From 45b69848a2fea11c03f3a54241416e36eb94e38c Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Sat, 23 Jul 2022 17:22:47 +0200 Subject: [PATCH 01/24] x86/speculation: Make all RETbleed mitigations 64-bit only commit b648ab487f31bc4c38941bc770ea97fe394304bb upstream. The mitigations for RETBleed are currently ineffective on x86_32 since entry_32.S does not use the required macros. However, for an x86_32 target, the kconfig symbols for them are still enabled by default and /sys/devices/system/cpu/vulnerabilities/retbleed will wrongly report that mitigations are in place. Make all of these symbols depend on X86_64, and only enable RETHUNK by default on X86_64. Fixes: f43b9876e857 ("x86/retbleed: Add fine grained Kconfig knobs") Signed-off-by: Ben Hutchings Signed-off-by: Borislav Petkov Cc: Link: https://lore.kernel.org/r/YtwSR3NNsWp1ohfV@decadent.org.uk [bwh: Backported to 5.10/5.15/5.18: adjust context] Signed-off-by: Ben Hutchings Signed-off-by: Greg Kroah-Hartman --- arch/x86/Kconfig | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 16c045906b2a..159646da3c6b 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2447,7 +2447,7 @@ config RETPOLINE config RETHUNK bool "Enable return-thunks" depends on RETPOLINE && CC_HAS_RETURN_THUNK - default y + default y if X86_64 help Compile the kernel with the return-thunks compiler option to guard against kernel-to-user data leaks by avoiding return speculation. @@ -2456,21 +2456,21 @@ config RETHUNK config CPU_UNRET_ENTRY bool "Enable UNRET on kernel entry" - depends on CPU_SUP_AMD && RETHUNK + depends on CPU_SUP_AMD && RETHUNK && X86_64 default y help Compile the kernel with support for the retbleed=unret mitigation. config CPU_IBPB_ENTRY bool "Enable IBPB on kernel entry" - depends on CPU_SUP_AMD + depends on CPU_SUP_AMD && X86_64 default y help Compile the kernel with support for the retbleed=ibpb mitigation. config CPU_IBRS_ENTRY bool "Enable IBRS on kernel entry" - depends on CPU_SUP_INTEL + depends on CPU_SUP_INTEL && X86_64 default y help Compile the kernel with support for the spectre_v2=ibrs mitigation. From 4f3b852336602ee37876494077efb3f23afd5ba3 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Mon, 1 Aug 2022 18:59:07 +0300 Subject: [PATCH 02/24] ath9k_htc: fix NULL pointer dereference at ath9k_htc_rxep() commit b0ec7e55fce65f125bd1d7f02e2dc4de62abee34 upstream. syzbot is reporting lockdep warning followed by kernel panic at ath9k_htc_rxep() [1], for ath9k_htc_rxep() depends on ath9k_rx_init() being already completed. Since ath9k_htc_rxep() is set by ath9k_htc_connect_svc(WMI_BEACON_SVC) from ath9k_init_htc_services(), it is possible that ath9k_htc_rxep() is called via timer interrupt before ath9k_rx_init() from ath9k_init_device() is called. Since we can't call ath9k_init_device() before ath9k_init_htc_services(), let's hold ath9k_htc_rxep() no-op until ath9k_rx_init() completes. Link: https://syzkaller.appspot.com/bug?extid=4d2d56175b934b9a7bf9 [1] Reported-by: syzbot Signed-off-by: Tetsuo Handa Tested-by: syzbot Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/2b88f416-b2cb-7a18-d688-951e6dc3fe92@i-love.sakura.ne.jp Signed-off-by: Fedor Pchelkin Signed-off-by: Greg Kroah-Hartman --- drivers/net/wireless/ath/ath9k/htc.h | 1 + drivers/net/wireless/ath/ath9k/htc_drv_txrx.c | 8 ++++++++ 2 files changed, 9 insertions(+) diff --git a/drivers/net/wireless/ath/ath9k/htc.h b/drivers/net/wireless/ath/ath9k/htc.h index 0a1634238e67..4f71e962279a 100644 --- a/drivers/net/wireless/ath/ath9k/htc.h +++ b/drivers/net/wireless/ath/ath9k/htc.h @@ -281,6 +281,7 @@ struct ath9k_htc_rxbuf { struct ath9k_htc_rx { struct list_head rxbuf; spinlock_t rxbuflock; + bool initialized; }; #define ATH9K_HTC_TX_CLEANUP_INTERVAL 50 /* ms */ diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c index 30ddf333e04d..592034ea4b68 100644 --- a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c +++ b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c @@ -1133,6 +1133,10 @@ void ath9k_htc_rxep(void *drv_priv, struct sk_buff *skb, struct ath9k_htc_rxbuf *rxbuf = NULL, *tmp_buf = NULL; unsigned long flags; + /* Check if ath9k_rx_init() completed. */ + if (!data_race(priv->rx.initialized)) + goto err; + spin_lock_irqsave(&priv->rx.rxbuflock, flags); list_for_each_entry(tmp_buf, &priv->rx.rxbuf, list) { if (!tmp_buf->in_process) { @@ -1188,6 +1192,10 @@ int ath9k_rx_init(struct ath9k_htc_priv *priv) list_add_tail(&rxbuf->list, &priv->rx.rxbuf); } + /* Allow ath9k_htc_rxep() to operate. */ + smp_wmb(); + priv->rx.initialized = true; + return 0; err: From 78c8397132dd4735ac6a7b5a651302f0b9f264ad Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Mon, 1 Aug 2022 18:59:08 +0300 Subject: [PATCH 03/24] ath9k_htc: fix NULL pointer dereference at ath9k_htc_tx_get_packet() commit 8b3046abc99eefe11438090bcc4ec3a3994b55d0 upstream. syzbot is reporting lockdep warning at ath9k_wmi_event_tasklet() followed by kernel panic at get_htc_epid_queue() from ath9k_htc_tx_get_packet() from ath9k_htc_txstatus() [1], for ath9k_wmi_event_tasklet(WMI_TXSTATUS_EVENTID) depends on spin_lock_init() from ath9k_init_priv() being already completed. Since ath9k_wmi_event_tasklet() is set by ath9k_init_wmi() from ath9k_htc_probe_device(), it is possible that ath9k_wmi_event_tasklet() is called via tasklet interrupt before spin_lock_init() from ath9k_init_priv() from ath9k_init_device() from ath9k_htc_probe_device() is called. Let's hold ath9k_wmi_event_tasklet(WMI_TXSTATUS_EVENTID) no-op until ath9k_tx_init() completes. Link: https://syzkaller.appspot.com/bug?extid=31d54c60c5b254d6f75b [1] Reported-by: syzbot Signed-off-by: Tetsuo Handa Tested-by: syzbot Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/77b76ac8-2bee-6444-d26c-8c30858b8daa@i-love.sakura.ne.jp Signed-off-by: Fedor Pchelkin Signed-off-by: Greg Kroah-Hartman --- drivers/net/wireless/ath/ath9k/htc.h | 1 + drivers/net/wireless/ath/ath9k/htc_drv_txrx.c | 5 +++++ drivers/net/wireless/ath/ath9k/wmi.c | 4 ++++ 3 files changed, 10 insertions(+) diff --git a/drivers/net/wireless/ath/ath9k/htc.h b/drivers/net/wireless/ath/ath9k/htc.h index 4f71e962279a..6b45e63fae4b 100644 --- a/drivers/net/wireless/ath/ath9k/htc.h +++ b/drivers/net/wireless/ath/ath9k/htc.h @@ -306,6 +306,7 @@ struct ath9k_htc_tx { DECLARE_BITMAP(tx_slot, MAX_TX_BUF_NUM); struct timer_list cleanup_timer; spinlock_t tx_lock; + bool initialized; }; struct ath9k_htc_tx_ctl { diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c index 592034ea4b68..43a743ec9d9e 100644 --- a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c +++ b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c @@ -808,6 +808,11 @@ int ath9k_tx_init(struct ath9k_htc_priv *priv) skb_queue_head_init(&priv->tx.data_vi_queue); skb_queue_head_init(&priv->tx.data_vo_queue); skb_queue_head_init(&priv->tx.tx_failed); + + /* Allow ath9k_wmi_event_tasklet(WMI_TXSTATUS_EVENTID) to operate. */ + smp_wmb(); + priv->tx.initialized = true; + return 0; } diff --git a/drivers/net/wireless/ath/ath9k/wmi.c b/drivers/net/wireless/ath/ath9k/wmi.c index fe29ad4b9023..f315c54bd3ac 100644 --- a/drivers/net/wireless/ath/ath9k/wmi.c +++ b/drivers/net/wireless/ath/ath9k/wmi.c @@ -169,6 +169,10 @@ void ath9k_wmi_event_tasklet(struct tasklet_struct *t) &wmi->drv_priv->fatal_work); break; case WMI_TXSTATUS_EVENTID: + /* Check if ath9k_tx_init() completed. */ + if (!data_race(priv->tx.initialized)) + break; + spin_lock_bh(&priv->tx.tx_lock); if (priv->tx.flags & ATH9K_HTC_OP_TX_DRAIN) { spin_unlock_bh(&priv->tx.tx_lock); From 042fb1c281f357d58308366b5e2ddd8e5f1ad384 Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Mon, 1 Aug 2022 17:57:02 +0300 Subject: [PATCH 04/24] selftests/bpf: Extend verifier and bpf_sock tests for dst_port loads commit 8f50f16ff39dd4e2d43d1548ca66925652f8aff7 upstream. Add coverage to the verifier tests and tests for reading bpf_sock fields to ensure that 32-bit, 16-bit, and 8-bit loads from dst_port field are allowed only at intended offsets and produce expected values. While 16-bit and 8-bit access to dst_port field is straight-forward, 32-bit wide loads need be allowed and produce a zero-padded 16-bit value for backward compatibility. Signed-off-by: Jakub Sitnicki Link: https://lore.kernel.org/r/20220130115518.213259-3-jakub@cloudflare.com Signed-off-by: Alexei Starovoitov [OP: backport to 5.10: adjusted context in sock_fields.c] Signed-off-by: Ovidiu Panait Signed-off-by: Greg Kroah-Hartman --- tools/include/uapi/linux/bpf.h | 3 +- .../selftests/bpf/prog_tests/sock_fields.c | 60 +++++++++----- .../selftests/bpf/progs/test_sock_fields.c | 41 ++++++++++ tools/testing/selftests/bpf/verifier/sock.c | 81 ++++++++++++++++++- 4 files changed, 162 insertions(+), 23 deletions(-) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index b9ee2ded381a..7943e748916d 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4180,7 +4180,8 @@ struct bpf_sock { __u32 src_ip4; __u32 src_ip6[4]; __u32 src_port; /* host byte order */ - __u32 dst_port; /* network byte order */ + __be16 dst_port; /* network byte order */ + __u16 :16; /* zero padding */ __u32 dst_ip4; __u32 dst_ip6[4]; __u32 state; diff --git a/tools/testing/selftests/bpf/prog_tests/sock_fields.c b/tools/testing/selftests/bpf/prog_tests/sock_fields.c index af87118e748e..e8b5bf707cd4 100644 --- a/tools/testing/selftests/bpf/prog_tests/sock_fields.c +++ b/tools/testing/selftests/bpf/prog_tests/sock_fields.c @@ -1,9 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ +#define _GNU_SOURCE #include #include #include +#include #include #include #include @@ -21,6 +23,7 @@ enum bpf_linum_array_idx { EGRESS_LINUM_IDX, INGRESS_LINUM_IDX, + READ_SK_DST_PORT_LINUM_IDX, __NR_BPF_LINUM_ARRAY_IDX, }; @@ -43,8 +46,16 @@ static __u64 child_cg_id; static int linum_map_fd; static __u32 duration; -static __u32 egress_linum_idx = EGRESS_LINUM_IDX; -static __u32 ingress_linum_idx = INGRESS_LINUM_IDX; +static bool create_netns(void) +{ + if (!ASSERT_OK(unshare(CLONE_NEWNET), "create netns")) + return false; + + if (!ASSERT_OK(system("ip link set dev lo up"), "bring up lo")) + return false; + + return true; +} static void print_sk(const struct bpf_sock *sk, const char *prefix) { @@ -92,19 +103,24 @@ static void check_result(void) { struct bpf_tcp_sock srv_tp, cli_tp, listen_tp; struct bpf_sock srv_sk, cli_sk, listen_sk; - __u32 ingress_linum, egress_linum; + __u32 idx, ingress_linum, egress_linum, linum; int err; - err = bpf_map_lookup_elem(linum_map_fd, &egress_linum_idx, - &egress_linum); + idx = EGRESS_LINUM_IDX; + err = bpf_map_lookup_elem(linum_map_fd, &idx, &egress_linum); CHECK(err == -1, "bpf_map_lookup_elem(linum_map_fd)", "err:%d errno:%d\n", err, errno); - err = bpf_map_lookup_elem(linum_map_fd, &ingress_linum_idx, - &ingress_linum); + idx = INGRESS_LINUM_IDX; + err = bpf_map_lookup_elem(linum_map_fd, &idx, &ingress_linum); CHECK(err == -1, "bpf_map_lookup_elem(linum_map_fd)", "err:%d errno:%d\n", err, errno); + idx = READ_SK_DST_PORT_LINUM_IDX; + err = bpf_map_lookup_elem(linum_map_fd, &idx, &linum); + ASSERT_OK(err, "bpf_map_lookup_elem(linum_map_fd, READ_SK_DST_PORT_IDX)"); + ASSERT_EQ(linum, 0, "failure in read_sk_dst_port on line"); + memcpy(&srv_sk, &skel->bss->srv_sk, sizeof(srv_sk)); memcpy(&srv_tp, &skel->bss->srv_tp, sizeof(srv_tp)); memcpy(&cli_sk, &skel->bss->cli_sk, sizeof(cli_sk)); @@ -263,7 +279,7 @@ static void test(void) char buf[DATA_LEN]; /* Prepare listen_fd */ - listen_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0); + listen_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0xcafe, 0); /* start_server() has logged the error details */ if (CHECK_FAIL(listen_fd == -1)) goto done; @@ -331,8 +347,12 @@ static void test(void) void test_sock_fields(void) { - struct bpf_link *egress_link = NULL, *ingress_link = NULL; int parent_cg_fd = -1, child_cg_fd = -1; + struct bpf_link *link; + + /* Use a dedicated netns to have a fixed listen port */ + if (!create_netns()) + return; /* Create a cgroup, get fd, and join it */ parent_cg_fd = test__join_cgroup(PARENT_CGROUP); @@ -353,17 +373,20 @@ void test_sock_fields(void) if (CHECK(!skel, "test_sock_fields__open_and_load", "failed\n")) goto done; - egress_link = bpf_program__attach_cgroup(skel->progs.egress_read_sock_fields, - child_cg_fd); - if (CHECK(IS_ERR(egress_link), "attach_cgroup(egress)", "err:%ld\n", - PTR_ERR(egress_link))) + link = bpf_program__attach_cgroup(skel->progs.egress_read_sock_fields, child_cg_fd); + if (!ASSERT_OK_PTR(link, "attach_cgroup(egress_read_sock_fields)")) goto done; + skel->links.egress_read_sock_fields = link; - ingress_link = bpf_program__attach_cgroup(skel->progs.ingress_read_sock_fields, - child_cg_fd); - if (CHECK(IS_ERR(ingress_link), "attach_cgroup(ingress)", "err:%ld\n", - PTR_ERR(ingress_link))) + link = bpf_program__attach_cgroup(skel->progs.ingress_read_sock_fields, child_cg_fd); + if (!ASSERT_OK_PTR(link, "attach_cgroup(ingress_read_sock_fields)")) goto done; + skel->links.ingress_read_sock_fields = link; + + link = bpf_program__attach_cgroup(skel->progs.read_sk_dst_port, child_cg_fd); + if (!ASSERT_OK_PTR(link, "attach_cgroup(read_sk_dst_port")) + goto done; + skel->links.read_sk_dst_port = link; linum_map_fd = bpf_map__fd(skel->maps.linum_map); sk_pkt_out_cnt_fd = bpf_map__fd(skel->maps.sk_pkt_out_cnt); @@ -372,8 +395,7 @@ void test_sock_fields(void) test(); done: - bpf_link__destroy(egress_link); - bpf_link__destroy(ingress_link); + test_sock_fields__detach(skel); test_sock_fields__destroy(skel); if (child_cg_fd != -1) close(child_cg_fd); diff --git a/tools/testing/selftests/bpf/progs/test_sock_fields.c b/tools/testing/selftests/bpf/progs/test_sock_fields.c index 7967348b11af..3e2e3ee51cc9 100644 --- a/tools/testing/selftests/bpf/progs/test_sock_fields.c +++ b/tools/testing/selftests/bpf/progs/test_sock_fields.c @@ -12,6 +12,7 @@ enum bpf_linum_array_idx { EGRESS_LINUM_IDX, INGRESS_LINUM_IDX, + READ_SK_DST_PORT_LINUM_IDX, __NR_BPF_LINUM_ARRAY_IDX, }; @@ -250,4 +251,44 @@ int ingress_read_sock_fields(struct __sk_buff *skb) return CG_OK; } +static __noinline bool sk_dst_port__load_word(struct bpf_sock *sk) +{ + __u32 *word = (__u32 *)&sk->dst_port; + return word[0] == bpf_htonl(0xcafe0000); +} + +static __noinline bool sk_dst_port__load_half(struct bpf_sock *sk) +{ + __u16 *half = (__u16 *)&sk->dst_port; + return half[0] == bpf_htons(0xcafe); +} + +static __noinline bool sk_dst_port__load_byte(struct bpf_sock *sk) +{ + __u8 *byte = (__u8 *)&sk->dst_port; + return byte[0] == 0xca && byte[1] == 0xfe; +} + +SEC("cgroup_skb/egress") +int read_sk_dst_port(struct __sk_buff *skb) +{ + __u32 linum, linum_idx; + struct bpf_sock *sk; + + linum_idx = READ_SK_DST_PORT_LINUM_IDX; + + sk = skb->sk; + if (!sk) + RET_LOG(); + + if (!sk_dst_port__load_word(sk)) + RET_LOG(); + if (!sk_dst_port__load_half(sk)) + RET_LOG(); + if (!sk_dst_port__load_byte(sk)) + RET_LOG(); + + return CG_OK; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/verifier/sock.c b/tools/testing/selftests/bpf/verifier/sock.c index ce13ece08d51..8c224eac93df 100644 --- a/tools/testing/selftests/bpf/verifier/sock.c +++ b/tools/testing/selftests/bpf/verifier/sock.c @@ -121,7 +121,25 @@ .result = ACCEPT, }, { - "sk_fullsock(skb->sk): sk->dst_port [narrow load]", + "sk_fullsock(skb->sk): sk->dst_port [word load] (backward compatibility)", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_port)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = ACCEPT, +}, +{ + "sk_fullsock(skb->sk): sk->dst_port [half load]", .insns = { BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), @@ -139,7 +157,7 @@ .result = ACCEPT, }, { - "sk_fullsock(skb->sk): sk->dst_port [load 2nd byte]", + "sk_fullsock(skb->sk): sk->dst_port [half load] (invalid)", .insns = { BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), @@ -149,7 +167,64 @@ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), - BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_port) + 1), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_port) + 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = REJECT, + .errstr = "invalid sock access", +}, +{ + "sk_fullsock(skb->sk): sk->dst_port [byte load]", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_B, BPF_REG_2, BPF_REG_0, offsetof(struct bpf_sock, dst_port)), + BPF_LDX_MEM(BPF_B, BPF_REG_2, BPF_REG_0, offsetof(struct bpf_sock, dst_port) + 1), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = ACCEPT, +}, +{ + "sk_fullsock(skb->sk): sk->dst_port [byte load] (invalid)", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_port) + 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = REJECT, + .errstr = "invalid sock access", +}, +{ + "sk_fullsock(skb->sk): past sk->dst_port [half load] (invalid)", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_0, offsetofend(struct bpf_sock, dst_port)), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, From 1069087e2fb11f5fe61f68d83762cf01a25d8061 Mon Sep 17 00:00:00 2001 From: Jakub Sitnicki Date: Mon, 1 Aug 2022 17:57:03 +0300 Subject: [PATCH 05/24] selftests/bpf: Check dst_port only on the client socket commit 2d2202ba858c112b03f84d546e260c61425831a1 upstream. cgroup_skb/egress programs which sock_fields test installs process packets flying in both directions, from the client to the server, and in reverse direction. Recently added dst_port check relies on the fact that destination port (remote peer port) of the socket which sends the packet is known ahead of time. This holds true only for the client socket, which connects to the known server port. Filter out any traffic that is not egressing from the client socket in the BPF program that tests reading the dst_port. Fixes: 8f50f16ff39d ("selftests/bpf: Extend verifier and bpf_sock tests for dst_port loads") Signed-off-by: Jakub Sitnicki Signed-off-by: Daniel Borkmann Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20220317113920.1068535-3-jakub@cloudflare.com Signed-off-by: Ovidiu Panait Signed-off-by: Greg Kroah-Hartman --- tools/testing/selftests/bpf/progs/test_sock_fields.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/test_sock_fields.c b/tools/testing/selftests/bpf/progs/test_sock_fields.c index 3e2e3ee51cc9..43b31aa1fcf7 100644 --- a/tools/testing/selftests/bpf/progs/test_sock_fields.c +++ b/tools/testing/selftests/bpf/progs/test_sock_fields.c @@ -281,6 +281,10 @@ int read_sk_dst_port(struct __sk_buff *skb) if (!sk) RET_LOG(); + /* Ignore everything but the SYN from the client socket */ + if (sk->state != BPF_TCP_SYN_SENT) + return CG_OK; + if (!sk_dst_port__load_word(sk)) RET_LOG(); if (!sk_dst_port__load_half(sk)) From a01a4e9f5dc93335c716fa4023b1901956e8c904 Mon Sep 17 00:00:00 2001 From: George Kennedy Date: Thu, 16 Dec 2021 13:25:32 -0500 Subject: [PATCH 06/24] tun: avoid double free in tun_free_netdev commit 158b515f703e75e7d68289bf4d98c664e1d632df upstream. Avoid double free in tun_free_netdev() by moving the dev->tstats and tun->security allocs to a new ndo_init routine (tun_net_init()) that will be called by register_netdevice(). ndo_init is paired with the desctructor (tun_free_netdev()), so if there's an error in register_netdevice() the destructor will handle the frees. BUG: KASAN: double-free or invalid-free in selinux_tun_dev_free_security+0x1a/0x20 security/selinux/hooks.c:5605 CPU: 0 PID: 25750 Comm: syz-executor416 Not tainted 5.16.0-rc2-syzk #1 Hardware name: Red Hat KVM, BIOS Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x89/0xb5 lib/dump_stack.c:106 print_address_description.constprop.9+0x28/0x160 mm/kasan/report.c:247 kasan_report_invalid_free+0x55/0x80 mm/kasan/report.c:372 ____kasan_slab_free mm/kasan/common.c:346 [inline] __kasan_slab_free+0x107/0x120 mm/kasan/common.c:374 kasan_slab_free include/linux/kasan.h:235 [inline] slab_free_hook mm/slub.c:1723 [inline] slab_free_freelist_hook mm/slub.c:1749 [inline] slab_free mm/slub.c:3513 [inline] kfree+0xac/0x2d0 mm/slub.c:4561 selinux_tun_dev_free_security+0x1a/0x20 security/selinux/hooks.c:5605 security_tun_dev_free_security+0x4f/0x90 security/security.c:2342 tun_free_netdev+0xe6/0x150 drivers/net/tun.c:2215 netdev_run_todo+0x4df/0x840 net/core/dev.c:10627 rtnl_unlock+0x13/0x20 net/core/rtnetlink.c:112 __tun_chr_ioctl+0x80c/0x2870 drivers/net/tun.c:3302 tun_chr_ioctl+0x2f/0x40 drivers/net/tun.c:3311 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:874 [inline] __se_sys_ioctl fs/ioctl.c:860 [inline] __x64_sys_ioctl+0x19d/0x220 fs/ioctl.c:860 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3a/0x80 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae Reported-by: syzkaller Signed-off-by: George Kennedy Suggested-by: Jakub Kicinski Link: https://lore.kernel.org/r/1639679132-19884-1-git-send-email-george.kennedy@oracle.com Signed-off-by: Jakub Kicinski Signed-off-by: Fedor Pchelkin Signed-off-by: Greg Kroah-Hartman --- drivers/net/tun.c | 114 ++++++++++++++++++++++++---------------------- 1 file changed, 59 insertions(+), 55 deletions(-) diff --git a/drivers/net/tun.c b/drivers/net/tun.c index be9ff6a74ecc..a643b2f2f4de 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -220,6 +220,9 @@ struct tun_struct { struct tun_prog __rcu *steering_prog; struct tun_prog __rcu *filter_prog; struct ethtool_link_ksettings link_ksettings; + /* init args */ + struct file *file; + struct ifreq *ifr; }; struct veth { @@ -227,6 +230,9 @@ struct veth { __be16 h_vlan_TCI; }; +static void tun_flow_init(struct tun_struct *tun); +static void tun_flow_uninit(struct tun_struct *tun); + static int tun_napi_receive(struct napi_struct *napi, int budget) { struct tun_file *tfile = container_of(napi, struct tun_file, napi); @@ -975,6 +981,49 @@ static int check_filter(struct tap_filter *filter, const struct sk_buff *skb) static const struct ethtool_ops tun_ethtool_ops; +static int tun_net_init(struct net_device *dev) +{ + struct tun_struct *tun = netdev_priv(dev); + struct ifreq *ifr = tun->ifr; + int err; + + tun->pcpu_stats = netdev_alloc_pcpu_stats(struct tun_pcpu_stats); + if (!tun->pcpu_stats) + return -ENOMEM; + + spin_lock_init(&tun->lock); + + err = security_tun_dev_alloc_security(&tun->security); + if (err < 0) { + free_percpu(tun->pcpu_stats); + return err; + } + + tun_flow_init(tun); + + dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | + TUN_USER_FEATURES | NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_STAG_TX; + dev->features = dev->hw_features | NETIF_F_LLTX; + dev->vlan_features = dev->features & + ~(NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_STAG_TX); + + tun->flags = (tun->flags & ~TUN_FEATURES) | + (ifr->ifr_flags & TUN_FEATURES); + + INIT_LIST_HEAD(&tun->disabled); + err = tun_attach(tun, tun->file, false, ifr->ifr_flags & IFF_NAPI, + ifr->ifr_flags & IFF_NAPI_FRAGS, false); + if (err < 0) { + tun_flow_uninit(tun); + security_tun_dev_free_security(tun->security); + free_percpu(tun->pcpu_stats); + return err; + } + return 0; +} + /* Net device detach from fd. */ static void tun_net_uninit(struct net_device *dev) { @@ -1216,6 +1265,7 @@ static int tun_net_change_carrier(struct net_device *dev, bool new_carrier) } static const struct net_device_ops tun_netdev_ops = { + .ndo_init = tun_net_init, .ndo_uninit = tun_net_uninit, .ndo_open = tun_net_open, .ndo_stop = tun_net_close, @@ -1296,6 +1346,7 @@ static int tun_xdp_tx(struct net_device *dev, struct xdp_buff *xdp) } static const struct net_device_ops tap_netdev_ops = { + .ndo_init = tun_net_init, .ndo_uninit = tun_net_uninit, .ndo_open = tun_net_open, .ndo_stop = tun_net_close, @@ -1336,7 +1387,7 @@ static void tun_flow_uninit(struct tun_struct *tun) #define MAX_MTU 65535 /* Initialize net device. */ -static void tun_net_init(struct net_device *dev) +static void tun_net_initialize(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); @@ -2268,10 +2319,6 @@ static void tun_free_netdev(struct net_device *dev) BUG_ON(!(list_empty(&tun->disabled))); free_percpu(tun->pcpu_stats); - /* We clear pcpu_stats so that tun_set_iff() can tell if - * tun_free_netdev() has been called from register_netdevice(). - */ - tun->pcpu_stats = NULL; tun_flow_uninit(tun); security_tun_dev_free_security(tun->security); @@ -2784,41 +2831,16 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) tun->rx_batched = 0; RCU_INIT_POINTER(tun->steering_prog, NULL); - tun->pcpu_stats = netdev_alloc_pcpu_stats(struct tun_pcpu_stats); - if (!tun->pcpu_stats) { - err = -ENOMEM; - goto err_free_dev; - } + tun->ifr = ifr; + tun->file = file; - spin_lock_init(&tun->lock); - - err = security_tun_dev_alloc_security(&tun->security); - if (err < 0) - goto err_free_stat; - - tun_net_init(dev); - tun_flow_init(tun); - - dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | - TUN_USER_FEATURES | NETIF_F_HW_VLAN_CTAG_TX | - NETIF_F_HW_VLAN_STAG_TX; - dev->features = dev->hw_features | NETIF_F_LLTX; - dev->vlan_features = dev->features & - ~(NETIF_F_HW_VLAN_CTAG_TX | - NETIF_F_HW_VLAN_STAG_TX); - - tun->flags = (tun->flags & ~TUN_FEATURES) | - (ifr->ifr_flags & TUN_FEATURES); - - INIT_LIST_HEAD(&tun->disabled); - err = tun_attach(tun, file, false, ifr->ifr_flags & IFF_NAPI, - ifr->ifr_flags & IFF_NAPI_FRAGS, false); - if (err < 0) - goto err_free_flow; + tun_net_initialize(dev); err = register_netdevice(tun->dev); - if (err < 0) - goto err_detach; + if (err < 0) { + free_netdev(dev); + return err; + } /* free_netdev() won't check refcnt, to aovid race * with dev_put() we need publish tun after registration. */ @@ -2835,24 +2857,6 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) strcpy(ifr->ifr_name, tun->dev->name); return 0; - -err_detach: - tun_detach_all(dev); - /* We are here because register_netdevice() has failed. - * If register_netdevice() already called tun_free_netdev() - * while dealing with the error, tun->pcpu_stats has been cleared. - */ - if (!tun->pcpu_stats) - goto err_free_dev; - -err_free_flow: - tun_flow_uninit(tun); - security_tun_dev_free_security(tun->security); -err_free_stat: - free_percpu(tun->pcpu_stats); -err_free_dev: - free_netdev(dev); - return err; } static void tun_get_iff(struct tun_struct *tun, struct ifreq *ifr) From a2b472b152f9e407f013486dd1673e6c3b6f1fd5 Mon Sep 17 00:00:00 2001 From: Werner Sembach Date: Thu, 7 Jul 2022 20:09:52 +0200 Subject: [PATCH 07/24] ACPI: video: Force backlight native for some TongFang devices commit c752089f7cf5b5800c6ace4cdd1a8351ee78a598 upstream. The TongFang PF5PU1G, PF4NU1F, PF5NU1G, and PF5LUXG/TUXEDO BA15 Gen10, Pulse 14/15 Gen1, and Pulse 15 Gen2 have the same problem as the Clevo NL5xRU and NL5xNU/TUXEDO Aura 15 Gen1 and Gen2: They have a working native and video interface. However the default detection mechanism first registers the video interface before unregistering it again and switching to the native interface during boot. This results in a dangling SBIOS request for backlight change for some reason, causing the backlight to switch to ~2% once per boot on the first power cord connect or disconnect event. Setting the native interface explicitly circumvents this buggy behaviour by avoiding the unregistering process. Signed-off-by: Werner Sembach Cc: All applicable Reviewed-by: Hans de Goede Signed-off-by: Rafael J. Wysocki Signed-off-by: Greg Kroah-Hartman --- drivers/acpi/video_detect.c | 51 ++++++++++++++++++++++++++++++++++++- 1 file changed, 50 insertions(+), 1 deletion(-) diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index 7b9793cb55c5..3021254597f9 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -484,7 +484,56 @@ static const struct dmi_system_id video_detect_dmi_table[] = { DMI_MATCH(DMI_BOARD_NAME, "NL5xNU"), }, }, - + /* + * The TongFang PF5PU1G, PF4NU1F, PF5NU1G, and PF5LUXG/TUXEDO BA15 Gen10, + * Pulse 14/15 Gen1, and Pulse 15 Gen2 have the same problem as the Clevo + * NL5xRU and NL5xNU/TUXEDO Aura 15 Gen1 and Gen2. See the description + * above. + */ + { + .callback = video_detect_force_native, + .ident = "TongFang PF5PU1G", + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "PF5PU1G"), + }, + }, + { + .callback = video_detect_force_native, + .ident = "TongFang PF4NU1F", + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "PF4NU1F"), + }, + }, + { + .callback = video_detect_force_native, + .ident = "TongFang PF4NU1F", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TUXEDO"), + DMI_MATCH(DMI_BOARD_NAME, "PULSE1401"), + }, + }, + { + .callback = video_detect_force_native, + .ident = "TongFang PF5NU1G", + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "PF5NU1G"), + }, + }, + { + .callback = video_detect_force_native, + .ident = "TongFang PF5NU1G", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TUXEDO"), + DMI_MATCH(DMI_BOARD_NAME, "PULSE1501"), + }, + }, + { + .callback = video_detect_force_native, + .ident = "TongFang PF5LUXG", + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "PF5LUXG"), + }, + }, /* * Desktops which falsely report a backlight and which our heuristics * for this do not catch. From 6ccff35588d22bcd7e797163434a796baa540a94 Mon Sep 17 00:00:00 2001 From: Werner Sembach Date: Thu, 7 Jul 2022 20:09:53 +0200 Subject: [PATCH 08/24] ACPI: video: Shortening quirk list by identifying Clevo by board_name only commit f0341e67b3782603737f7788e71bd3530012a4f4 upstream. Taking a recent change in the i8042 quirklist to this one: Clevo board_names are somewhat unique, and if not: The generic Board_-/Sys_Vendor string "Notebook" doesn't help much anyway. So identifying the devices just by the board_name helps keeping the list significantly shorter and might even hit more devices requiring the fix. Signed-off-by: Werner Sembach Fixes: c844d22fe0c0 ("ACPI: video: Force backlight native for Clevo NL5xRU and NL5xNU") Cc: All applicable Reviewed-by: Hans de Goede Signed-off-by: Rafael J. Wysocki Signed-off-by: Greg Kroah-Hartman --- drivers/acpi/video_detect.c | 34 ---------------------------------- 1 file changed, 34 deletions(-) diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index 3021254597f9..e39d59ad6496 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -424,23 +424,6 @@ static const struct dmi_system_id video_detect_dmi_table[] = { .callback = video_detect_force_native, .ident = "Clevo NL5xRU", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "TUXEDO"), - DMI_MATCH(DMI_BOARD_NAME, "NL5xRU"), - }, - }, - { - .callback = video_detect_force_native, - .ident = "Clevo NL5xRU", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "SchenkerTechnologiesGmbH"), - DMI_MATCH(DMI_BOARD_NAME, "NL5xRU"), - }, - }, - { - .callback = video_detect_force_native, - .ident = "Clevo NL5xRU", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Notebook"), DMI_MATCH(DMI_BOARD_NAME, "NL5xRU"), }, }, @@ -464,23 +447,6 @@ static const struct dmi_system_id video_detect_dmi_table[] = { .callback = video_detect_force_native, .ident = "Clevo NL5xNU", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "TUXEDO"), - DMI_MATCH(DMI_BOARD_NAME, "NL5xNU"), - }, - }, - { - .callback = video_detect_force_native, - .ident = "Clevo NL5xNU", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "SchenkerTechnologiesGmbH"), - DMI_MATCH(DMI_BOARD_NAME, "NL5xNU"), - }, - }, - { - .callback = video_detect_force_native, - .ident = "Clevo NL5xNU", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Notebook"), DMI_MATCH(DMI_BOARD_NAME, "NL5xNU"), }, }, From e2c63e1afdb30d71d7b96c5d776bfc9761bba666 Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Wed, 22 Jun 2022 10:09:06 -0700 Subject: [PATCH 09/24] ACPI: APEI: Better fix to avoid spamming the console with old error logs commit c3481b6b75b4797657838f44028fd28226ab48e0 upstream. The fix in commit 3f8dec116210 ("ACPI/APEI: Limit printable size of BERT table data") does not work as intended on systems where the BIOS has a fixed size block of memory for the BERT table, relying on s/w to quit when it finds a record with estatus->block_status == 0. On these systems all errors are suppressed because the check: if (region_len < ACPI_BERT_PRINT_MAX_LEN) always fails. New scheme skips individual CPER records that are too large, and also limits the total number of records that will be printed to 5. Fixes: 3f8dec116210 ("ACPI/APEI: Limit printable size of BERT table data") Cc: All applicable Signed-off-by: Tony Luck Signed-off-by: Rafael J. Wysocki Signed-off-by: Greg Kroah-Hartman --- drivers/acpi/apei/bert.c | 31 +++++++++++++++++++++++-------- 1 file changed, 23 insertions(+), 8 deletions(-) diff --git a/drivers/acpi/apei/bert.c b/drivers/acpi/apei/bert.c index 598fd19b65fa..45973aa6e06d 100644 --- a/drivers/acpi/apei/bert.c +++ b/drivers/acpi/apei/bert.c @@ -29,16 +29,26 @@ #undef pr_fmt #define pr_fmt(fmt) "BERT: " fmt + +#define ACPI_BERT_PRINT_MAX_RECORDS 5 #define ACPI_BERT_PRINT_MAX_LEN 1024 static int bert_disable; +/* + * Print "all" the error records in the BERT table, but avoid huge spam to + * the console if the BIOS included oversize records, or too many records. + * Skipping some records here does not lose anything because the full + * data is available to user tools in: + * /sys/firmware/acpi/tables/data/BERT + */ static void __init bert_print_all(struct acpi_bert_region *region, unsigned int region_len) { struct acpi_hest_generic_status *estatus = (struct acpi_hest_generic_status *)region; int remain = region_len; + int printed = 0, skipped = 0; u32 estatus_len; while (remain >= sizeof(struct acpi_bert_region)) { @@ -46,24 +56,26 @@ static void __init bert_print_all(struct acpi_bert_region *region, if (remain < estatus_len) { pr_err(FW_BUG "Truncated status block (length: %u).\n", estatus_len); - return; + break; } /* No more error records. */ if (!estatus->block_status) - return; + break; if (cper_estatus_check(estatus)) { pr_err(FW_BUG "Invalid error record.\n"); - return; + break; } - pr_info_once("Error records from previous boot:\n"); - if (region_len < ACPI_BERT_PRINT_MAX_LEN) + if (estatus_len < ACPI_BERT_PRINT_MAX_LEN && + printed < ACPI_BERT_PRINT_MAX_RECORDS) { + pr_info_once("Error records from previous boot:\n"); cper_estatus_print(KERN_INFO HW_ERR, estatus); - else - pr_info_once("Max print length exceeded, table data is available at:\n" - "/sys/firmware/acpi/tables/data/BERT"); + printed++; + } else { + skipped++; + } /* * Because the boot error source is "one-time polled" type, @@ -75,6 +87,9 @@ static void __init bert_print_all(struct acpi_bert_region *region, estatus = (void *)estatus + estatus_len; remain -= estatus_len; } + + if (skipped) + pr_info(HW_ERR "Skipped %d error records\n", skipped); } static int __init setup_bert_disable(char *str) From 3c77292d52b341831cb09c24ca4112a1e4f9e91f Mon Sep 17 00:00:00 2001 From: GUO Zihua Date: Fri, 22 Jul 2022 14:31:57 +0800 Subject: [PATCH 10/24] crypto: arm64/poly1305 - fix a read out-of-bound commit 7ae19d422c7da84b5f13bc08b98bd737a08d3a53 upstream. A kasan error was reported during fuzzing: BUG: KASAN: slab-out-of-bounds in neon_poly1305_blocks.constprop.0+0x1b4/0x250 [poly1305_neon] Read of size 4 at addr ffff0010e293f010 by task syz-executor.5/1646715 CPU: 4 PID: 1646715 Comm: syz-executor.5 Kdump: loaded Not tainted 5.10.0.aarch64 #1 Hardware name: Huawei TaiShan 2280 /BC11SPCD, BIOS 1.59 01/31/2019 Call trace: dump_backtrace+0x0/0x394 show_stack+0x34/0x4c arch/arm64/kernel/stacktrace.c:196 __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x158/0x1e4 lib/dump_stack.c:118 print_address_description.constprop.0+0x68/0x204 mm/kasan/report.c:387 __kasan_report+0xe0/0x140 mm/kasan/report.c:547 kasan_report+0x44/0xe0 mm/kasan/report.c:564 check_memory_region_inline mm/kasan/generic.c:187 [inline] __asan_load4+0x94/0xd0 mm/kasan/generic.c:252 neon_poly1305_blocks.constprop.0+0x1b4/0x250 [poly1305_neon] neon_poly1305_do_update+0x6c/0x15c [poly1305_neon] neon_poly1305_update+0x9c/0x1c4 [poly1305_neon] crypto_shash_update crypto/shash.c:131 [inline] shash_finup_unaligned+0x84/0x15c crypto/shash.c:179 crypto_shash_finup+0x8c/0x140 crypto/shash.c:193 shash_digest_unaligned+0xb8/0xe4 crypto/shash.c:201 crypto_shash_digest+0xa4/0xfc crypto/shash.c:217 crypto_shash_tfm_digest+0xb4/0x150 crypto/shash.c:229 essiv_skcipher_setkey+0x164/0x200 [essiv] crypto_skcipher_setkey+0xb0/0x160 crypto/skcipher.c:612 skcipher_setkey+0x3c/0x50 crypto/algif_skcipher.c:305 alg_setkey+0x114/0x2a0 crypto/af_alg.c:220 alg_setsockopt+0x19c/0x210 crypto/af_alg.c:253 __sys_setsockopt+0x190/0x2e0 net/socket.c:2123 __do_sys_setsockopt net/socket.c:2134 [inline] __se_sys_setsockopt net/socket.c:2131 [inline] __arm64_sys_setsockopt+0x78/0x94 net/socket.c:2131 __invoke_syscall arch/arm64/kernel/syscall.c:36 [inline] invoke_syscall+0x64/0x100 arch/arm64/kernel/syscall.c:48 el0_svc_common.constprop.0+0x220/0x230 arch/arm64/kernel/syscall.c:155 do_el0_svc+0xb4/0xd4 arch/arm64/kernel/syscall.c:217 el0_svc+0x24/0x3c arch/arm64/kernel/entry-common.c:353 el0_sync_handler+0x160/0x164 arch/arm64/kernel/entry-common.c:369 el0_sync+0x160/0x180 arch/arm64/kernel/entry.S:683 This error can be reproduced by the following code compiled as ko on a system with kasan enabled: #include #include #include #include char test_data[] = "\x00\x01\x02\x03\x04\x05\x06\x07" "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f" "\x10\x11\x12\x13\x14\x15\x16\x17" "\x18\x19\x1a\x1b\x1c\x1d\x1e"; int init(void) { struct crypto_shash *tfm = NULL; char *data = NULL, *out = NULL; tfm = crypto_alloc_shash("poly1305", 0, 0); data = kmalloc(POLY1305_KEY_SIZE - 1, GFP_KERNEL); out = kmalloc(POLY1305_DIGEST_SIZE, GFP_KERNEL); memcpy(data, test_data, POLY1305_KEY_SIZE - 1); crypto_shash_tfm_digest(tfm, data, POLY1305_KEY_SIZE - 1, out); kfree(data); kfree(out); return 0; } void deinit(void) { } module_init(init) module_exit(deinit) MODULE_LICENSE("GPL"); The root cause of the bug sits in neon_poly1305_blocks. The logic neon_poly1305_blocks() performed is that if it was called with both s[] and r[] uninitialized, it will first try to initialize them with the data from the first "block" that it believed to be 32 bytes in length. First 16 bytes are used as the key and the next 16 bytes for s[]. This would lead to the aforementioned read out-of-bound. However, after calling poly1305_init_arch(), only 16 bytes were deducted from the input and s[] is initialized yet again with the following 16 bytes. The second initialization of s[] is certainly redundent which indicates that the first initialization should be for r[] only. This patch fixes the issue by calling poly1305_init_arm64() instead of poly1305_init_arch(). This is also the implementation for the same algorithm on arm platform. Fixes: f569ca164751 ("crypto: arm64/poly1305 - incorporate OpenSSL/CRYPTOGAMS NEON implementation") Cc: stable@vger.kernel.org Signed-off-by: GUO Zihua Reviewed-by: Eric Biggers Acked-by: Will Deacon Signed-off-by: Herbert Xu Signed-off-by: Greg Kroah-Hartman --- arch/arm64/crypto/poly1305-glue.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/crypto/poly1305-glue.c b/arch/arm64/crypto/poly1305-glue.c index 01e22fe40823..9f4599014854 100644 --- a/arch/arm64/crypto/poly1305-glue.c +++ b/arch/arm64/crypto/poly1305-glue.c @@ -52,7 +52,7 @@ static void neon_poly1305_blocks(struct poly1305_desc_ctx *dctx, const u8 *src, { if (unlikely(!dctx->sset)) { if (!dctx->rset) { - poly1305_init_arch(dctx, src); + poly1305_init_arm64(&dctx->h, src); src += POLY1305_BLOCK_SIZE; len -= POLY1305_BLOCK_SIZE; dctx->rset = 1; From a56e1ccdb7bb455d0b23a7b4de0016153d513aae Mon Sep 17 00:00:00 2001 From: Dmitry Klochkov Date: Tue, 14 Jun 2022 15:11:41 +0300 Subject: [PATCH 11/24] tools/kvm_stat: fix display of error when multiple processes are found [ Upstream commit 933b5f9f98da29af646b51b36a0753692908ef64 ] Instead of printing an error message, kvm_stat script fails when we restrict statistics to a guest by its name and there are multiple guests with such name: # kvm_stat -g my_vm Traceback (most recent call last): File "/usr/bin/kvm_stat", line 1819, in main() File "/usr/bin/kvm_stat", line 1779, in main options = get_options() File "/usr/bin/kvm_stat", line 1718, in get_options options = argparser.parse_args() File "/usr/lib64/python3.10/argparse.py", line 1825, in parse_args args, argv = self.parse_known_args(args, namespace) File "/usr/lib64/python3.10/argparse.py", line 1858, in parse_known_args namespace, args = self._parse_known_args(args, namespace) File "/usr/lib64/python3.10/argparse.py", line 2067, in _parse_known_args start_index = consume_optional(start_index) File "/usr/lib64/python3.10/argparse.py", line 2007, in consume_optional take_action(action, args, option_string) File "/usr/lib64/python3.10/argparse.py", line 1935, in take_action action(self, namespace, argument_values, option_string) File "/usr/bin/kvm_stat", line 1649, in __call__ ' to specify the desired pid'.format(" ".join(pids))) TypeError: sequence item 0: expected str instance, int found To avoid this, it's needed to convert pids int values to strings before pass them to join(). Signed-off-by: Dmitry Klochkov Message-Id: <20220614121141.160689-1-kdmitry556@gmail.com> Signed-off-by: Paolo Bonzini Signed-off-by: Sasha Levin --- tools/kvm/kvm_stat/kvm_stat | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat index b0bf56c5f120..a1efcfbd8b9e 100755 --- a/tools/kvm/kvm_stat/kvm_stat +++ b/tools/kvm/kvm_stat/kvm_stat @@ -1646,7 +1646,8 @@ Press any other key to refresh statistics immediately. .format(values)) if len(pids) > 1: sys.exit('Error: Multiple processes found (pids: {}). Use "-p"' - ' to specify the desired pid'.format(" ".join(pids))) + ' to specify the desired pid' + .format(" ".join(map(str, pids)))) namespace.pid = pids[0] argparser = argparse.ArgumentParser(description=description_text, From 50763f0ac0706e63c0ba550adccfca25eb3d0667 Mon Sep 17 00:00:00 2001 From: Raghavendra Rao Ananta Date: Wed, 15 Jun 2022 18:57:06 +0000 Subject: [PATCH 12/24] selftests: KVM: Handle compiler optimizations in ucall [ Upstream commit 9e2f6498efbbc880d7caa7935839e682b64fe5a6 ] The selftests, when built with newer versions of clang, is found to have over optimized guests' ucall() function, and eliminating the stores for uc.cmd (perhaps due to no immediate readers). This resulted in the userspace side always reading a value of '0', and causing multiple test failures. As a result, prevent the compiler from optimizing the stores in ucall() with WRITE_ONCE(). Suggested-by: Ricardo Koller Suggested-by: Reiji Watanabe Signed-off-by: Raghavendra Rao Ananta Message-Id: <20220615185706.1099208-1-rananta@google.com> Reviewed-by: Andrew Jones Signed-off-by: Paolo Bonzini Signed-off-by: Sasha Levin --- tools/testing/selftests/kvm/lib/aarch64/ucall.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/kvm/lib/aarch64/ucall.c b/tools/testing/selftests/kvm/lib/aarch64/ucall.c index 2f37b90ee1a9..f600311fdc6a 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/ucall.c +++ b/tools/testing/selftests/kvm/lib/aarch64/ucall.c @@ -73,20 +73,19 @@ void ucall_uninit(struct kvm_vm *vm) void ucall(uint64_t cmd, int nargs, ...) { - struct ucall uc = { - .cmd = cmd, - }; + struct ucall uc = {}; va_list va; int i; + WRITE_ONCE(uc.cmd, cmd); nargs = nargs <= UCALL_MAX_ARGS ? nargs : UCALL_MAX_ARGS; va_start(va, nargs); for (i = 0; i < nargs; ++i) - uc.args[i] = va_arg(va, uint64_t); + WRITE_ONCE(uc.args[i], va_arg(va, uint64_t)); va_end(va); - *ucall_exit_mmio_addr = (vm_vaddr_t)&uc; + WRITE_ONCE(*ucall_exit_mmio_addr, (vm_vaddr_t)&uc); } uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc) From 033a4455d9d6ccba0f8acbf297d3094b78ee409e Mon Sep 17 00:00:00 2001 From: Ahmad Fatoum Date: Tue, 24 May 2022 07:56:41 +0200 Subject: [PATCH 13/24] Bluetooth: hci_bcm: Add BCM4349B1 variant commit 4f17c2b6694d0c4098f33b07ee3a696976940aa5 upstream. The BCM4349B1, aka CYW/BCM89359, is a WiFi+BT chip and its Bluetooth portion can be controlled over serial. Two subversions are added for the chip, because ROM firmware reports 002.002.013 (at least for the chips I have here), while depending on patchram firmware revision, either 002.002.013 or 002.002.014 is reported. Signed-off-by: Ahmad Fatoum Reviewed-by: Linus Walleij Signed-off-by: Marcel Holtmann Signed-off-by: Greg Kroah-Hartman --- drivers/bluetooth/btbcm.c | 2 ++ drivers/bluetooth/hci_bcm.c | 1 + 2 files changed, 3 insertions(+) diff --git a/drivers/bluetooth/btbcm.c b/drivers/bluetooth/btbcm.c index 1b9743b7f2ef..d263eac784da 100644 --- a/drivers/bluetooth/btbcm.c +++ b/drivers/bluetooth/btbcm.c @@ -401,6 +401,8 @@ static const struct bcm_subver_table bcm_uart_subver_table[] = { { 0x6606, "BCM4345C5" }, /* 003.006.006 */ { 0x230f, "BCM4356A2" }, /* 001.003.015 */ { 0x220e, "BCM20702A1" }, /* 001.002.014 */ + { 0x420d, "BCM4349B1" }, /* 002.002.013 */ + { 0x420e, "BCM4349B1" }, /* 002.002.014 */ { 0x4217, "BCM4329B1" }, /* 002.002.023 */ { 0x6106, "BCM4359C0" }, /* 003.001.006 */ { 0x4106, "BCM4335A0" }, /* 002.001.006 */ diff --git a/drivers/bluetooth/hci_bcm.c b/drivers/bluetooth/hci_bcm.c index 259a643377c2..574f84708859 100644 --- a/drivers/bluetooth/hci_bcm.c +++ b/drivers/bluetooth/hci_bcm.c @@ -1489,6 +1489,7 @@ static const struct of_device_id bcm_bluetooth_of_match[] = { { .compatible = "brcm,bcm4345c5" }, { .compatible = "brcm,bcm4330-bt" }, { .compatible = "brcm,bcm43438-bt", .data = &bcm43438_device_data }, + { .compatible = "brcm,bcm4349-bt", .data = &bcm43438_device_data }, { .compatible = "brcm,bcm43540-bt", .data = &bcm4354_device_data }, { .compatible = "brcm,bcm4335a0" }, { }, From 918ce738e28bb79d84dd208ff9b5dacd8f533058 Mon Sep 17 00:00:00 2001 From: Hakan Jansson Date: Thu, 30 Jun 2022 14:45:22 +0200 Subject: [PATCH 14/24] Bluetooth: hci_bcm: Add DT compatible for CYW55572 commit f8cad62002a7699fd05a23b558b980b5a77defe0 upstream. CYW55572 is a Wi-Fi + Bluetooth combo device from Infineon. Signed-off-by: Hakan Jansson Reviewed-by: Linus Walleij Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Greg Kroah-Hartman --- drivers/bluetooth/hci_bcm.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/bluetooth/hci_bcm.c b/drivers/bluetooth/hci_bcm.c index 574f84708859..3f6e96a4e114 100644 --- a/drivers/bluetooth/hci_bcm.c +++ b/drivers/bluetooth/hci_bcm.c @@ -1492,6 +1492,7 @@ static const struct of_device_id bcm_bluetooth_of_match[] = { { .compatible = "brcm,bcm4349-bt", .data = &bcm43438_device_data }, { .compatible = "brcm,bcm43540-bt", .data = &bcm4354_device_data }, { .compatible = "brcm,bcm4335a0" }, + { .compatible = "infineon,cyw55572-bt" }, { }, }; MODULE_DEVICE_TABLE(of, bcm_bluetooth_of_match); From e81f95d03060090c4bd4d1d7cea15fb9542224ba Mon Sep 17 00:00:00 2001 From: Aaron Ma Date: Thu, 2 Jun 2022 17:28:22 +0800 Subject: [PATCH 15/24] Bluetooth: btusb: Add support of IMC Networks PID 0x3568 commit c69ecb0ea4c96b8b191cbaa0b420222a37867655 upstream. It is 13d3:3568 for MediaTek MT7922 USB Bluetooth chip. T: Bus=03 Lev=01 Prnt=01 Port=02 Cnt=01 Dev#= 2 Spd=480 MxCh= 0 D: Ver= 2.10 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=13d3 ProdID=3568 Rev=01.00 S: Manufacturer=MediaTek Inc. S: Product=Wireless_Device S: SerialNumber=... C: #Ifs= 3 Cfg#= 1 Atr=e0 MxPwr=100mA I: If#= 0 Alt= 0 #EPs= 3 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms E: Ad=81(I) Atr=03(Int.) MxPS= 16 Ivl=125us E: Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms I: If#= 1 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 0 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 0 Ivl=1ms I: If#= 2 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=(none) E: Ad=0a(O) Atr=03(Int.) MxPS= 64 Ivl=125us E: Ad=8a(I) Atr=03(Int.) MxPS= 64 Ivl=125us Signed-off-by: Aaron Ma Signed-off-by: Marcel Holtmann Signed-off-by: Greg Kroah-Hartman --- drivers/bluetooth/btusb.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 538232b4c42a..d450da1211e0 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -416,6 +416,9 @@ static const struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x0489, 0xe0d9), .driver_info = BTUSB_MEDIATEK | BTUSB_WIDEBAND_SPEECH | BTUSB_VALID_LE_STATES }, + { USB_DEVICE(0x13d3, 0x3568), .driver_info = BTUSB_MEDIATEK | + BTUSB_WIDEBAND_SPEECH | + BTUSB_VALID_LE_STATES }, /* Additional Realtek 8723AE Bluetooth devices */ { USB_DEVICE(0x0930, 0x021d), .driver_info = BTUSB_REALTEK }, From 1a2a2e34569cf85cad743ee8095d07c3cba5473b Mon Sep 17 00:00:00 2001 From: Hilda Wu Date: Thu, 14 Jul 2022 19:25:19 +0800 Subject: [PATCH 16/24] Bluetooth: btusb: Add Realtek RTL8852C support ID 0x04CA:0x4007 commit c379c96cc221767af9688a5d4758a78eea30883a upstream. Add the support ID(0x04CA, 0x4007) to usb_device_id table for Realtek RTL8852C. The device info from /sys/kernel/debug/usb/devices as below. T: Bus=03 Lev=01 Prnt=01 Port=02 Cnt=01 Dev#= 2 Spd=12 MxCh= 0 D: Ver= 1.00 Cls=e0(wlcon) Sub=01 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=04ca ProdID=4007 Rev= 0.00 S: Manufacturer=Realtek S: Product=Bluetooth Radio S: SerialNumber=00e04c000001 C:* #Ifs= 2 Cfg#= 1 Atr=e0 MxPwr=500mA I:* If#= 0 Alt= 0 #EPs= 3 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=81(I) Atr=03(Int.) MxPS= 16 Ivl=1ms E: Ad=02(O) Atr=02(Bulk) MxPS= 64 Ivl=0ms E: Ad=82(I) Atr=02(Bulk) MxPS= 64 Ivl=0ms I:* If#= 1 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 0 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 0 Ivl=1ms I: If#= 1 Alt= 1 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 9 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 9 Ivl=1ms I: If#= 1 Alt= 2 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 17 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 17 Ivl=1ms I: If#= 1 Alt= 3 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 25 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 25 Ivl=1ms I: If#= 1 Alt= 4 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 33 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 33 Ivl=1ms I: If#= 1 Alt= 5 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 49 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 49 Ivl=1ms Signed-off-by: Hilda Wu Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Greg Kroah-Hartman --- drivers/bluetooth/btusb.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index d450da1211e0..ed529bcac92a 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -399,6 +399,10 @@ static const struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x0bda, 0xc822), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, + /* Realtek 8852CE Bluetooth devices */ + { USB_DEVICE(0x04ca, 0x4007), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, + /* Realtek Bluetooth devices */ { USB_VENDOR_AND_INTERFACE_INFO(0x0bda, 0xe0, 0x01, 0x01), .driver_info = BTUSB_REALTEK }, From 3a292cb18132cb7af3a146613f1c9a47ef6f8463 Mon Sep 17 00:00:00 2001 From: Hilda Wu Date: Thu, 14 Jul 2022 19:25:20 +0800 Subject: [PATCH 17/24] Bluetooth: btusb: Add Realtek RTL8852C support ID 0x04C5:0x1675 commit 893fa8bc9952a36fb682ee12f0a994b5817a36d2 upstream. Add the support ID(0x04c5, 0x1675) to usb_device_id table for Realtek RTL8852C. The device info from /sys/kernel/debug/usb/devices as below. T: Bus=03 Lev=01 Prnt=01 Port=02 Cnt=01 Dev#= 2 Spd=12 MxCh= 0 D: Ver= 1.00 Cls=e0(wlcon) Sub=01 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=04c5 ProdID=1675 Rev= 0.00 S: Manufacturer=Realtek S: Product=Bluetooth Radio S: SerialNumber=00e04c000001 C:* #Ifs= 2 Cfg#= 1 Atr=e0 MxPwr=500mA I:* If#= 0 Alt= 0 #EPs= 3 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=81(I) Atr=03(Int.) MxPS= 16 Ivl=1ms E: Ad=02(O) Atr=02(Bulk) MxPS= 64 Ivl=0ms E: Ad=82(I) Atr=02(Bulk) MxPS= 64 Ivl=0ms I:* If#= 1 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 0 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 0 Ivl=1ms I: If#= 1 Alt= 1 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 9 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 9 Ivl=1ms I: If#= 1 Alt= 2 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 17 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 17 Ivl=1ms I: If#= 1 Alt= 3 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 25 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 25 Ivl=1ms I: If#= 1 Alt= 4 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 33 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 33 Ivl=1ms I: If#= 1 Alt= 5 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 49 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 49 Ivl=1ms Signed-off-by: Hilda Wu Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Greg Kroah-Hartman --- drivers/bluetooth/btusb.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index ed529bcac92a..263210a3b7b3 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -402,6 +402,8 @@ static const struct usb_device_id blacklist_table[] = { /* Realtek 8852CE Bluetooth devices */ { USB_DEVICE(0x04ca, 0x4007), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x04c5, 0x1675), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, /* Realtek Bluetooth devices */ { USB_VENDOR_AND_INTERFACE_INFO(0x0bda, 0xe0, 0x01, 0x01), From 9c45bb363e26e86ebaf20f6d2009bedf19fc0d39 Mon Sep 17 00:00:00 2001 From: Hilda Wu Date: Thu, 14 Jul 2022 19:25:21 +0800 Subject: [PATCH 18/24] Bluetooth: btusb: Add Realtek RTL8852C support ID 0x0CB8:0xC558 commit 5b75ee37ebb73f58468d4cca172434324af203f1 upstream. Add the support ID(0x0CB8, 0xC558) to usb_device_id table for Realtek RTL8852C. The device info from /sys/kernel/debug/usb/devices as below. T: Bus=03 Lev=01 Prnt=01 Port=02 Cnt=01 Dev#= 2 Spd=12 MxCh= 0 D: Ver= 1.00 Cls=e0(wlcon) Sub=01 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=0cb8 ProdID=c558 Rev= 0.00 S: Manufacturer=Realtek S: Product=Bluetooth Radio S: SerialNumber=00e04c000001 C:* #Ifs= 2 Cfg#= 1 Atr=e0 MxPwr=500mA I:* If#= 0 Alt= 0 #EPs= 3 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=81(I) Atr=03(Int.) MxPS= 16 Ivl=1ms E: Ad=02(O) Atr=02(Bulk) MxPS= 64 Ivl=0ms E: Ad=82(I) Atr=02(Bulk) MxPS= 64 Ivl=0ms I:* If#= 1 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 0 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 0 Ivl=1ms I: If#= 1 Alt= 1 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 9 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 9 Ivl=1ms I: If#= 1 Alt= 2 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 17 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 17 Ivl=1ms I: If#= 1 Alt= 3 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 25 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 25 Ivl=1ms I: If#= 1 Alt= 4 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 33 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 33 Ivl=1ms I: If#= 1 Alt= 5 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 49 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 49 Ivl=1ms Signed-off-by: Hilda Wu Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Greg Kroah-Hartman --- drivers/bluetooth/btusb.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 263210a3b7b3..0e9e88c82520 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -404,6 +404,8 @@ static const struct usb_device_id blacklist_table[] = { BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x04c5, 0x1675), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x0cb8, 0xc558), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, /* Realtek Bluetooth devices */ { USB_VENDOR_AND_INTERFACE_INFO(0x0bda, 0xe0, 0x01, 0x01), From 40e2e7f1bf0301d1ed7437b10d9e1c92cb51bf81 Mon Sep 17 00:00:00 2001 From: Hilda Wu Date: Thu, 14 Jul 2022 19:25:22 +0800 Subject: [PATCH 19/24] Bluetooth: btusb: Add Realtek RTL8852C support ID 0x13D3:0x3587 commit 8f0054dd29373cd877db87751c143610561d549d upstream. Add the support ID(0x13D3, 0x3587) to usb_device_id table for Realtek RTL8852C. The device info from /sys/kernel/debug/usb/devices as below. T: Bus=03 Lev=01 Prnt=01 Port=02 Cnt=01 Dev#= 2 Spd=12 MxCh= 0 D: Ver= 1.00 Cls=e0(wlcon) Sub=01 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=13d3 ProdID=3587 Rev= 0.00 S: Manufacturer=Realtek S: Product=Bluetooth Radio S: SerialNumber=00e04c000001 C:* #Ifs= 2 Cfg#= 1 Atr=e0 MxPwr=500mA I:* If#= 0 Alt= 0 #EPs= 3 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=81(I) Atr=03(Int.) MxPS= 16 Ivl=1ms E: Ad=02(O) Atr=02(Bulk) MxPS= 64 Ivl=0ms E: Ad=82(I) Atr=02(Bulk) MxPS= 64 Ivl=0ms I:* If#= 1 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 0 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 0 Ivl=1ms I: If#= 1 Alt= 1 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 9 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 9 Ivl=1ms I: If#= 1 Alt= 2 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 17 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 17 Ivl=1ms I: If#= 1 Alt= 3 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 25 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 25 Ivl=1ms I: If#= 1 Alt= 4 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 33 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 33 Ivl=1ms I: If#= 1 Alt= 5 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 49 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 49 Ivl=1ms Signed-off-by: Hilda Wu Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Greg Kroah-Hartman --- drivers/bluetooth/btusb.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 0e9e88c82520..ff27697a0daa 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -406,6 +406,8 @@ static const struct usb_device_id blacklist_table[] = { BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x0cb8, 0xc558), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x13d3, 0x3587), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, /* Realtek Bluetooth devices */ { USB_VENDOR_AND_INTERFACE_INFO(0x0bda, 0xe0, 0x01, 0x01), From 75742ffc3630203e95844c72c7144f507e2a557d Mon Sep 17 00:00:00 2001 From: Hilda Wu Date: Thu, 14 Jul 2022 19:25:23 +0800 Subject: [PATCH 20/24] Bluetooth: btusb: Add Realtek RTL8852C support ID 0x13D3:0x3586 commit 6ad353dfc8ee3230a5e123c21da50f1b64cc4b39 upstream. Add the support ID(0x13D3, 0x3586) to usb_device_id table for Realtek RTL8852C. The device info from /sys/kernel/debug/usb/devices as below. T: Bus=03 Lev=01 Prnt=01 Port=02 Cnt=01 Dev#= 2 Spd=12 MxCh= 0 D: Ver= 1.00 Cls=e0(wlcon) Sub=01 Prot=01 MxPS=64 #Cfgs= 1 P: Vendor=13d3 ProdID=3586 Rev= 0.00 S: Manufacturer=Realtek S: Product=Bluetooth Radio S: SerialNumber=00e04c000001 C:* #Ifs= 2 Cfg#= 1 Atr=e0 MxPwr=500mA I:* If#= 0 Alt= 0 #EPs= 3 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=81(I) Atr=03(Int.) MxPS= 16 Ivl=1ms E: Ad=02(O) Atr=02(Bulk) MxPS= 64 Ivl=0ms E: Ad=82(I) Atr=02(Bulk) MxPS= 64 Ivl=0ms I:* If#= 1 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 0 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 0 Ivl=1ms I: If#= 1 Alt= 1 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 9 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 9 Ivl=1ms I: If#= 1 Alt= 2 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 17 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 17 Ivl=1ms I: If#= 1 Alt= 3 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 25 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 25 Ivl=1ms I: If#= 1 Alt= 4 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 33 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 33 Ivl=1ms I: If#= 1 Alt= 5 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb E: Ad=03(O) Atr=01(Isoc) MxPS= 49 Ivl=1ms E: Ad=83(I) Atr=01(Isoc) MxPS= 49 Ivl=1ms Signed-off-by: Hilda Wu Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Greg Kroah-Hartman --- drivers/bluetooth/btusb.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index ff27697a0daa..a699e6166aef 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -408,6 +408,8 @@ static const struct usb_device_id blacklist_table[] = { BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x13d3, 0x3587), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x13d3, 0x3586), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, /* Realtek Bluetooth devices */ { USB_VENDOR_AND_INTERFACE_INFO(0x0bda, 0xe0, 0x01, 0x01), From e5b556a7b2711a39e3aa13aeff26560c17417b8b Mon Sep 17 00:00:00 2001 From: Ning Qiang Date: Wed, 13 Jul 2022 23:37:34 +0800 Subject: [PATCH 21/24] macintosh/adb: fix oob read in do_adb_query() function commit fd97e4ad6d3b0c9fce3bca8ea8e6969d9ce7423b upstream. In do_adb_query() function of drivers/macintosh/adb.c, req->data is copied form userland. The parameter "req->data[2]" is missing check, the array size of adb_handler[] is 16, so adb_handler[req->data[2]].original_address and adb_handler[req->data[2]].handler_id will lead to oob read. Cc: stable Signed-off-by: Ning Qiang Reviewed-by: Kees Cook Reviewed-by: Greg Kroah-Hartman Acked-by: Benjamin Herrenschmidt Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20220713153734.2248-1-sohu0106@126.com Signed-off-by: Greg Kroah-Hartman --- drivers/macintosh/adb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/macintosh/adb.c b/drivers/macintosh/adb.c index 73b396189039..afb0942ccc29 100644 --- a/drivers/macintosh/adb.c +++ b/drivers/macintosh/adb.c @@ -647,7 +647,7 @@ do_adb_query(struct adb_request *req) switch(req->data[1]) { case ADB_QUERY_GETDEVINFO: - if (req->nbytes < 3) + if (req->nbytes < 3 || req->data[2] >= 16) break; mutex_lock(&adb_handler_mutex); req->reply[0] = adb_handler[req->data[2]].original_address; From 509c2c9fe75ea7493eebbb6bb2f711f37530ae19 Mon Sep 17 00:00:00 2001 From: Daniel Sneddon Date: Tue, 2 Aug 2022 15:47:01 -0700 Subject: [PATCH 22/24] x86/speculation: Add RSB VM Exit protections commit 2b1299322016731d56807aa49254a5ea3080b6b3 upstream. tl;dr: The Enhanced IBRS mitigation for Spectre v2 does not work as documented for RET instructions after VM exits. Mitigate it with a new one-entry RSB stuffing mechanism and a new LFENCE. == Background == Indirect Branch Restricted Speculation (IBRS) was designed to help mitigate Branch Target Injection and Speculative Store Bypass, i.e. Spectre, attacks. IBRS prevents software run in less privileged modes from affecting branch prediction in more privileged modes. IBRS requires the MSR to be written on every privilege level change. To overcome some of the performance issues of IBRS, Enhanced IBRS was introduced. eIBRS is an "always on" IBRS, in other words, just turn it on once instead of writing the MSR on every privilege level change. When eIBRS is enabled, more privileged modes should be protected from less privileged modes, including protecting VMMs from guests. == Problem == Here's a simplification of how guests are run on Linux' KVM: void run_kvm_guest(void) { // Prepare to run guest VMRESUME(); // Clean up after guest runs } The execution flow for that would look something like this to the processor: 1. Host-side: call run_kvm_guest() 2. Host-side: VMRESUME 3. Guest runs, does "CALL guest_function" 4. VM exit, host runs again 5. Host might make some "cleanup" function calls 6. Host-side: RET from run_kvm_guest() Now, when back on the host, there are a couple of possible scenarios of post-guest activity the host needs to do before executing host code: * on pre-eIBRS hardware (legacy IBRS, or nothing at all), the RSB is not touched and Linux has to do a 32-entry stuffing. * on eIBRS hardware, VM exit with IBRS enabled, or restoring the host IBRS=1 shortly after VM exit, has a documented side effect of flushing the RSB except in this PBRSB situation where the software needs to stuff the last RSB entry "by hand". IOW, with eIBRS supported, host RET instructions should no longer be influenced by guest behavior after the host retires a single CALL instruction. However, if the RET instructions are "unbalanced" with CALLs after a VM exit as is the RET in #6, it might speculatively use the address for the instruction after the CALL in #3 as an RSB prediction. This is a problem since the (untrusted) guest controls this address. Balanced CALL/RET instruction pairs such as in step #5 are not affected. == Solution == The PBRSB issue affects a wide variety of Intel processors which support eIBRS. But not all of them need mitigation. Today, X86_FEATURE_RSB_VMEXIT triggers an RSB filling sequence that mitigates PBRSB. Systems setting RSB_VMEXIT need no further mitigation - i.e., eIBRS systems which enable legacy IBRS explicitly. However, such systems (X86_FEATURE_IBRS_ENHANCED) do not set RSB_VMEXIT and most of them need a new mitigation. Therefore, introduce a new feature flag X86_FEATURE_RSB_VMEXIT_LITE which triggers a lighter-weight PBRSB mitigation versus RSB_VMEXIT. The lighter-weight mitigation performs a CALL instruction which is immediately followed by a speculative execution barrier (INT3). This steers speculative execution to the barrier -- just like a retpoline -- which ensures that speculation can never reach an unbalanced RET. Then, ensure this CALL is retired before continuing execution with an LFENCE. In other words, the window of exposure is opened at VM exit where RET behavior is troublesome. While the window is open, force RSB predictions sampling for RET targets to a dead end at the INT3. Close the window with the LFENCE. There is a subset of eIBRS systems which are not vulnerable to PBRSB. Add these systems to the cpu_vuln_whitelist[] as NO_EIBRS_PBRSB. Future systems that aren't vulnerable will set ARCH_CAP_PBRSB_NO. [ bp: Massage, incorporate review comments from Andy Cooper. ] Signed-off-by: Daniel Sneddon Co-developed-by: Pawan Gupta Signed-off-by: Pawan Gupta Signed-off-by: Borislav Petkov Signed-off-by: Greg Kroah-Hartman --- Documentation/admin-guide/hw-vuln/spectre.rst | 8 ++ arch/x86/include/asm/cpufeatures.h | 2 + arch/x86/include/asm/msr-index.h | 4 + arch/x86/include/asm/nospec-branch.h | 17 +++- arch/x86/kernel/cpu/bugs.c | 86 ++++++++++++++----- arch/x86/kernel/cpu/common.c | 12 ++- arch/x86/kvm/vmx/vmenter.S | 8 +- tools/arch/x86/include/asm/cpufeatures.h | 1 + tools/arch/x86/include/asm/msr-index.h | 4 + 9 files changed, 113 insertions(+), 29 deletions(-) diff --git a/Documentation/admin-guide/hw-vuln/spectre.rst b/Documentation/admin-guide/hw-vuln/spectre.rst index 6bd97cd50d62..7e061ed449aa 100644 --- a/Documentation/admin-guide/hw-vuln/spectre.rst +++ b/Documentation/admin-guide/hw-vuln/spectre.rst @@ -422,6 +422,14 @@ The possible values in this file are: 'RSB filling' Protection of RSB on context switch enabled ============= =========================================== + - EIBRS Post-barrier Return Stack Buffer (PBRSB) protection status: + + =========================== ======================================================= + 'PBRSB-eIBRS: SW sequence' CPU is affected and protection of RSB on VMEXIT enabled + 'PBRSB-eIBRS: Vulnerable' CPU is vulnerable + 'PBRSB-eIBRS: Not affected' CPU is not affected by PBRSB + =========================== ======================================================= + Full mitigation might require a microcode update from the CPU vendor. When the necessary microcode is not available, the kernel will report vulnerability. diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 2a51ee2f5a0f..37ba0cdf99aa 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -299,6 +299,7 @@ #define X86_FEATURE_RETHUNK (11*32+14) /* "" Use REturn THUNK */ #define X86_FEATURE_UNRET (11*32+15) /* "" AMD BTB untrain return */ #define X86_FEATURE_USE_IBPB_FW (11*32+16) /* "" Use IBPB during runtime firmware calls */ +#define X86_FEATURE_RSB_VMEXIT_LITE (11*32+17) /* "" Fill RSB on VM exit when EIBRS is enabled */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ @@ -429,5 +430,6 @@ #define X86_BUG_SRBDS X86_BUG(24) /* CPU may leak RNG bits if not mitigated */ #define X86_BUG_MMIO_STALE_DATA X86_BUG(25) /* CPU is affected by Processor MMIO Stale Data vulnerabilities */ #define X86_BUG_RETBLEED X86_BUG(26) /* CPU is affected by RETBleed */ +#define X86_BUG_EIBRS_PBRSB X86_BUG(27) /* EIBRS is vulnerable to Post Barrier RSB Predictions */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 407de670cd60..144dc164b759 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -148,6 +148,10 @@ * are restricted to targets in * kernel. */ +#define ARCH_CAP_PBRSB_NO BIT(24) /* + * Not susceptible to Post-Barrier + * Return Stack Buffer Predictions. + */ #define MSR_IA32_FLUSH_CMD 0x0000010b #define L1D_FLUSH BIT(0) /* diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index c3e8e50633ea..8ff940058a41 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -118,13 +118,28 @@ #endif .endm +.macro ISSUE_UNBALANCED_RET_GUARD + ANNOTATE_INTRA_FUNCTION_CALL + call .Lunbalanced_ret_guard_\@ + int3 +.Lunbalanced_ret_guard_\@: + add $(BITS_PER_LONG/8), %_ASM_SP + lfence +.endm + /* * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP * monstrosity above, manually. */ -.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req +.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req ftr2 +.ifb \ftr2 ALTERNATIVE "jmp .Lskip_rsb_\@", "", \ftr +.else + ALTERNATIVE_2 "jmp .Lskip_rsb_\@", "", \ftr, "jmp .Lunbalanced_\@", \ftr2 +.endif __FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP) +.Lunbalanced_\@: + ISSUE_UNBALANCED_RET_GUARD .Lskip_rsb_\@: .endm diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 2e5762faf774..859a3f59526c 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1291,6 +1291,53 @@ static void __init spec_ctrl_disable_kernel_rrsba(void) } } +static void __init spectre_v2_determine_rsb_fill_type_at_vmexit(enum spectre_v2_mitigation mode) +{ + /* + * Similar to context switches, there are two types of RSB attacks + * after VM exit: + * + * 1) RSB underflow + * + * 2) Poisoned RSB entry + * + * When retpoline is enabled, both are mitigated by filling/clearing + * the RSB. + * + * When IBRS is enabled, while #1 would be mitigated by the IBRS branch + * prediction isolation protections, RSB still needs to be cleared + * because of #2. Note that SMEP provides no protection here, unlike + * user-space-poisoned RSB entries. + * + * eIBRS should protect against RSB poisoning, but if the EIBRS_PBRSB + * bug is present then a LITE version of RSB protection is required, + * just a single call needs to retire before a RET is executed. + */ + switch (mode) { + case SPECTRE_V2_NONE: + return; + + case SPECTRE_V2_EIBRS_LFENCE: + case SPECTRE_V2_EIBRS: + if (boot_cpu_has_bug(X86_BUG_EIBRS_PBRSB)) { + setup_force_cpu_cap(X86_FEATURE_RSB_VMEXIT_LITE); + pr_info("Spectre v2 / PBRSB-eIBRS: Retire a single CALL on VMEXIT\n"); + } + return; + + case SPECTRE_V2_EIBRS_RETPOLINE: + case SPECTRE_V2_RETPOLINE: + case SPECTRE_V2_LFENCE: + case SPECTRE_V2_IBRS: + setup_force_cpu_cap(X86_FEATURE_RSB_VMEXIT); + pr_info("Spectre v2 / SpectreRSB : Filling RSB on VMEXIT\n"); + return; + } + + pr_warn_once("Unknown Spectre v2 mode, disabling RSB mitigation at VM exit"); + dump_stack(); +} + static void __init spectre_v2_select_mitigation(void) { enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline(); @@ -1441,28 +1488,7 @@ static void __init spectre_v2_select_mitigation(void) setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW); pr_info("Spectre v2 / SpectreRSB mitigation: Filling RSB on context switch\n"); - /* - * Similar to context switches, there are two types of RSB attacks - * after vmexit: - * - * 1) RSB underflow - * - * 2) Poisoned RSB entry - * - * When retpoline is enabled, both are mitigated by filling/clearing - * the RSB. - * - * When IBRS is enabled, while #1 would be mitigated by the IBRS branch - * prediction isolation protections, RSB still needs to be cleared - * because of #2. Note that SMEP provides no protection here, unlike - * user-space-poisoned RSB entries. - * - * eIBRS, on the other hand, has RSB-poisoning protections, so it - * doesn't need RSB clearing after vmexit. - */ - if (boot_cpu_has(X86_FEATURE_RETPOLINE) || - boot_cpu_has(X86_FEATURE_KERNEL_IBRS)) - setup_force_cpu_cap(X86_FEATURE_RSB_VMEXIT); + spectre_v2_determine_rsb_fill_type_at_vmexit(mode); /* * Retpoline protects the kernel, but doesn't protect firmware. IBRS @@ -2215,6 +2241,19 @@ static char *ibpb_state(void) return ""; } +static char *pbrsb_eibrs_state(void) +{ + if (boot_cpu_has_bug(X86_BUG_EIBRS_PBRSB)) { + if (boot_cpu_has(X86_FEATURE_RSB_VMEXIT_LITE) || + boot_cpu_has(X86_FEATURE_RSB_VMEXIT)) + return ", PBRSB-eIBRS: SW sequence"; + else + return ", PBRSB-eIBRS: Vulnerable"; + } else { + return ", PBRSB-eIBRS: Not affected"; + } +} + static ssize_t spectre_v2_show_state(char *buf) { if (spectre_v2_enabled == SPECTRE_V2_LFENCE) @@ -2227,12 +2266,13 @@ static ssize_t spectre_v2_show_state(char *buf) spectre_v2_enabled == SPECTRE_V2_EIBRS_LFENCE) return sprintf(buf, "Vulnerable: eIBRS+LFENCE with unprivileged eBPF and SMT\n"); - return sprintf(buf, "%s%s%s%s%s%s\n", + return sprintf(buf, "%s%s%s%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], ibpb_state(), boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", stibp_state(), boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? ", RSB filling" : "", + pbrsb_eibrs_state(), spectre_v2_module_string()); } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 901352bd3b42..9fc91482e85e 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1024,6 +1024,7 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) #define NO_SWAPGS BIT(6) #define NO_ITLB_MULTIHIT BIT(7) #define NO_SPECTRE_V2 BIT(8) +#define NO_EIBRS_PBRSB BIT(9) #define VULNWL(vendor, family, model, whitelist) \ X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, whitelist) @@ -1064,7 +1065,7 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), VULNWL_INTEL(ATOM_GOLDMONT_D, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), - VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_EIBRS_PBRSB), /* * Technically, swapgs isn't serializing on AMD (despite it previously @@ -1074,7 +1075,9 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { * good enough for our purposes. */ - VULNWL_INTEL(ATOM_TREMONT_D, NO_ITLB_MULTIHIT), + VULNWL_INTEL(ATOM_TREMONT, NO_EIBRS_PBRSB), + VULNWL_INTEL(ATOM_TREMONT_L, NO_EIBRS_PBRSB), + VULNWL_INTEL(ATOM_TREMONT_D, NO_ITLB_MULTIHIT | NO_EIBRS_PBRSB), /* AMD Family 0xf - 0x12 */ VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), @@ -1252,6 +1255,11 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) setup_force_cpu_bug(X86_BUG_RETBLEED); } + if (cpu_has(c, X86_FEATURE_IBRS_ENHANCED) && + !cpu_matches(cpu_vuln_whitelist, NO_EIBRS_PBRSB) && + !(ia32_cap & ARCH_CAP_PBRSB_NO)) + setup_force_cpu_bug(X86_BUG_EIBRS_PBRSB); + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 857fa0fc49fa..982138bebb70 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -197,11 +197,13 @@ SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL) * entries and (in some cases) RSB underflow. * * eIBRS has its own protection against poisoned RSB, so it doesn't - * need the RSB filling sequence. But it does need to be enabled - * before the first unbalanced RET. + * need the RSB filling sequence. But it does need to be enabled, and a + * single call to retire, before the first unbalanced RET. */ - FILL_RETURN_BUFFER %_ASM_CX, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_VMEXIT + FILL_RETURN_BUFFER %_ASM_CX, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_VMEXIT,\ + X86_FEATURE_RSB_VMEXIT_LITE + pop %_ASM_ARG2 /* @flags */ pop %_ASM_ARG1 /* @vmx */ diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 54ba20492ad1..ec53f52a06a5 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -296,6 +296,7 @@ #define X86_FEATURE_RETPOLINE_LFENCE (11*32+13) /* "" Use LFENCE for Spectre variant 2 */ #define X86_FEATURE_RETHUNK (11*32+14) /* "" Use REturn THUNK */ #define X86_FEATURE_UNRET (11*32+15) /* "" AMD BTB untrain return */ +#define X86_FEATURE_RSB_VMEXIT_LITE (11*32+17) /* "" Fill RSB on VM-Exit when EIBRS is enabled */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 407de670cd60..144dc164b759 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -148,6 +148,10 @@ * are restricted to targets in * kernel. */ +#define ARCH_CAP_PBRSB_NO BIT(24) /* + * Not susceptible to Post-Barrier + * Return Stack Buffer Predictions. + */ #define MSR_IA32_FLUSH_CMD 0x0000010b #define L1D_FLUSH BIT(0) /* From 1bea03b44ea2267988cce064f5887b01d421b28c Mon Sep 17 00:00:00 2001 From: Pawan Gupta Date: Tue, 2 Aug 2022 15:47:02 -0700 Subject: [PATCH 23/24] x86/speculation: Add LFENCE to RSB fill sequence commit ba6e31af2be96c4d0536f2152ed6f7b6c11bca47 upstream. RSB fill sequence does not have any protection for miss-prediction of conditional branch at the end of the sequence. CPU can speculatively execute code immediately after the sequence, while RSB filling hasn't completed yet. #define __FILL_RETURN_BUFFER(reg, nr, sp) \ mov $(nr/2), reg; \ 771: \ ANNOTATE_INTRA_FUNCTION_CALL; \ call 772f; \ 773: /* speculation trap */ \ UNWIND_HINT_EMPTY; \ pause; \ lfence; \ jmp 773b; \ 772: \ ANNOTATE_INTRA_FUNCTION_CALL; \ call 774f; \ 775: /* speculation trap */ \ UNWIND_HINT_EMPTY; \ pause; \ lfence; \ jmp 775b; \ 774: \ add $(BITS_PER_LONG/8) * 2, sp; \ dec reg; \ jnz 771b; <----- CPU can miss-predict here. Before RSB is filled, RETs that come in program order after this macro can be executed speculatively, making them vulnerable to RSB-based attacks. Mitigate it by adding an LFENCE after the conditional branch to prevent speculation while RSB is being filled. Suggested-by: Andrew Cooper Signed-off-by: Pawan Gupta Signed-off-by: Borislav Petkov Signed-off-by: Daniel Sneddon Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/nospec-branch.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 8ff940058a41..0acd99329923 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -60,7 +60,9 @@ 774: \ add $(BITS_PER_LONG/8) * 2, sp; \ dec reg; \ - jnz 771b; + jnz 771b; \ + /* barrier for jnz misprediction */ \ + lfence; #ifdef __ASSEMBLY__ From 6eae1503ddf94b4c3581092d566b17ed12d80f20 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 11 Aug 2022 13:06:47 +0200 Subject: [PATCH 24/24] Linux 5.10.136 Link: https://lore.kernel.org/r/20220809175512.853274191@linuxfoundation.org Tested-by: Florian Fainelli Tested-by: Linux Kernel Functional Testing Tested-by: Pavel Machek (CIP) Tested-by: Rudi Heitbaum Tested-by: Salvatore Bonaccorso Tested-by: Sudip Mukherjee Tested-by: Guenter Roeck Tested-by: Jon Hunter Tested-by: Shuah Khan Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 5f4dbcb43307..1730698124c7 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 10 -SUBLEVEL = 135 +SUBLEVEL = 136 EXTRAVERSION = NAME = Dare mighty things