o $@ @@ -45,8 +47,8 @@ $(OUTPUT)/call.o: call.S $(OUTPUT)/sign_key.o: sign_key.S $(CC) $(HOST_CFLAGS) -c $< -o $@ -$(OUTPUT)/test_encl.elf: test_encl.lds test_encl.c test_encl_bootstrap.S - $(CC) $(ENCL_CFLAGS) -T $^ -o $@ -Wl,--build-id=none +$(OUTPUT)/test_encl.elf: test_encl.c test_encl_bootstrap.S + $(CC) $(ENCL_CFLAGS) $^ -o $@ $(ENCL_LDFLAGS) EXTRA_CLEAN := \ $(OUTPUT)/test_encl.elf \ diff --git a/tools/testing/selftests/sgx/defines.h b/tools/testing/selftests/sgx/defines.h index d8587c971941..402f8787a71c 100644 --- a/tools/testing/selftests/sgx/defines.h +++ b/tools/testing/selftests/sgx/defines.h @@ -13,6 +13,8 @@ #define __aligned(x) __attribute__((__aligned__(x))) #define __packed __attribute__((packed)) +#define __used __attribute__((used)) +#define __section(x)__attribute__((__section__(x))) #include "../../../../arch/x86/include/asm/sgx.h" #include "../../../../arch/x86/include/asm/enclu.h" diff --git a/tools/testing/selftests/sgx/load.c b/tools/testing/selftests/sgx/load.c index 94bdeac1cf04..c9f658e44de6 100644 --- a/tools/testing/selftests/sgx/load.c +++ b/tools/testing/selftests/sgx/load.c @@ -136,11 +136,11 @@ static bool encl_ioc_add_pages(struct encl *encl, struct encl_segment *seg) */ uint64_t encl_get_entry(struct encl *encl, const char *symbol) { + Elf64_Sym *symtab = NULL; + char *sym_names = NULL; Elf64_Shdr *sections; - Elf64_Sym *symtab; Elf64_Ehdr *ehdr; - char *sym_names; - int num_sym; + int num_sym = 0; int i; ehdr = encl->bin; @@ -161,6 +161,9 @@ uint64_t encl_get_entry(struct encl *encl, const char *symbol) } } + if (!symtab || !sym_names) + return 0; + for (i = 0; i < num_sym; i++) { Elf64_Sym *sym = &symtab[i]; diff --git a/tools/testing/selftests/sgx/sigstruct.c b/tools/testing/selftests/sgx/sigstruct.c index a07896a46364..d73b29becf5b 100644 --- a/tools/testing/selftests/sgx/sigstruct.c +++ b/tools/testing/selftests/sgx/sigstruct.c @@ -318,9 +318,9 @@ bool encl_measure(struct encl *encl) struct sgx_sigstruct *sigstruct = &encl->sigstruct; struct sgx_sigstruct_payload payload; uint8_t digest[SHA256_DIGEST_LENGTH]; + EVP_MD_CTX *ctx = NULL; unsigned int siglen; RSA *key = NULL; - EVP_MD_CTX *ctx; int i; memset(sigstruct, 0, sizeof(*sigstruct)); @@ -384,7 +384,8 @@ bool encl_measure(struct encl *encl) return true; err: - EVP_MD_CTX_destroy(ctx); + if (ctx) + EVP_MD_CTX_destroy(ctx); RSA_free(key); return false; } diff --git a/tools/testing/selftests/sgx/test_encl.c b/tools/testing/selftests/sgx/test_encl.c index c0d6397295e3..2c4d709cce2d 100644 --- a/tools/testing/selftests/sgx/test_encl.c +++ b/tools/testing/selftests/sgx/test_encl.c @@ -5,11 +5,12 @@ #include "defines.h" /* - * Data buffer spanning two pages that will be placed first in .data - * segment. Even if not used internally the second page is needed by - * external test manipulating page permissions. + * Data buffer spanning two pages that will be placed first in the .data + * segment via the linker script. Even if not used internally the second page + * is needed by external test manipulating page permissions, so mark + * encl_buffer as "used" to make sure it is entirely preserved by the compiler. */ -static uint8_t encl_buffer[8192] = { 1 }; +static uint8_t __used __section(".data.encl_buffer") encl_buffer[8192] = { 1 }; enum sgx_enclu_function { EACCEPT = 0x5, @@ -24,10 +25,11 @@ static void do_encl_emodpe(void *_op) secinfo.flags = op->flags; asm volatile(".byte 0x0f, 0x01, 0xd7" - : + : /* no outputs */ : "a" (EMODPE), "b" (&secinfo), - "c" (op->epc_addr)); + "c" (op->epc_addr) + : "memory" /* read from secinfo pointer */); } static void do_encl_eaccept(void *_op) @@ -42,7 +44,8 @@ static void do_encl_eaccept(void *_op) : "=a" (rax) : "a" (EACCEPT), "b" (&secinfo), - "c" (op->epc_addr)); + "c" (op->epc_addr) + : "memory" /* read from secinfo pointer */); op->ret = rax; } @@ -119,21 +122,41 @@ static void do_encl_op_nop(void *_op) } +/* + * Symbol placed at the start of the enclave image by the linker script. + * Declare this extern symbol with visibility "hidden" to ensure the compiler + * does not access it through the GOT and generates position-independent + * addressing as __encl_base(%rip), so we can get the actual enclave base + * during runtime. + */ +extern const uint8_t __attribute__((visibility("hidden"))) __encl_base; + +typedef void (*encl_op_t)(void *); +static const encl_op_t encl_op_array[ENCL_OP_MAX] = { + do_encl_op_put_to_buf, + do_encl_op_get_from_buf, + do_encl_op_put_to_addr, + do_encl_op_get_from_addr, + do_encl_op_nop, + do_encl_eaccept, + do_encl_emodpe, + do_encl_init_tcs_page, +}; + void encl_body(void *rdi, void *rsi) { - const void (*encl_op_array[ENCL_OP_MAX])(void *) = { - do_encl_op_put_to_buf, - do_encl_op_get_from_buf, - do_encl_op_put_to_addr, - do_encl_op_get_from_addr, - do_encl_op_nop, - do_encl_eaccept, - do_encl_emodpe, - do_encl_init_tcs_page, - }; - - struct encl_op_header *op = (struct encl_op_header *)rdi; - - if (op->type < ENCL_OP_MAX) - (*encl_op_array[op->type])(op); + struct encl_op_header *header = (struct encl_op_header *)rdi; + encl_op_t op; + + if (header->type >= ENCL_OP_MAX) + return; + + /* + * The enclave base address needs to be added, as this call site + * *cannot be* made rip-relative by the compiler, or fixed up by + * any other possible means. + */ + op = ((uint64_t)&__encl_base) + encl_op_array[header->type]; + + (*op)(header); } diff --git a/tools/testing/selftests/sgx/test_encl.lds b/tools/testing/selftests/sgx/test_encl.lds index a1ec64f7d91f..ffe851a1cac4 100644 --- a/tools/testing/selftests/sgx/test_encl.lds +++ b/tools/testing/selftests/sgx/test_encl.lds @@ -10,6 +10,7 @@ PHDRS SECTIONS { . = 0; + __encl_base = .; .tcs : { *(.tcs*) } : tcs @@ -23,6 +24,7 @@ SECTIONS } : text .data : { + *(.data.encl_buffer) *(.data*) } : data @@ -31,11 +33,9 @@ SECTIONS *(.note*) *(.debug*) *(.eh_frame*) + *(.dyn*) + *(.gnu.hash) } } -ASSERT(!DEFINED(.altinstructions), "ALTERNATIVES are not supported in enclaves") -ASSERT(!DEFINED(.altinstr_replacement), "ALTERNATIVES are not supported in enclaves") -ASSERT(!DEFINED(.discard.retpoline_safe), "RETPOLINE ALTERNATIVES are not supported in enclaves") -ASSERT(!DEFINED(.discard.nospec), "RETPOLINE ALTERNATIVES are not supported in enclaves") -ASSERT(!DEFINED(.got.plt), "Libcalls are not supported in enclaves") +ASSERT(!DEFINED(_GLOBAL_OFFSET_TABLE_), "Libcalls through GOT are not supported in enclaves") diff --git a/tools/testing/selftests/sgx/test_encl_bootstrap.S b/tools/testing/selftests/sgx/test_encl_bootstrap.S index 03ae0f57e29d..d8c4ac94e032 100644 --- a/tools/testing/selftests/sgx/test_encl_bootstrap.S +++ b/tools/testing/selftests/sgx/test_encl_bootstrap.S @@ -42,9 +42,12 @@ encl_entry: # RBX contains the base address for TCS, which is the first address # inside the enclave for TCS #1 and one page into the enclave for - # TCS #2. By adding the value of encl_stack to it, we get - # the absolute address for the stack. - lea (encl_stack)(%rbx), %rax + # TCS #2. First make it relative by substracting __encl_base and + # then add the address of encl_stack to get the address for the stack. + lea __encl_base(%rip), %rax + sub %rax, %rbx + lea encl_stack(%rip), %rax + add %rbx, %rax jmp encl_entry_core encl_dyn_entry: # Entry point for dynamically created TCS page expected to follow @@ -55,25 +58,12 @@ encl_entry_core: push %rax push %rcx # push the address after EENTER - push %rbx # push the enclave base address + # NOTE: as the selftest enclave is *not* intended for production, + # simplify the code by not initializing ABI registers on entry or + # cleansing caller-save registers on exit. call encl_body - pop %rbx # pop the enclave base address - - /* Clear volatile GPRs, except RAX (EEXIT function). */ - xor %rcx, %rcx - xor %rdx, %rdx - xor %rdi, %rdi - xor %rsi, %rsi - xor %r8, %r8 - xor %r9, %r9 - xor %r10, %r10 - xor %r11, %r11 - - # Reset status flags. - add %rdx, %rdx # OF = SF = AF = CF = 0; ZF = PF = 1 - # Prepare EEXIT target by popping the address of the instruction after # EENTER to RBX. pop %rbx |