From e2dcac2f58f5a95ab092d1da237ffdc0da1832cf Mon Sep 17 00:00:00 2001 From: Jinghao Jia Date: Fri, 29 Jul 2022 20:17:13 +0000 Subject: BPF: Fix potential bad pointer dereference in bpf_sys_bpf() The bpf_sys_bpf() helper function allows an eBPF program to load another eBPF program from within the kernel. In this case the argument union bpf_attr pointer (as well as the insns and license pointers inside) is a kernel address instead of a userspace address (which is the case of a usual bpf() syscall). To make the memory copying process in the syscall work in both cases, bpfptr_t was introduced to wrap around the pointer and distinguish its origin. Specifically, when copying memory contents from a bpfptr_t, a copy_from_user() is performed in case of a userspace address and a memcpy() is performed for a kernel address. This can lead to problems because the in-kernel pointer is never checked for validity. The problem happens when an eBPF syscall program tries to call bpf_sys_bpf() to load a program but provides a bad insns pointer -- say 0xdeadbeef -- in the bpf_attr union. The helper calls __sys_bpf() which would then call bpf_prog_load() to load the program. bpf_prog_load() is responsible for copying the eBPF instructions to the newly allocated memory for the program; it creates a kernel bpfptr_t for insns and invokes copy_from_bpfptr(). Internally, all bpfptr_t operations are backed by the corresponding sockptr_t operations, which performs direct memcpy() on kernel pointers for copy_from/strncpy_from operations. Therefore, the code is always happy to dereference the bad pointer to trigger a un-handle-able page fault and in turn an oops. However, this is not supposed to happen because at that point the eBPF program is already verified and should not cause a memory error. Sample KASAN trace: [ 25.685056][ T228] ================================================================== [ 25.685680][ T228] BUG: KASAN: user-memory-access in copy_from_bpfptr+0x21/0x30 [ 25.686210][ T228] Read of size 80 at addr 00000000deadbeef by task poc/228 [ 25.686732][ T228] [ 25.686893][ T228] CPU: 3 PID: 228 Comm: poc Not tainted 5.19.0-rc7 #7 [ 25.687375][ T228] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS d55cb5a 04/01/2014 [ 25.687991][ T228] Call Trace: [ 25.688223][ T228] [ 25.688429][ T228] dump_stack_lvl+0x73/0x9e [ 25.688747][ T228] print_report+0xea/0x200 [ 25.689061][ T228] ? copy_from_bpfptr+0x21/0x30 [ 25.689401][ T228] ? _printk+0x54/0x6e [ 25.689693][ T228] ? _raw_spin_lock_irqsave+0x70/0xd0 [ 25.690071][ T228] ? copy_from_bpfptr+0x21/0x30 [ 25.690412][ T228] kasan_report+0xb5/0xe0 [ 25.690716][ T228] ? copy_from_bpfptr+0x21/0x30 [ 25.691059][ T228] kasan_check_range+0x2bd/0x2e0 [ 25.691405][ T228] ? copy_from_bpfptr+0x21/0x30 [ 25.691734][ T228] memcpy+0x25/0x60 [ 25.692000][ T228] copy_from_bpfptr+0x21/0x30 [ 25.692328][ T228] bpf_prog_load+0x604/0x9e0 [ 25.692653][ T228] ? cap_capable+0xb4/0xe0 [ 25.692956][ T228] ? security_capable+0x4f/0x70 [ 25.693324][ T228] __sys_bpf+0x3af/0x580 [ 25.693635][ T228] bpf_sys_bpf+0x45/0x240 [ 25.693937][ T228] bpf_prog_f0ec79a5a3caca46_bpf_func1+0xa2/0xbd [ 25.694394][ T228] bpf_prog_run_pin_on_cpu+0x2f/0xb0 [ 25.694756][ T228] bpf_prog_test_run_syscall+0x146/0x1c0 [ 25.695144][ T228] bpf_prog_test_run+0x172/0x190 [ 25.695487][ T228] __sys_bpf+0x2c5/0x580 [ 25.695776][ T228] __x64_sys_bpf+0x3a/0x50 [ 25.696084][ T228] do_syscall_64+0x60/0x90 [ 25.696393][ T228] ? fpregs_assert_state_consistent+0x50/0x60 [ 25.696815][ T228] ? exit_to_user_mode_prepare+0x36/0xa0 [ 25.697202][ T228] ? syscall_exit_to_user_mode+0x20/0x40 [ 25.697586][ T228] ? do_syscall_64+0x6e/0x90 [ 25.697899][ T228] entry_SYSCALL_64_after_hwframe+0x63/0xcd [ 25.698312][ T228] RIP: 0033:0x7f6d543fb759 [ 25.698624][ T228] Code: 08 5b 89 e8 5d c3 66 2e 0f 1f 84 00 00 00 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 97 a6 0e 00 f7 d8 64 89 01 48 [ 25.699946][ T228] RSP: 002b:00007ffc3df78468 EFLAGS: 00000287 ORIG_RAX: 0000000000000141 [ 25.700526][ T228] RAX: ffffffffffffffda RBX: 00007ffc3df78628 RCX: 00007f6d543fb759 [ 25.701071][ T228] RDX: 0000000000000090 RSI: 00007ffc3df78478 RDI: 000000000000000a [ 25.701636][ T228] RBP: 00007ffc3df78510 R08: 0000000000000000 R09: 0000000000300000 [ 25.702191][ T228] R10: 0000000000000005 R11: 0000000000000287 R12: 0000000000000000 [ 25.702736][ T228] R13: 00007ffc3df78638 R14: 000055a1584aca68 R15: 00007f6d5456a000 [ 25.703282][ T228] [ 25.703490][ T228] ================================================================== [ 25.704050][ T228] Disabling lock debugging due to kernel taint Update copy_from_bpfptr() and strncpy_from_bpfptr() so that: - for a kernel pointer, it uses the safe copy_from_kernel_nofault() and strncpy_from_kernel_nofault() functions. - for a userspace pointer, it performs copy_from_user() and strncpy_from_user(). Fixes: af2ac3e13e45 ("bpf: Prepare bpf syscall to be used from kernel and user space.") Link: https://lore.kernel.org/bpf/20220727132905.45166-1-jinghao@linux.ibm.com/ Signed-off-by: Jinghao Jia Acked-by: Yonghong Song Link: https://lore.kernel.org/r/20220729201713.88688-1-jinghao@linux.ibm.com Signed-off-by: Alexei Starovoitov --- include/linux/bpfptr.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpfptr.h b/include/linux/bpfptr.h index 46e1757d06a3..79b2f78eec1a 100644 --- a/include/linux/bpfptr.h +++ b/include/linux/bpfptr.h @@ -49,7 +49,9 @@ static inline void bpfptr_add(bpfptr_t *bpfptr, size_t val) static inline int copy_from_bpfptr_offset(void *dst, bpfptr_t src, size_t offset, size_t size) { - return copy_from_sockptr_offset(dst, (sockptr_t) src, offset, size); + if (!bpfptr_is_kernel(src)) + return copy_from_user(dst, src.user + offset, size); + return copy_from_kernel_nofault(dst, src.kernel + offset, size); } static inline int copy_from_bpfptr(void *dst, bpfptr_t src, size_t size) @@ -78,7 +80,9 @@ static inline void *kvmemdup_bpfptr(bpfptr_t src, size_t len) static inline long strncpy_from_bpfptr(char *dst, bpfptr_t src, size_t count) { - return strncpy_from_sockptr(dst, (sockptr_t) src, count); + if (bpfptr_is_kernel(src)) + return strncpy_from_kernel_nofault(dst, src.kernel, count); + return strncpy_from_user(dst, src.user, count); } #endif /* _LINUX_BPFPTR_H */ -- cgit v1.3-8-gc7d7 From 2a0133723f9ebeb751cfce19f74ec07e108bef1f Mon Sep 17 00:00:00 2001 From: Hawkins Jiawei Date: Fri, 5 Aug 2022 15:48:34 +0800 Subject: net: fix refcount bug in sk_psock_get (2) Syzkaller reports refcount bug as follows: ------------[ cut here ]------------ refcount_t: saturated; leaking memory. WARNING: CPU: 1 PID: 3605 at lib/refcount.c:19 refcount_warn_saturate+0xf4/0x1e0 lib/refcount.c:19 Modules linked in: CPU: 1 PID: 3605 Comm: syz-executor208 Not tainted 5.18.0-syzkaller-03023-g7e062cda7d90 #0 __refcount_add_not_zero include/linux/refcount.h:163 [inline] __refcount_inc_not_zero include/linux/refcount.h:227 [inline] refcount_inc_not_zero include/linux/refcount.h:245 [inline] sk_psock_get+0x3bc/0x410 include/linux/skmsg.h:439 tls_data_ready+0x6d/0x1b0 net/tls/tls_sw.c:2091 tcp_data_ready+0x106/0x520 net/ipv4/tcp_input.c:4983 tcp_data_queue+0x25f2/0x4c90 net/ipv4/tcp_input.c:5057 tcp_rcv_state_process+0x1774/0x4e80 net/ipv4/tcp_input.c:6659 tcp_v4_do_rcv+0x339/0x980 net/ipv4/tcp_ipv4.c:1682 sk_backlog_rcv include/net/sock.h:1061 [inline] __release_sock+0x134/0x3b0 net/core/sock.c:2849 release_sock+0x54/0x1b0 net/core/sock.c:3404 inet_shutdown+0x1e0/0x430 net/ipv4/af_inet.c:909 __sys_shutdown_sock net/socket.c:2331 [inline] __sys_shutdown_sock net/socket.c:2325 [inline] __sys_shutdown+0xf1/0x1b0 net/socket.c:2343 __do_sys_shutdown net/socket.c:2351 [inline] __se_sys_shutdown net/socket.c:2349 [inline] __x64_sys_shutdown+0x50/0x70 net/socket.c:2349 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x46/0xb0 During SMC fallback process in connect syscall, kernel will replaces TCP with SMC. In order to forward wakeup smc socket waitqueue after fallback, kernel will sets clcsk->sk_user_data to origin smc socket in smc_fback_replace_callbacks(). Later, in shutdown syscall, kernel will calls sk_psock_get(), which treats the clcsk->sk_user_data as psock type, triggering the refcnt warning. So, the root cause is that smc and psock, both will use sk_user_data field. So they will mismatch this field easily. This patch solves it by using another bit(defined as SK_USER_DATA_PSOCK) in PTRMASK, to mark whether sk_user_data points to a psock object or not. This patch depends on a PTRMASK introduced in commit f1ff5ce2cd5e ("net, sk_msg: Clear sk_user_data pointer on clone if tagged"). For there will possibly be more flags in the sk_user_data field, this patch also refactor sk_user_data flags code to be more generic to improve its maintainability. Reported-and-tested-by: syzbot+5f26f85569bd179c18ce@syzkaller.appspotmail.com Suggested-by: Jakub Kicinski Acked-by: Wen Gu Signed-off-by: Hawkins Jiawei Reviewed-by: Jakub Sitnicki Signed-off-by: Jakub Kicinski --- include/linux/skmsg.h | 3 ++- include/net/sock.h | 68 ++++++++++++++++++++++++++++++++++++--------------- net/core/skmsg.c | 4 ++- 3 files changed, 53 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 153b6dec9b6a..48f4b645193b 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -278,7 +278,8 @@ static inline void sk_msg_sg_copy_clear(struct sk_msg *msg, u32 start) static inline struct sk_psock *sk_psock(const struct sock *sk) { - return rcu_dereference_sk_user_data(sk); + return __rcu_dereference_sk_user_data_with_flags(sk, + SK_USER_DATA_PSOCK); } static inline void sk_psock_set_state(struct sk_psock *psock, diff --git a/include/net/sock.h b/include/net/sock.h index a7273b289188..05a1bbdf5805 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -545,14 +545,26 @@ enum sk_pacing { SK_PACING_FQ = 2, }; -/* Pointer stored in sk_user_data might not be suitable for copying - * when cloning the socket. For instance, it can point to a reference - * counted object. sk_user_data bottom bit is set if pointer must not - * be copied. +/* flag bits in sk_user_data + * + * - SK_USER_DATA_NOCOPY: Pointer stored in sk_user_data might + * not be suitable for copying when cloning the socket. For instance, + * it can point to a reference counted object. sk_user_data bottom + * bit is set if pointer must not be copied. + * + * - SK_USER_DATA_BPF: Mark whether sk_user_data field is + * managed/owned by a BPF reuseport array. This bit should be set + * when sk_user_data's sk is added to the bpf's reuseport_array. + * + * - SK_USER_DATA_PSOCK: Mark whether pointer stored in + * sk_user_data points to psock type. This bit should be set + * when sk_user_data is assigned to a psock object. */ #define SK_USER_DATA_NOCOPY 1UL -#define SK_USER_DATA_BPF 2UL /* Managed by BPF */ -#define SK_USER_DATA_PTRMASK ~(SK_USER_DATA_NOCOPY | SK_USER_DATA_BPF) +#define SK_USER_DATA_BPF 2UL +#define SK_USER_DATA_PSOCK 4UL +#define SK_USER_DATA_PTRMASK ~(SK_USER_DATA_NOCOPY | SK_USER_DATA_BPF |\ + SK_USER_DATA_PSOCK) /** * sk_user_data_is_nocopy - Test if sk_user_data pointer must not be copied @@ -565,24 +577,40 @@ static inline bool sk_user_data_is_nocopy(const struct sock *sk) #define __sk_user_data(sk) ((*((void __rcu **)&(sk)->sk_user_data))) +/** + * __rcu_dereference_sk_user_data_with_flags - return the pointer + * only if argument flags all has been set in sk_user_data. Otherwise + * return NULL + * + * @sk: socket + * @flags: flag bits + */ +static inline void * +__rcu_dereference_sk_user_data_with_flags(const struct sock *sk, + uintptr_t flags) +{ + uintptr_t sk_user_data = (uintptr_t)rcu_dereference(__sk_user_data(sk)); + + WARN_ON_ONCE(flags & SK_USER_DATA_PTRMASK); + + if ((sk_user_data & flags) == flags) + return (void *)(sk_user_data & SK_USER_DATA_PTRMASK); + return NULL; +} + #define rcu_dereference_sk_user_data(sk) \ + __rcu_dereference_sk_user_data_with_flags(sk, 0) +#define __rcu_assign_sk_user_data_with_flags(sk, ptr, flags) \ ({ \ - void *__tmp = rcu_dereference(__sk_user_data((sk))); \ - (void *)((uintptr_t)__tmp & SK_USER_DATA_PTRMASK); \ -}) -#define rcu_assign_sk_user_data(sk, ptr) \ -({ \ - uintptr_t __tmp = (uintptr_t)(ptr); \ - WARN_ON_ONCE(__tmp & ~SK_USER_DATA_PTRMASK); \ - rcu_assign_pointer(__sk_user_data((sk)), __tmp); \ -}) -#define rcu_assign_sk_user_data_nocopy(sk, ptr) \ -({ \ - uintptr_t __tmp = (uintptr_t)(ptr); \ - WARN_ON_ONCE(__tmp & ~SK_USER_DATA_PTRMASK); \ + uintptr_t __tmp1 = (uintptr_t)(ptr), \ + __tmp2 = (uintptr_t)(flags); \ + WARN_ON_ONCE(__tmp1 & ~SK_USER_DATA_PTRMASK); \ + WARN_ON_ONCE(__tmp2 & SK_USER_DATA_PTRMASK); \ rcu_assign_pointer(__sk_user_data((sk)), \ - __tmp | SK_USER_DATA_NOCOPY); \ + __tmp1 | __tmp2); \ }) +#define rcu_assign_sk_user_data(sk, ptr) \ + __rcu_assign_sk_user_data_with_flags(sk, ptr, 0) static inline struct net *sock_net(const struct sock *sk) diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 81627892bdd4..57e942a6431a 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -739,7 +739,9 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node) sk_psock_set_state(psock, SK_PSOCK_TX_ENABLED); refcount_set(&psock->refcnt, 1); - rcu_assign_sk_user_data_nocopy(sk, psock); + __rcu_assign_sk_user_data_with_flags(sk, psock, + SK_USER_DATA_NOCOPY | + SK_USER_DATA_PSOCK); sock_hold(sk); out: -- cgit v1.3-8-gc7d7