From 53c8036cb715f3577a7fe1db6e6ad06e8697b36f Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 25 May 2018 23:33:19 +0200 Subject: bpf: btf: avoid -Wreturn-type warning gcc warns about a noreturn function possibly returning in some configurations: kernel/bpf/btf.c: In function 'env_type_is_resolve_sink': kernel/bpf/btf.c:729:1: error: control reaches end of non-void function [-Werror=return-type] Using BUG() instead of BUG_ON() avoids that warning and otherwise does the exact same thing. Fixes: eb3f595dab40 ("bpf: btf: Validate type reference") Signed-off-by: Arnd Bergmann Acked-by: Song Liu Signed-off-by: Daniel Borkmann --- kernel/bpf/btf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 7e90fd13b5b5..3d20aa1f4b54 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -749,7 +749,7 @@ static bool env_type_is_resolve_sink(const struct btf_verifier_env *env, !btf_type_is_array(next_type) && !btf_type_is_struct(next_type); default: - BUG_ON(1); + BUG(); } } -- cgit v1.2.3 From dc3b8ae9d271897e09b27fa4e4e0000de98590d1 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 25 May 2018 23:33:20 +0200 Subject: bpf: avoid -Wmaybe-uninitialized warning The stack_map_get_build_id_offset() function is too long for gcc to track whether 'work' may or may not be initialized at the end of it, leading to a false-positive warning: kernel/bpf/stackmap.c: In function 'stack_map_get_build_id_offset': kernel/bpf/stackmap.c:334:13: error: 'work' may be used uninitialized in this function [-Werror=maybe-uninitialized] This removes the 'in_nmi_ctx' flag and uses the state of that variable itself to see if it got initialized. Fixes: bae77c5eb5b2 ("bpf: enable stackmap with build_id in nmi context") Signed-off-by: Arnd Bergmann Acked-by: Song Liu Signed-off-by: Daniel Borkmann --- kernel/bpf/stackmap.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index b59ace0f0f09..b675a3f3d141 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -285,11 +285,10 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, { int i; struct vm_area_struct *vma; - bool in_nmi_ctx = in_nmi(); bool irq_work_busy = false; - struct stack_map_irq_work *work; + struct stack_map_irq_work *work = NULL; - if (in_nmi_ctx) { + if (in_nmi()) { work = this_cpu_ptr(&up_read_work); if (work->irq_work.flags & IRQ_WORK_BUSY) /* cannot queue more up_read, fallback */ @@ -328,7 +327,7 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, id_offs[i].status = BPF_STACK_BUILD_ID_VALID; } - if (!in_nmi_ctx) { + if (!work) { up_read(¤t->mm->mmap_sem); } else { work->sem = ¤t->mm->mmap_sem; -- cgit v1.2.3 From 1cedee13d25ab118d325f95588c1a084e9317229 Mon Sep 17 00:00:00 2001 From: Andrey Ignatov Date: Fri, 25 May 2018 08:55:23 -0700 Subject: bpf: Hooks for sys_sendmsg In addition to already existing BPF hooks for sys_bind and sys_connect, the patch provides new hooks for sys_sendmsg. It leverages existing BPF program type `BPF_PROG_TYPE_CGROUP_SOCK_ADDR` that provides access to socket itlself (properties like family, type, protocol) and user-passed `struct sockaddr *` so that BPF program can override destination IP and port for system calls such as sendto(2) or sendmsg(2) and/or assign source IP to the socket. The hooks are implemented as two new attach types: `BPF_CGROUP_UDP4_SENDMSG` and `BPF_CGROUP_UDP6_SENDMSG` for UDPv4 and UDPv6 correspondingly. UDPv4 and UDPv6 separate attach types for same reason as sys_bind and sys_connect hooks, i.e. to prevent reading from / writing to e.g. user_ip6 fields when user passes sockaddr_in since it'd be out-of-bound. The difference with already existing hooks is sys_sendmsg are implemented only for unconnected UDP. For TCP it doesn't make sense to change user-provided `struct sockaddr *` at sendto(2)/sendmsg(2) time since socket either was already connected and has source/destination set or wasn't connected and call to sendto(2)/sendmsg(2) would lead to ENOTCONN anyway. Connected UDP is already handled by sys_connect hooks that can override source/destination at connect time and use fast-path later, i.e. these hooks don't affect UDP fast-path. Rewriting source IP is implemented differently than that in sys_connect hooks. When sys_sendmsg is used with unconnected UDP it doesn't work to just bind socket to desired local IP address since source IP can be set on per-packet basis by using ancillary data (cmsg(3)). So no matter if socket is bound or not, source IP has to be rewritten on every call to sys_sendmsg. To do so two new fields are added to UAPI `struct bpf_sock_addr`; * `msg_src_ip4` to set source IPv4 for UDPv4; * `msg_src_ip6` to set source IPv6 for UDPv6. Signed-off-by: Andrey Ignatov Acked-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann --- include/linux/bpf-cgroup.h | 23 +++++++++++++++++------ include/linux/filter.h | 1 + include/uapi/linux/bpf.h | 8 ++++++++ kernel/bpf/cgroup.c | 11 ++++++++++- kernel/bpf/syscall.c | 8 ++++++++ net/core/filter.c | 39 +++++++++++++++++++++++++++++++++++++++ net/ipv4/udp.c | 20 ++++++++++++++++++-- net/ipv6/udp.c | 24 ++++++++++++++++++++++++ 8 files changed, 125 insertions(+), 9 deletions(-) (limited to 'kernel') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index de8e89a3758b..975fb4cf1bb7 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -66,7 +66,8 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk, int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, struct sockaddr *uaddr, - enum bpf_attach_type type); + enum bpf_attach_type type, + void *t_ctx); int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, struct bpf_sock_ops_kern *sock_ops, @@ -120,16 +121,18 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, ({ \ int __ret = 0; \ if (cgroup_bpf_enabled) \ - __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type); \ + __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type, \ + NULL); \ __ret; \ }) -#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, type) \ +#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, type, t_ctx) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled) { \ lock_sock(sk); \ - __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type); \ + __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type, \ + t_ctx); \ release_sock(sk); \ } \ __ret; \ @@ -151,10 +154,16 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, BPF_CGROUP_RUN_SA_PROG(sk, uaddr, BPF_CGROUP_INET6_CONNECT) #define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET4_CONNECT) + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET4_CONNECT, NULL) #define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET6_CONNECT) + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET6_CONNECT, NULL) + +#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, t_ctx) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_UDP4_SENDMSG, t_ctx) + +#define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, t_ctx) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_UDP6_SENDMSG, t_ctx) #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) \ ({ \ @@ -198,6 +207,8 @@ static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; } #define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, t_ctx) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, t_ctx) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; }) diff --git a/include/linux/filter.h b/include/linux/filter.h index d358d1815c16..d90abdaea94b 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1010,6 +1010,7 @@ struct bpf_sock_addr_kern { * only two (src and dst) are available at convert_ctx_access time */ u64 tmp_reg; + void *t_ctx; /* Attach type specific context. */ }; struct bpf_sock_ops_kern { diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 9b8c6e310e9a..cc68787f2d97 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -160,6 +160,8 @@ enum bpf_attach_type { BPF_CGROUP_INET6_CONNECT, BPF_CGROUP_INET4_POST_BIND, BPF_CGROUP_INET6_POST_BIND, + BPF_CGROUP_UDP4_SENDMSG, + BPF_CGROUP_UDP6_SENDMSG, __MAX_BPF_ATTACH_TYPE }; @@ -2363,6 +2365,12 @@ struct bpf_sock_addr { __u32 family; /* Allows 4-byte read, but no write */ __u32 type; /* Allows 4-byte read, but no write */ __u32 protocol; /* Allows 4-byte read, but no write */ + __u32 msg_src_ip4; /* Allows 1,2,4-byte read an 4-byte write. + * Stored in network byte order. + */ + __u32 msg_src_ip6[4]; /* Allows 1,2,4-byte read an 4-byte write. + * Stored in network byte order. + */ }; /* User bpf_sock_ops struct to access socket values and specify request ops diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 43171a0bb02b..f7c00bd6f8e4 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -500,6 +500,7 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); * @sk: sock struct that will use sockaddr * @uaddr: sockaddr struct provided by user * @type: The type of program to be exectuted + * @t_ctx: Pointer to attach type specific context * * socket is expected to be of type INET or INET6. * @@ -508,12 +509,15 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); */ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, struct sockaddr *uaddr, - enum bpf_attach_type type) + enum bpf_attach_type type, + void *t_ctx) { struct bpf_sock_addr_kern ctx = { .sk = sk, .uaddr = uaddr, + .t_ctx = t_ctx, }; + struct sockaddr_storage unspec; struct cgroup *cgrp; int ret; @@ -523,6 +527,11 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6) return 0; + if (!ctx.uaddr) { + memset(&unspec, 0, sizeof(unspec)); + ctx.uaddr = (struct sockaddr *)&unspec; + } + cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx, BPF_PROG_RUN); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 388d4feda348..e254526d6744 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1249,6 +1249,8 @@ bpf_prog_load_check_attach_type(enum bpf_prog_type prog_type, case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UDP4_SENDMSG: + case BPF_CGROUP_UDP6_SENDMSG: return 0; default: return -EINVAL; @@ -1565,6 +1567,8 @@ static int bpf_prog_attach(const union bpf_attr *attr) case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UDP4_SENDMSG: + case BPF_CGROUP_UDP6_SENDMSG: ptype = BPF_PROG_TYPE_CGROUP_SOCK_ADDR; break; case BPF_CGROUP_SOCK_OPS: @@ -1635,6 +1639,8 @@ static int bpf_prog_detach(const union bpf_attr *attr) case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UDP4_SENDMSG: + case BPF_CGROUP_UDP6_SENDMSG: ptype = BPF_PROG_TYPE_CGROUP_SOCK_ADDR; break; case BPF_CGROUP_SOCK_OPS: @@ -1692,6 +1698,8 @@ static int bpf_prog_query(const union bpf_attr *attr, case BPF_CGROUP_INET6_POST_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UDP4_SENDMSG: + case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_SOCK_OPS: case BPF_CGROUP_DEVICE: break; diff --git a/net/core/filter.c b/net/core/filter.c index acf1f4fb99d1..24e6ce8be567 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5299,6 +5299,7 @@ static bool sock_addr_is_valid_access(int off, int size, switch (prog->expected_attach_type) { case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET4_CONNECT: + case BPF_CGROUP_UDP4_SENDMSG: break; default: return false; @@ -5308,6 +5309,24 @@ static bool sock_addr_is_valid_access(int off, int size, switch (prog->expected_attach_type) { case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UDP6_SENDMSG: + break; + default: + return false; + } + break; + case bpf_ctx_range(struct bpf_sock_addr, msg_src_ip4): + switch (prog->expected_attach_type) { + case BPF_CGROUP_UDP4_SENDMSG: + break; + default: + return false; + } + break; + case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0], + msg_src_ip6[3]): + switch (prog->expected_attach_type) { + case BPF_CGROUP_UDP6_SENDMSG: break; default: return false; @@ -5318,6 +5337,9 @@ static bool sock_addr_is_valid_access(int off, int size, switch (off) { case bpf_ctx_range(struct bpf_sock_addr, user_ip4): case bpf_ctx_range_till(struct bpf_sock_addr, user_ip6[0], user_ip6[3]): + case bpf_ctx_range(struct bpf_sock_addr, msg_src_ip4): + case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0], + msg_src_ip6[3]): /* Only narrow read access allowed for now. */ if (type == BPF_READ) { bpf_ctx_record_field_size(info, size_default); @@ -6072,6 +6094,23 @@ static u32 sock_addr_convert_ctx_access(enum bpf_access_type type, *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, SK_FL_PROTO_SHIFT); break; + + case offsetof(struct bpf_sock_addr, msg_src_ip4): + /* Treat t_ctx as struct in_addr for msg_src_ip4. */ + SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF( + struct bpf_sock_addr_kern, struct in_addr, t_ctx, + s_addr, BPF_SIZE(si->code), 0, tmp_reg); + break; + + case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0], + msg_src_ip6[3]): + off = si->off; + off -= offsetof(struct bpf_sock_addr, msg_src_ip6[0]); + /* Treat t_ctx as struct in6_addr for msg_src_ip6. */ + SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF( + struct bpf_sock_addr_kern, struct in6_addr, t_ctx, + s6_addr32[0], BPF_SIZE(si->code), off, tmp_reg); + break; } return insn - insn_buf; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index d71f1f3e1155..3c27d00b5730 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -901,6 +901,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct inet_sock *inet = inet_sk(sk); struct udp_sock *up = udp_sk(sk); + DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name); struct flowi4 fl4_stack; struct flowi4 *fl4; int ulen = len; @@ -955,8 +956,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) /* * Get and verify the address. */ - if (msg->msg_name) { - DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name); + if (usin) { if (msg->msg_namelen < sizeof(*usin)) return -EINVAL; if (usin->sin_family != AF_INET) { @@ -1010,6 +1010,22 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) rcu_read_unlock(); } + if (cgroup_bpf_enabled && !connected) { + err = BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, + (struct sockaddr *)usin, &ipc.addr); + if (err) + goto out_free; + if (usin) { + if (usin->sin_port == 0) { + /* BPF program set invalid port. Reject it. */ + err = -EINVAL; + goto out_free; + } + daddr = usin->sin_addr.s_addr; + dport = usin->sin_port; + } + } + saddr = ipc.addr; ipc.addr = faddr = daddr; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 426c9d2b418d..9f729a7b8cf0 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1316,6 +1316,29 @@ do_udp_sendmsg: fl6.saddr = np->saddr; fl6.fl6_sport = inet->inet_sport; + if (cgroup_bpf_enabled && !connected) { + err = BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, + (struct sockaddr *)sin6, &fl6.saddr); + if (err) + goto out_no_dst; + if (sin6) { + if (ipv6_addr_v4mapped(&sin6->sin6_addr)) { + /* BPF program rewrote IPv6-only by IPv4-mapped + * IPv6. It's currently unsupported. + */ + err = -ENOTSUPP; + goto out_no_dst; + } + if (sin6->sin6_port == 0) { + /* BPF program set invalid port. Reject it. */ + err = -EINVAL; + goto out_no_dst; + } + fl6.fl6_dport = sin6->sin6_port; + fl6.daddr = sin6->sin6_addr; + } + } + final_p = fl6_update_dst(&fl6, opt, &final); if (final_p) connected = false; @@ -1395,6 +1418,7 @@ do_append_data: out: dst_release(dst); +out_no_dst: fl6_sock_release(flowlabel); txopt_put(opt_to_free); if (!err) -- cgit v1.2.3 From 170a7e3ea0709eae12c8f944b9f33c54fe80c6c1 Mon Sep 17 00:00:00 2001 From: Sean Young Date: Sun, 27 May 2018 12:24:08 +0100 Subject: bpf: bpf_prog_array_copy() should return -ENOENT if exclude_prog not found This makes is it possible for bpf prog detach to return -ENOENT. Acked-by: Yonghong Song Signed-off-by: Sean Young Signed-off-by: Daniel Borkmann --- kernel/bpf/core.c | 11 +++++++++-- kernel/trace/bpf_trace.c | 2 ++ 2 files changed, 11 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index b574dddc05b8..527587de8a67 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1616,6 +1616,7 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array, int new_prog_cnt, carry_prog_cnt = 0; struct bpf_prog **existing_prog; struct bpf_prog_array *array; + bool found_exclude = false; int new_prog_idx = 0; /* Figure out how many existing progs we need to carry over to @@ -1624,14 +1625,20 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array, if (old_array) { existing_prog = old_array->progs; for (; *existing_prog; existing_prog++) { - if (*existing_prog != exclude_prog && - *existing_prog != &dummy_bpf_prog.prog) + if (*existing_prog == exclude_prog) { + found_exclude = true; + continue; + } + if (*existing_prog != &dummy_bpf_prog.prog) carry_prog_cnt++; if (*existing_prog == include_prog) return -EEXIST; } } + if (exclude_prog && !found_exclude) + return -ENOENT; + /* How many progs (not NULL) will be in the new array? */ new_prog_cnt = carry_prog_cnt; if (include_prog) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 81fdf2fc94ac..af1486d9a0ed 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1006,6 +1006,8 @@ void perf_event_detach_bpf_prog(struct perf_event *event) old_array = event->tp_event->prog_array; ret = bpf_prog_array_copy(old_array, event->prog, NULL, &new_array); + if (ret == -ENOENT) + goto unlock; if (ret < 0) { bpf_prog_array_delete_safe(old_array, event->prog); } else { -- cgit v1.2.3 From f4364dcfc86df7c1ca47b256eaf6b6d0cdd0d936 Mon Sep 17 00:00:00 2001 From: Sean Young Date: Sun, 27 May 2018 12:24:09 +0100 Subject: media: rc: introduce BPF_PROG_LIRC_MODE2 Add support for BPF_PROG_LIRC_MODE2. This type of BPF program can call rc_keydown() to reported decoded IR scancodes, or rc_repeat() to report that the last key should be repeated. The bpf program can be attached to using the bpf(BPF_PROG_ATTACH) syscall; the target_fd must be the /dev/lircN device. Acked-by: Yonghong Song Signed-off-by: Sean Young Signed-off-by: Daniel Borkmann --- drivers/media/rc/Kconfig | 13 ++ drivers/media/rc/Makefile | 1 + drivers/media/rc/bpf-lirc.c | 313 ++++++++++++++++++++++++++++++++++++++++ drivers/media/rc/lirc_dev.c | 30 ++++ drivers/media/rc/rc-core-priv.h | 21 +++ drivers/media/rc/rc-ir-raw.c | 12 +- include/linux/bpf_lirc.h | 29 ++++ include/linux/bpf_types.h | 3 + include/uapi/linux/bpf.h | 53 ++++++- kernel/bpf/syscall.c | 7 + 10 files changed, 479 insertions(+), 3 deletions(-) create mode 100644 drivers/media/rc/bpf-lirc.c create mode 100644 include/linux/bpf_lirc.h (limited to 'kernel') diff --git a/drivers/media/rc/Kconfig b/drivers/media/rc/Kconfig index eb2c3b6eca7f..d5b35a6ba899 100644 --- a/drivers/media/rc/Kconfig +++ b/drivers/media/rc/Kconfig @@ -25,6 +25,19 @@ config LIRC passes raw IR to and from userspace, which is needed for IR transmitting (aka "blasting") and for the lirc daemon. +config BPF_LIRC_MODE2 + bool "Support for eBPF programs attached to lirc devices" + depends on BPF_SYSCALL + depends on RC_CORE=y + depends on LIRC + help + Allow attaching eBPF programs to a lirc device using the bpf(2) + syscall command BPF_PROG_ATTACH. This is supported for raw IR + receivers. + + These eBPF programs can be used to decode IR into scancodes, for + IR protocols not supported by the kernel decoders. + menuconfig RC_DECODERS bool "Remote controller decoders" depends on RC_CORE diff --git a/drivers/media/rc/Makefile b/drivers/media/rc/Makefile index 2e1c87066f6c..e0340d043fe8 100644 --- a/drivers/media/rc/Makefile +++ b/drivers/media/rc/Makefile @@ -5,6 +5,7 @@ obj-y += keymaps/ obj-$(CONFIG_RC_CORE) += rc-core.o rc-core-y := rc-main.o rc-ir-raw.o rc-core-$(CONFIG_LIRC) += lirc_dev.o +rc-core-$(CONFIG_BPF_LIRC_MODE2) += bpf-lirc.o obj-$(CONFIG_IR_NEC_DECODER) += ir-nec-decoder.o obj-$(CONFIG_IR_RC5_DECODER) += ir-rc5-decoder.o obj-$(CONFIG_IR_RC6_DECODER) += ir-rc6-decoder.o diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c new file mode 100644 index 000000000000..40826bba06b6 --- /dev/null +++ b/drivers/media/rc/bpf-lirc.c @@ -0,0 +1,313 @@ +// SPDX-License-Identifier: GPL-2.0 +// bpf-lirc.c - handles bpf +// +// Copyright (C) 2018 Sean Young + +#include +#include +#include +#include "rc-core-priv.h" + +/* + * BPF interface for raw IR + */ +const struct bpf_prog_ops lirc_mode2_prog_ops = { +}; + +BPF_CALL_1(bpf_rc_repeat, u32*, sample) +{ + struct ir_raw_event_ctrl *ctrl; + + ctrl = container_of(sample, struct ir_raw_event_ctrl, bpf_sample); + + rc_repeat(ctrl->dev); + + return 0; +} + +static const struct bpf_func_proto rc_repeat_proto = { + .func = bpf_rc_repeat, + .gpl_only = true, /* rc_repeat is EXPORT_SYMBOL_GPL */ + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; + +/* + * Currently rc-core does not support 64-bit scancodes, but there are many + * known protocols with more than 32 bits. So, define the interface as u64 + * as a future-proof. + */ +BPF_CALL_4(bpf_rc_keydown, u32*, sample, u32, protocol, u64, scancode, + u32, toggle) +{ + struct ir_raw_event_ctrl *ctrl; + + ctrl = container_of(sample, struct ir_raw_event_ctrl, bpf_sample); + + rc_keydown(ctrl->dev, protocol, scancode, toggle != 0); + + return 0; +} + +static const struct bpf_func_proto rc_keydown_proto = { + .func = bpf_rc_keydown, + .gpl_only = true, /* rc_keydown is EXPORT_SYMBOL_GPL */ + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_ANYTHING, +}; + +static const struct bpf_func_proto * +lirc_mode2_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + switch (func_id) { + case BPF_FUNC_rc_repeat: + return &rc_repeat_proto; + case BPF_FUNC_rc_keydown: + return &rc_keydown_proto; + case BPF_FUNC_map_lookup_elem: + return &bpf_map_lookup_elem_proto; + case BPF_FUNC_map_update_elem: + return &bpf_map_update_elem_proto; + case BPF_FUNC_map_delete_elem: + return &bpf_map_delete_elem_proto; + case BPF_FUNC_ktime_get_ns: + return &bpf_ktime_get_ns_proto; + case BPF_FUNC_tail_call: + return &bpf_tail_call_proto; + case BPF_FUNC_get_prandom_u32: + return &bpf_get_prandom_u32_proto; + case BPF_FUNC_trace_printk: + if (capable(CAP_SYS_ADMIN)) + return bpf_get_trace_printk_proto(); + /* fall through */ + default: + return NULL; + } +} + +static bool lirc_mode2_is_valid_access(int off, int size, + enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info) +{ + /* We have one field of u32 */ + return type == BPF_READ && off == 0 && size == sizeof(u32); +} + +const struct bpf_verifier_ops lirc_mode2_verifier_ops = { + .get_func_proto = lirc_mode2_func_proto, + .is_valid_access = lirc_mode2_is_valid_access +}; + +#define BPF_MAX_PROGS 64 + +static int lirc_bpf_attach(struct rc_dev *rcdev, struct bpf_prog *prog) +{ + struct bpf_prog_array __rcu *old_array; + struct bpf_prog_array *new_array; + struct ir_raw_event_ctrl *raw; + int ret; + + if (rcdev->driver_type != RC_DRIVER_IR_RAW) + return -EINVAL; + + ret = mutex_lock_interruptible(&ir_raw_handler_lock); + if (ret) + return ret; + + raw = rcdev->raw; + if (!raw) { + ret = -ENODEV; + goto unlock; + } + + if (raw->progs && bpf_prog_array_length(raw->progs) >= BPF_MAX_PROGS) { + ret = -E2BIG; + goto unlock; + } + + old_array = raw->progs; + ret = bpf_prog_array_copy(old_array, NULL, prog, &new_array); + if (ret < 0) + goto unlock; + + rcu_assign_pointer(raw->progs, new_array); + bpf_prog_array_free(old_array); + +unlock: + mutex_unlock(&ir_raw_handler_lock); + return ret; +} + +static int lirc_bpf_detach(struct rc_dev *rcdev, struct bpf_prog *prog) +{ + struct bpf_prog_array __rcu *old_array; + struct bpf_prog_array *new_array; + struct ir_raw_event_ctrl *raw; + int ret; + + if (rcdev->driver_type != RC_DRIVER_IR_RAW) + return -EINVAL; + + ret = mutex_lock_interruptible(&ir_raw_handler_lock); + if (ret) + return ret; + + raw = rcdev->raw; + if (!raw) { + ret = -ENODEV; + goto unlock; + } + + old_array = raw->progs; + ret = bpf_prog_array_copy(old_array, prog, NULL, &new_array); + /* + * Do not use bpf_prog_array_delete_safe() as we would end up + * with a dummy entry in the array, and the we would free the + * dummy in lirc_bpf_free() + */ + if (ret) + goto unlock; + + rcu_assign_pointer(raw->progs, new_array); + bpf_prog_array_free(old_array); +unlock: + mutex_unlock(&ir_raw_handler_lock); + return ret; +} + +void lirc_bpf_run(struct rc_dev *rcdev, u32 sample) +{ + struct ir_raw_event_ctrl *raw = rcdev->raw; + + raw->bpf_sample = sample; + + if (raw->progs) + BPF_PROG_RUN_ARRAY(raw->progs, &raw->bpf_sample, BPF_PROG_RUN); +} + +/* + * This should be called once the rc thread has been stopped, so there can be + * no concurrent bpf execution. + */ +void lirc_bpf_free(struct rc_dev *rcdev) +{ + struct bpf_prog **progs; + + if (!rcdev->raw->progs) + return; + + progs = rcu_dereference(rcdev->raw->progs)->progs; + while (*progs) + bpf_prog_put(*progs++); + + bpf_prog_array_free(rcdev->raw->progs); +} + +int lirc_prog_attach(const union bpf_attr *attr) +{ + struct bpf_prog *prog; + struct rc_dev *rcdev; + int ret; + + if (attr->attach_flags) + return -EINVAL; + + prog = bpf_prog_get_type(attr->attach_bpf_fd, + BPF_PROG_TYPE_LIRC_MODE2); + if (IS_ERR(prog)) + return PTR_ERR(prog); + + rcdev = rc_dev_get_from_fd(attr->target_fd); + if (IS_ERR(rcdev)) { + bpf_prog_put(prog); + return PTR_ERR(rcdev); + } + + ret = lirc_bpf_attach(rcdev, prog); + if (ret) + bpf_prog_put(prog); + + put_device(&rcdev->dev); + + return ret; +} + +int lirc_prog_detach(const union bpf_attr *attr) +{ + struct bpf_prog *prog; + struct rc_dev *rcdev; + int ret; + + if (attr->attach_flags) + return -EINVAL; + + prog = bpf_prog_get_type(attr->attach_bpf_fd, + BPF_PROG_TYPE_LIRC_MODE2); + if (IS_ERR(prog)) + return PTR_ERR(prog); + + rcdev = rc_dev_get_from_fd(attr->target_fd); + if (IS_ERR(rcdev)) { + bpf_prog_put(prog); + return PTR_ERR(rcdev); + } + + ret = lirc_bpf_detach(rcdev, prog); + + bpf_prog_put(prog); + put_device(&rcdev->dev); + + return ret; +} + +int lirc_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) +{ + __u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids); + struct bpf_prog_array __rcu *progs; + struct rc_dev *rcdev; + u32 cnt, flags = 0; + int ret; + + if (attr->query.query_flags) + return -EINVAL; + + rcdev = rc_dev_get_from_fd(attr->query.target_fd); + if (IS_ERR(rcdev)) + return PTR_ERR(rcdev); + + if (rcdev->driver_type != RC_DRIVER_IR_RAW) { + ret = -EINVAL; + goto put; + } + + ret = mutex_lock_interruptible(&ir_raw_handler_lock); + if (ret) + goto put; + + progs = rcdev->raw->progs; + cnt = progs ? bpf_prog_array_length(progs) : 0; + + if (copy_to_user(&uattr->query.prog_cnt, &cnt, sizeof(cnt))) { + ret = -EFAULT; + goto unlock; + } + + if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags))) { + ret = -EFAULT; + goto unlock; + } + + if (attr->query.prog_cnt != 0 && prog_ids && cnt) + ret = bpf_prog_array_copy_to_user(progs, prog_ids, cnt); + +unlock: + mutex_unlock(&ir_raw_handler_lock); +put: + put_device(&rcdev->dev); + + return ret; +} diff --git a/drivers/media/rc/lirc_dev.c b/drivers/media/rc/lirc_dev.c index 24e9fbb80e81..da7013a12a58 100644 --- a/drivers/media/rc/lirc_dev.c +++ b/drivers/media/rc/lirc_dev.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -104,6 +105,12 @@ void ir_lirc_raw_event(struct rc_dev *dev, struct ir_raw_event ev) TO_US(ev.duration), TO_STR(ev.pulse)); } + /* + * bpf does not care about the gap generated above; that exists + * for backwards compatibility + */ + lirc_bpf_run(dev, sample); + spin_lock_irqsave(&dev->lirc_fh_lock, flags); list_for_each_entry(fh, &dev->lirc_fh, list) { if (LIRC_IS_TIMEOUT(sample) && !fh->send_timeout_reports) @@ -816,4 +823,27 @@ void __exit lirc_dev_exit(void) unregister_chrdev_region(lirc_base_dev, RC_DEV_MAX); } +struct rc_dev *rc_dev_get_from_fd(int fd) +{ + struct fd f = fdget(fd); + struct lirc_fh *fh; + struct rc_dev *dev; + + if (!f.file) + return ERR_PTR(-EBADF); + + if (f.file->f_op != &lirc_fops) { + fdput(f); + return ERR_PTR(-EINVAL); + } + + fh = f.file->private_data; + dev = fh->rc; + + get_device(&dev->dev); + fdput(f); + + return dev; +} + MODULE_ALIAS("lirc_dev"); diff --git a/drivers/media/rc/rc-core-priv.h b/drivers/media/rc/rc-core-priv.h index e0e6a17460f6..eb004757038b 100644 --- a/drivers/media/rc/rc-core-priv.h +++ b/drivers/media/rc/rc-core-priv.h @@ -13,6 +13,7 @@ #define MAX_IR_EVENT_SIZE 512 #include +#include #include /** @@ -57,6 +58,11 @@ struct ir_raw_event_ctrl { /* raw decoder state follows */ struct ir_raw_event prev_ev; struct ir_raw_event this_ev; + +#ifdef CONFIG_BPF_LIRC_MODE2 + u32 bpf_sample; + struct bpf_prog_array __rcu *progs; +#endif struct nec_dec { int state; unsigned count; @@ -126,6 +132,9 @@ struct ir_raw_event_ctrl { } imon; }; +/* Mutex for locking raw IR processing and handler change */ +extern struct mutex ir_raw_handler_lock; + /* macros for IR decoders */ static inline bool geq_margin(unsigned d1, unsigned d2, unsigned margin) { @@ -288,6 +297,7 @@ void ir_lirc_raw_event(struct rc_dev *dev, struct ir_raw_event ev); void ir_lirc_scancode_event(struct rc_dev *dev, struct lirc_scancode *lsc); int ir_lirc_register(struct rc_dev *dev); void ir_lirc_unregister(struct rc_dev *dev); +struct rc_dev *rc_dev_get_from_fd(int fd); #else static inline int lirc_dev_init(void) { return 0; } static inline void lirc_dev_exit(void) {} @@ -299,4 +309,15 @@ static inline int ir_lirc_register(struct rc_dev *dev) { return 0; } static inline void ir_lirc_unregister(struct rc_dev *dev) { } #endif +/* + * bpf interface + */ +#ifdef CONFIG_BPF_LIRC_MODE2 +void lirc_bpf_free(struct rc_dev *dev); +void lirc_bpf_run(struct rc_dev *dev, u32 sample); +#else +static inline void lirc_bpf_free(struct rc_dev *dev) { } +static inline void lirc_bpf_run(struct rc_dev *dev, u32 sample) { } +#endif + #endif /* _RC_CORE_PRIV */ diff --git a/drivers/media/rc/rc-ir-raw.c b/drivers/media/rc/rc-ir-raw.c index 374f83105a23..7675b7ee5bc7 100644 --- a/drivers/media/rc/rc-ir-raw.c +++ b/drivers/media/rc/rc-ir-raw.c @@ -14,7 +14,7 @@ static LIST_HEAD(ir_raw_client_list); /* Used to handle IR raw handler extensions */ -static DEFINE_MUTEX(ir_raw_handler_lock); +DEFINE_MUTEX(ir_raw_handler_lock); static LIST_HEAD(ir_raw_handler_list); static atomic64_t available_protocols = ATOMIC64_INIT(0); @@ -621,9 +621,17 @@ void ir_raw_event_unregister(struct rc_dev *dev) list_for_each_entry(handler, &ir_raw_handler_list, list) if (handler->raw_unregister) handler->raw_unregister(dev); - mutex_unlock(&ir_raw_handler_lock); + + lirc_bpf_free(dev); ir_raw_event_free(dev); + + /* + * A user can be calling bpf(BPF_PROG_{QUERY|ATTACH|DETACH}), so + * ensure that the raw member is null on unlock; this is how + * "device gone" is checked. + */ + mutex_unlock(&ir_raw_handler_lock); } /* diff --git a/include/linux/bpf_lirc.h b/include/linux/bpf_lirc.h new file mode 100644 index 000000000000..5f8a4283092d --- /dev/null +++ b/include/linux/bpf_lirc.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _BPF_LIRC_H +#define _BPF_LIRC_H + +#include + +#ifdef CONFIG_BPF_LIRC_MODE2 +int lirc_prog_attach(const union bpf_attr *attr); +int lirc_prog_detach(const union bpf_attr *attr); +int lirc_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); +#else +static inline int lirc_prog_attach(const union bpf_attr *attr) +{ + return -EINVAL; +} + +static inline int lirc_prog_detach(const union bpf_attr *attr) +{ + return -EINVAL; +} + +static inline int lirc_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return -EINVAL; +} +#endif + +#endif /* _BPF_LIRC_H */ diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index b161e506dcfc..c5700c2d5549 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -26,6 +26,9 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT, raw_tracepoint) #ifdef CONFIG_CGROUP_BPF BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev) #endif +#ifdef CONFIG_BPF_LIRC_MODE2 +BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2) +#endif BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_ARRAY, percpu_array_map_ops) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 33f37eb0b6bf..64ac0f7a689e 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -143,6 +143,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_RAW_TRACEPOINT, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_PROG_TYPE_LWT_SEG6LOCAL, + BPF_PROG_TYPE_LIRC_MODE2, }; enum bpf_attach_type { @@ -162,6 +163,7 @@ enum bpf_attach_type { BPF_CGROUP_INET6_POST_BIND, BPF_CGROUP_UDP4_SENDMSG, BPF_CGROUP_UDP6_SENDMSG, + BPF_LIRC_MODE2, __MAX_BPF_ATTACH_TYPE }; @@ -2005,6 +2007,53 @@ union bpf_attr { * direct packet access. * Return * 0 on success, or a negative error in case of failure. + * + * int bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle) + * Description + * This helper is used in programs implementing IR decoding, to + * report a successfully decoded key press with *scancode*, + * *toggle* value in the given *protocol*. The scancode will be + * translated to a keycode using the rc keymap, and reported as + * an input key down event. After a period a key up event is + * generated. This period can be extended by calling either + * **bpf_rc_keydown** () again with the same values, or calling + * **bpf_rc_repeat** (). + * + * Some protocols include a toggle bit, in case the button was + * released and pressed again between consecutive scancodes. + * + * The *ctx* should point to the lirc sample as passed into + * the program. + * + * The *protocol* is the decoded protocol number (see + * **enum rc_proto** for some predefined values). + * + * This helper is only available is the kernel was compiled with + * the **CONFIG_BPF_LIRC_MODE2** configuration option set to + * "**y**". + * + * Return + * 0 + * + * int bpf_rc_repeat(void *ctx) + * Description + * This helper is used in programs implementing IR decoding, to + * report a successfully decoded repeat key message. This delays + * the generation of a key up event for previously generated + * key down event. + * + * Some IR protocols like NEC have a special IR message for + * repeating last button, for when a button is held down. + * + * The *ctx* should point to the lirc sample as passed into + * the program. + * + * This helper is only available is the kernel was compiled with + * the **CONFIG_BPF_LIRC_MODE2** configuration option set to + * "**y**". + * + * Return + * 0 */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2083,7 +2132,9 @@ union bpf_attr { FN(lwt_push_encap), \ FN(lwt_seg6_store_bytes), \ FN(lwt_seg6_adjust_srh), \ - FN(lwt_seg6_action), + FN(lwt_seg6_action), \ + FN(rc_repeat), \ + FN(rc_keydown), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index e254526d6744..7365d79ae00d 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -11,6 +11,7 @@ */ #include #include +#include #include #include #include @@ -1582,6 +1583,8 @@ static int bpf_prog_attach(const union bpf_attr *attr) case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, true); + case BPF_LIRC_MODE2: + return lirc_prog_attach(attr); default: return -EINVAL; } @@ -1654,6 +1657,8 @@ static int bpf_prog_detach(const union bpf_attr *attr) case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, false); + case BPF_LIRC_MODE2: + return lirc_prog_detach(attr); default: return -EINVAL; } @@ -1703,6 +1708,8 @@ static int bpf_prog_query(const union bpf_attr *attr, case BPF_CGROUP_SOCK_OPS: case BPF_CGROUP_DEVICE: break; + case BPF_LIRC_MODE2: + return lirc_prog_query(attr, uattr); default: return -EINVAL; } -- cgit v1.2.3 From 71b2c87df3ac37f5f83e166db136b0c1d065a781 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Wed, 30 May 2018 16:09:16 +0100 Subject: bpf: devmap: remove redundant assignment of dev = dev The assignment dev = dev is redundant and should be removed. Detected by CoverityScan, CID#1469486 ("Evaluation order violation") Signed-off-by: Colin Ian King Acked-by: Song Liu Signed-off-by: Alexei Starovoitov --- kernel/bpf/devmap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index ae16d0c373ef..1fe3fe60508a 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -352,7 +352,7 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, static void *dev_map_lookup_elem(struct bpf_map *map, void *key) { struct bpf_dtab_netdev *obj = __dev_map_lookup_elem(map, *(u32 *)key); - struct net_device *dev = dev = obj ? obj->dev : NULL; + struct net_device *dev = obj ? obj->dev : NULL; return dev ? &dev->ifindex : NULL; } -- cgit v1.2.3 From b9308ae696b2c35e862636eec631d95ff958c33d Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Sat, 2 Jun 2018 09:06:50 -0700 Subject: bpf: btf: Check array t->size This patch ensures array's t->size is 0. The array size is decided by its individual elem's size and the number of elements. Hence, t->size is not used and it must be 0. A test case is added to test_btf.c Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov --- kernel/bpf/btf.c | 5 +++++ tools/testing/selftests/bpf/test_btf.c | 23 +++++++++++++++++++++++ 2 files changed, 28 insertions(+) (limited to 'kernel') diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 3d20aa1f4b54..84ad532f2854 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -1342,6 +1342,11 @@ static s32 btf_array_check_meta(struct btf_verifier_env *env, return -EINVAL; } + if (t->size) { + btf_verifier_log_type(env, t, "size != 0"); + return -EINVAL; + } + /* Array elem type and index type cannot be in type void, * so !array->type and !array->index_type are not allowed. */ diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c index 35064df688c1..fd8246e84149 100644 --- a/tools/testing/selftests/bpf/test_btf.c +++ b/tools/testing/selftests/bpf/test_btf.c @@ -1178,6 +1178,29 @@ static struct btf_raw_test raw_tests[] = { .err_str = "Invalid index", }, +{ + .descr = "array test. t->size != 0\"", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* int[16] */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ARRAY, 0, 0), 1), + BTF_ARRAY_ENC(1, 1, 16), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "array_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "size != 0", +}, + { .descr = "int test. invalid int_data", .raw_types = { -- cgit v1.2.3 From 8175383f2320dbc1b4e803d857ed499ed3e76199 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Sat, 2 Jun 2018 09:06:51 -0700 Subject: bpf: btf: Ensure t->type == 0 for BTF_KIND_FWD The t->type in BTF_KIND_FWD is not used. It must be 0. This patch ensures that and also adds a test case in test_btf.c Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov --- kernel/bpf/btf.c | 21 ++++++++++++++++++++- tools/testing/selftests/bpf/test_btf.c | 22 ++++++++++++++++++++++ 2 files changed, 42 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 84ad532f2854..8653ab004c73 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -1286,8 +1286,27 @@ static struct btf_kind_operations ptr_ops = { .seq_show = btf_ptr_seq_show, }; +static s32 btf_fwd_check_meta(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left) +{ + if (btf_type_vlen(t)) { + btf_verifier_log_type(env, t, "vlen != 0"); + return -EINVAL; + } + + if (t->type) { + btf_verifier_log_type(env, t, "type != 0"); + return -EINVAL; + } + + btf_verifier_log_type(env, t, NULL); + + return 0; +} + static struct btf_kind_operations fwd_ops = { - .check_meta = btf_ref_type_check_meta, + .check_meta = btf_fwd_check_meta, .resolve = btf_df_resolve, .check_member = btf_df_check_member, .log_details = btf_ref_type_log, diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c index fd8246e84149..3619f3023088 100644 --- a/tools/testing/selftests/bpf/test_btf.c +++ b/tools/testing/selftests/bpf/test_btf.c @@ -1242,6 +1242,28 @@ static struct btf_raw_test raw_tests[] = { .err_str = "Invalid btf_info", }, +{ + .descr = "fwd test. t->type != 0\"", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* fwd type */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FWD, 0, 0), 1), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "fwd_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .btf_load_err = true, + .err_str = "type != 0", +}, + }; /* struct btf_raw_test raw_tests[] */ static const char *get_next_str(const char *start, const char *end) -- cgit v1.2.3 From 3fe2867cdf088ffb2dc5aed6cdcf757b4c62476c Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 2 Jun 2018 23:06:33 +0200 Subject: bpf: fixup error message from gpl helpers on license mismatch Stating 'proprietary program' in the error is just silly since it can also be a different open source license than that which is just not compatible. Reference: https://twitter.com/majek04/status/998531268039102465 Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Acked-by: Jesper Dangaard Brouer Acked-by: Song Liu Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 1fd9667b29f1..4f4786ea2296 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2462,7 +2462,7 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn /* eBPF programs must be GPL compatible to use GPL-ed functions */ if (!env->prog->gpl_compatible && fn->gpl_only) { - verbose(env, "cannot call GPL only function from proprietary program\n"); + verbose(env, "cannot call GPL-restricted function from non-GPL compatible program\n"); return -EINVAL; } -- cgit v1.2.3 From 4316b40914ecde3738968225af56e650e8b61938 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 2 Jun 2018 23:06:34 +0200 Subject: bpf: show prog and map id in fdinfo Its trivial and straight forward to expose it for scripts that can then use it along with bpftool in order to inspect an individual application's used maps and progs. Right now we dump some basic information in the fdinfo file but with the help of the map/prog id full introspection becomes possible now. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Acked-by: Song Liu Acked-by: Jesper Dangaard Brouer Signed-off-by: Alexei Starovoitov --- kernel/bpf/syscall.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 7365d79ae00d..0fa20624707f 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -327,13 +327,15 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) "value_size:\t%u\n" "max_entries:\t%u\n" "map_flags:\t%#x\n" - "memlock:\t%llu\n", + "memlock:\t%llu\n" + "map_id:\t%u\n", map->map_type, map->key_size, map->value_size, map->max_entries, map->map_flags, - map->pages * 1ULL << PAGE_SHIFT); + map->pages * 1ULL << PAGE_SHIFT, + map->id); if (owner_prog_type) { seq_printf(m, "owner_prog_type:\t%u\n", @@ -1070,11 +1072,13 @@ static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp) "prog_type:\t%u\n" "prog_jited:\t%u\n" "prog_tag:\t%s\n" - "memlock:\t%llu\n", + "memlock:\t%llu\n" + "prog_id:\t%u\n", prog->type, prog->jited, prog_tag, - prog->pages * 1ULL << PAGE_SHIFT); + prog->pages * 1ULL << PAGE_SHIFT, + prog->aux->id); } #endif -- cgit v1.2.3 From 09772d92cd5ad998b0d5f6f46cd1658f8cb698cf Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 2 Jun 2018 23:06:35 +0200 Subject: bpf: avoid retpoline for lookup/update/delete calls on maps While some of the BPF map lookup helpers provide a ->map_gen_lookup() callback for inlining the map lookup altogether it is not available for every map, so the remaining ones have to call bpf_map_lookup_elem() helper which does a dispatch to map->ops->map_lookup_elem(). In times of retpolines, this will control and trap speculative execution rather than letting it do its work for the indirect call and will therefore cause a slowdown. Likewise, bpf_map_update_elem() and bpf_map_delete_elem() do not have an inlined version and need to call into their map->ops->map_update_elem() resp. map->ops->map_delete_elem() handlers. Before: # bpftool prog dump xlated id 1 0: (bf) r2 = r10 1: (07) r2 += -8 2: (7a) *(u64 *)(r2 +0) = 0 3: (18) r1 = map[id:1] 5: (85) call __htab_map_lookup_elem#232656 6: (15) if r0 == 0x0 goto pc+4 7: (71) r1 = *(u8 *)(r0 +35) 8: (55) if r1 != 0x0 goto pc+1 9: (72) *(u8 *)(r0 +35) = 1 10: (07) r0 += 56 11: (15) if r0 == 0x0 goto pc+4 12: (bf) r2 = r0 13: (18) r1 = map[id:1] 15: (85) call bpf_map_delete_elem#215008 <-- indirect call via 16: (95) exit helper After: # bpftool prog dump xlated id 1 0: (bf) r2 = r10 1: (07) r2 += -8 2: (7a) *(u64 *)(r2 +0) = 0 3: (18) r1 = map[id:1] 5: (85) call __htab_map_lookup_elem#233328 6: (15) if r0 == 0x0 goto pc+4 7: (71) r1 = *(u8 *)(r0 +35) 8: (55) if r1 != 0x0 goto pc+1 9: (72) *(u8 *)(r0 +35) = 1 10: (07) r0 += 56 11: (15) if r0 == 0x0 goto pc+4 12: (bf) r2 = r0 13: (18) r1 = map[id:1] 15: (85) call htab_lru_map_delete_elem#238240 <-- direct call 16: (95) exit In all three lookup/update/delete cases however we can use the actual address of the map callback directly if we find that there's only a single path with a map pointer leading to the helper call, meaning when the map pointer has not been poisoned from verifier side. Example code can be seen above for the delete case. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Acked-by: Song Liu Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 3 +++ kernel/bpf/hashtab.c | 12 ++++++--- kernel/bpf/verifier.c | 68 ++++++++++++++++++++++++++++++++++++-------------- 3 files changed, 61 insertions(+), 22 deletions(-) (limited to 'kernel') diff --git a/include/linux/filter.h b/include/linux/filter.h index 6fd375fe7079..8e60f1e9a702 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -301,6 +301,9 @@ struct xdp_buff; /* Function call */ +#define BPF_CAST_CALL(x) \ + ((u64 (*)(u64, u64, u64, u64, u64))(x)) + #define BPF_EMIT_CALL(FUNC) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_CALL, \ diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index b76828f23b49..3ca2198a6d22 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -503,7 +503,9 @@ static u32 htab_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) struct bpf_insn *insn = insn_buf; const int ret = BPF_REG_0; - *insn++ = BPF_EMIT_CALL((u64 (*)(u64, u64, u64, u64, u64))__htab_map_lookup_elem); + BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem, + (void *(*)(struct bpf_map *map, void *key))NULL)); + *insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem)); *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 1); *insn++ = BPF_ALU64_IMM(BPF_ADD, ret, offsetof(struct htab_elem, key) + @@ -530,7 +532,9 @@ static u32 htab_lru_map_gen_lookup(struct bpf_map *map, const int ret = BPF_REG_0; const int ref_reg = BPF_REG_1; - *insn++ = BPF_EMIT_CALL((u64 (*)(u64, u64, u64, u64, u64))__htab_map_lookup_elem); + BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem, + (void *(*)(struct bpf_map *map, void *key))NULL)); + *insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem)); *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 4); *insn++ = BPF_LDX_MEM(BPF_B, ref_reg, ret, offsetof(struct htab_elem, lru_node) + @@ -1369,7 +1373,9 @@ static u32 htab_of_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn = insn_buf; const int ret = BPF_REG_0; - *insn++ = BPF_EMIT_CALL((u64 (*)(u64, u64, u64, u64, u64))__htab_map_lookup_elem); + BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem, + (void *(*)(struct bpf_map *map, void *key))NULL)); + *insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem)); *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 2); *insn++ = BPF_ALU64_IMM(BPF_ADD, ret, offsetof(struct htab_elem, key) + diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 4f4786ea2296..1dd6d5a7aa5b 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2421,8 +2421,11 @@ record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx]; if (func_id != BPF_FUNC_tail_call && - func_id != BPF_FUNC_map_lookup_elem) + func_id != BPF_FUNC_map_lookup_elem && + func_id != BPF_FUNC_map_update_elem && + func_id != BPF_FUNC_map_delete_elem) return 0; + if (meta->map_ptr == NULL) { verbose(env, "kernel subsystem misconfigured verifier\n"); return -EINVAL; @@ -5586,6 +5589,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) struct bpf_insn *insn = prog->insnsi; const struct bpf_func_proto *fn; const int insn_cnt = prog->len; + const struct bpf_map_ops *ops; struct bpf_insn_aux_data *aux; struct bpf_insn insn_buf[16]; struct bpf_prog *new_prog; @@ -5715,35 +5719,61 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) } /* BPF_EMIT_CALL() assumptions in some of the map_gen_lookup - * handlers are currently limited to 64 bit only. + * and other inlining handlers are currently limited to 64 bit + * only. */ if (prog->jit_requested && BITS_PER_LONG == 64 && - insn->imm == BPF_FUNC_map_lookup_elem) { + (insn->imm == BPF_FUNC_map_lookup_elem || + insn->imm == BPF_FUNC_map_update_elem || + insn->imm == BPF_FUNC_map_delete_elem)) { aux = &env->insn_aux_data[i + delta]; if (bpf_map_ptr_poisoned(aux)) goto patch_call_imm; map_ptr = BPF_MAP_PTR(aux->map_state); - if (!map_ptr->ops->map_gen_lookup) - goto patch_call_imm; + ops = map_ptr->ops; + if (insn->imm == BPF_FUNC_map_lookup_elem && + ops->map_gen_lookup) { + cnt = ops->map_gen_lookup(map_ptr, insn_buf); + if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) { + verbose(env, "bpf verifier is misconfigured\n"); + return -EINVAL; + } - cnt = map_ptr->ops->map_gen_lookup(map_ptr, insn_buf); - if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) { - verbose(env, "bpf verifier is misconfigured\n"); - return -EINVAL; - } + new_prog = bpf_patch_insn_data(env, i + delta, + insn_buf, cnt); + if (!new_prog) + return -ENOMEM; - new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, - cnt); - if (!new_prog) - return -ENOMEM; + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + continue; + } - delta += cnt - 1; + BUILD_BUG_ON(!__same_type(ops->map_lookup_elem, + (void *(*)(struct bpf_map *map, void *key))NULL)); + BUILD_BUG_ON(!__same_type(ops->map_delete_elem, + (int (*)(struct bpf_map *map, void *key))NULL)); + BUILD_BUG_ON(!__same_type(ops->map_update_elem, + (int (*)(struct bpf_map *map, void *key, void *value, + u64 flags))NULL)); + switch (insn->imm) { + case BPF_FUNC_map_lookup_elem: + insn->imm = BPF_CAST_CALL(ops->map_lookup_elem) - + __bpf_call_base; + continue; + case BPF_FUNC_map_update_elem: + insn->imm = BPF_CAST_CALL(ops->map_update_elem) - + __bpf_call_base; + continue; + case BPF_FUNC_map_delete_elem: + insn->imm = BPF_CAST_CALL(ops->map_delete_elem) - + __bpf_call_base; + continue; + } - /* keep walking new program and skip insns we just inserted */ - env->prog = prog = new_prog; - insn = new_prog->insnsi + i + delta; - continue; + goto patch_call_imm; } if (insn->imm == BPF_FUNC_redirect_map) { -- cgit v1.2.3 From bc23105ca0abdeed98366af01c700c2c3aff5cd5 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 2 Jun 2018 23:06:39 +0200 Subject: bpf: fix context access in tracing progs on 32 bit archs Wang reported that all the testcases for BPF_PROG_TYPE_PERF_EVENT program type in test_verifier report the following errors on x86_32: 172/p unpriv: spill/fill of different pointers ldx FAIL Unexpected error message! 0: (bf) r6 = r10 1: (07) r6 += -8 2: (15) if r1 == 0x0 goto pc+3 R1=ctx(id=0,off=0,imm=0) R6=fp-8,call_-1 R10=fp0,call_-1 3: (bf) r2 = r10 4: (07) r2 += -76 5: (7b) *(u64 *)(r6 +0) = r2 6: (55) if r1 != 0x0 goto pc+1 R1=ctx(id=0,off=0,imm=0) R2=fp-76,call_-1 R6=fp-8,call_-1 R10=fp0,call_-1 fp-8=fp 7: (7b) *(u64 *)(r6 +0) = r1 8: (79) r1 = *(u64 *)(r6 +0) 9: (79) r1 = *(u64 *)(r1 +68) invalid bpf_context access off=68 size=8 378/p check bpf_perf_event_data->sample_period byte load permitted FAIL Failed to load prog 'Permission denied'! 0: (b7) r0 = 0 1: (71) r0 = *(u8 *)(r1 +68) invalid bpf_context access off=68 size=1 379/p check bpf_perf_event_data->sample_period half load permitted FAIL Failed to load prog 'Permission denied'! 0: (b7) r0 = 0 1: (69) r0 = *(u16 *)(r1 +68) invalid bpf_context access off=68 size=2 380/p check bpf_perf_event_data->sample_period word load permitted FAIL Failed to load prog 'Permission denied'! 0: (b7) r0 = 0 1: (61) r0 = *(u32 *)(r1 +68) invalid bpf_context access off=68 size=4 381/p check bpf_perf_event_data->sample_period dword load permitted FAIL Failed to load prog 'Permission denied'! 0: (b7) r0 = 0 1: (79) r0 = *(u64 *)(r1 +68) invalid bpf_context access off=68 size=8 Reason is that struct pt_regs on x86_32 doesn't fully align to 8 byte boundary due to its size of 68 bytes. Therefore, bpf_ctx_narrow_access_ok() will then bail out saying that off & (size_default - 1) which is 68 & 7 doesn't cleanly align in the case of sample_period access from struct bpf_perf_event_data, hence verifier wrongly thinks we might be doing an unaligned access here though underlying arch can handle it just fine. Therefore adjust this down to machine size and check and rewrite the offset for narrow access on that basis. We also need to fix corresponding pe_prog_is_valid_access(), since we hit the check for off % size != 0 (e.g. 68 % 8 -> 4) in the first and last test. With that in place, progs for tracing work on x86_32. Reported-by: Wang YanQing Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Tested-by: Wang YanQing Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 30 ++++++++++++++++++++++++------ kernel/bpf/verifier.c | 3 ++- kernel/trace/bpf_trace.c | 10 ++++++++-- 3 files changed, 34 insertions(+), 9 deletions(-) (limited to 'kernel') diff --git a/include/linux/filter.h b/include/linux/filter.h index 8e60f1e9a702..45fc0f5000d8 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -639,16 +639,34 @@ static inline bool bpf_prog_was_classic(const struct bpf_prog *prog) return prog->type == BPF_PROG_TYPE_UNSPEC; } -static inline bool -bpf_ctx_narrow_access_ok(u32 off, u32 size, const u32 size_default) +static inline u32 bpf_ctx_off_adjust_machine(u32 size) +{ + const u32 size_machine = sizeof(unsigned long); + + if (size > size_machine && size % size_machine == 0) + size = size_machine; + + return size; +} + +static inline bool bpf_ctx_narrow_align_ok(u32 off, u32 size_access, + u32 size_default) { - bool off_ok; + size_default = bpf_ctx_off_adjust_machine(size_default); + size_access = bpf_ctx_off_adjust_machine(size_access); + #ifdef __LITTLE_ENDIAN - off_ok = (off & (size_default - 1)) == 0; + return (off & (size_default - 1)) == 0; #else - off_ok = (off & (size_default - 1)) + size == size_default; + return (off & (size_default - 1)) + size_access == size_default; #endif - return off_ok && size <= size_default && (size & (size - 1)) == 0; +} + +static inline bool +bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default) +{ + return bpf_ctx_narrow_align_ok(off, size, size_default) && + size <= size_default && (size & (size - 1)) == 0; } #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0])) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 1dd6d5a7aa5b..d6403b5166f4 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5349,6 +5349,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) */ is_narrower_load = size < ctx_field_size; if (is_narrower_load) { + u32 size_default = bpf_ctx_off_adjust_machine(ctx_field_size); u32 off = insn->off; u8 size_code; @@ -5363,7 +5364,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) else if (ctx_field_size == 8) size_code = BPF_DW; - insn->off = off & ~(ctx_field_size - 1); + insn->off = off & ~(size_default - 1); insn->code = BPF_LDX | BPF_MEM | size_code; } diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index af1486d9a0ed..752992ce3513 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -880,8 +880,14 @@ static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type return false; if (type != BPF_READ) return false; - if (off % size != 0) - return false; + if (off % size != 0) { + if (sizeof(unsigned long) != 4) + return false; + if (size != 8) + return false; + if (off % size != 4) + return false; + } switch (off) { case bpf_ctx_range(struct bpf_perf_event_data, sample_period): -- cgit v1.2.3 From 42b33468987bac0dd95c30f14820c7abac04a153 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Thu, 31 May 2018 10:59:47 +0200 Subject: xdp: add flags argument to ndo_xdp_xmit API This patch only change the API and reject any use of flags. This is an intermediate step that allows us to implement the flush flag operation later, for each individual driver in a separate patch. The plan is to implement flush operation via XDP_XMIT_FLUSH flag and then remove XDP_XMIT_FLAGS_NONE when done. Signed-off-by: Jesper Dangaard Brouer Acked-by: Song Liu Signed-off-by: Alexei Starovoitov --- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 6 +++++- drivers/net/ethernet/intel/i40e/i40e_txrx.h | 3 ++- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 5 ++++- drivers/net/tun.c | 8 ++++++-- drivers/net/virtio_net.c | 5 ++++- include/linux/netdevice.h | 7 ++++--- include/net/xdp.h | 5 +++++ kernel/bpf/devmap.c | 2 +- net/core/filter.c | 2 +- 9 files changed, 32 insertions(+), 11 deletions(-) (limited to 'kernel') diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 9b698c5acd05..c0451d6e0790 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -3670,7 +3670,8 @@ netdev_tx_t i40e_lan_xmit_frame(struct sk_buff *skb, struct net_device *netdev) * For error cases, a negative errno code is returned and no-frames * are transmitted (caller must handle freeing frames). **/ -int i40e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames) +int i40e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, + u32 flags) { struct i40e_netdev_priv *np = netdev_priv(dev); unsigned int queue_index = smp_processor_id(); @@ -3684,6 +3685,9 @@ int i40e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames) if (!i40e_enabled_xdp_vsi(vsi) || queue_index >= vsi->num_queue_pairs) return -ENXIO; + if (unlikely(flags & ~XDP_XMIT_FLAGS_NONE)) + return -EINVAL; + for (i = 0; i < n; i++) { struct xdp_frame *xdpf = frames[i]; int err; diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index eb8804b3d7b6..820f76db251b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -487,7 +487,8 @@ u32 i40e_get_tx_pending(struct i40e_ring *ring, bool in_sw); void i40e_detect_recover_hung(struct i40e_vsi *vsi); int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size); bool __i40e_chk_linearize(struct sk_buff *skb); -int i40e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames); +int i40e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, + u32 flags); void i40e_xdp_flush(struct net_device *dev); /** diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 031d65c4178d..87f088f4af52 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -10023,7 +10023,7 @@ static int ixgbe_xdp(struct net_device *dev, struct netdev_bpf *xdp) } static int ixgbe_xdp_xmit(struct net_device *dev, int n, - struct xdp_frame **frames) + struct xdp_frame **frames, u32 flags) { struct ixgbe_adapter *adapter = netdev_priv(dev); struct ixgbe_ring *ring; @@ -10033,6 +10033,9 @@ static int ixgbe_xdp_xmit(struct net_device *dev, int n, if (unlikely(test_bit(__IXGBE_DOWN, &adapter->state))) return -ENETDOWN; + if (unlikely(flags & ~XDP_XMIT_FLAGS_NONE)) + return -EINVAL; + /* During program transitions its possible adapter->xdp_prog is assigned * but ring has not been configured yet. In this case simply abort xmit. */ diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 2265d2ccea47..b182b8cdd219 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1285,7 +1285,8 @@ static const struct net_device_ops tun_netdev_ops = { .ndo_get_stats64 = tun_net_get_stats64, }; -static int tun_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames) +static int tun_xdp_xmit(struct net_device *dev, int n, + struct xdp_frame **frames, u32 flags) { struct tun_struct *tun = netdev_priv(dev); struct tun_file *tfile; @@ -1294,6 +1295,9 @@ static int tun_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames int cnt = n; int i; + if (unlikely(flags & ~XDP_XMIT_FLAGS_NONE)) + return -EINVAL; + rcu_read_lock(); numqueues = READ_ONCE(tun->numqueues); @@ -1332,7 +1336,7 @@ static int tun_xdp_tx(struct net_device *dev, struct xdp_buff *xdp) if (unlikely(!frame)) return -EOVERFLOW; - return tun_xdp_xmit(dev, 1, &frame); + return tun_xdp_xmit(dev, 1, &frame, 0); } static void tun_xdp_flush(struct net_device *dev) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index b2647dd5d302..4ed823625953 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -468,7 +468,7 @@ static int __virtnet_xdp_tx_xmit(struct virtnet_info *vi, } static int virtnet_xdp_xmit(struct net_device *dev, - int n, struct xdp_frame **frames) + int n, struct xdp_frame **frames, u32 flags) { struct virtnet_info *vi = netdev_priv(dev); struct receive_queue *rq = vi->rq; @@ -481,6 +481,9 @@ static int virtnet_xdp_xmit(struct net_device *dev, int err; int i; + if (unlikely(flags & ~XDP_XMIT_FLAGS_NONE)) + return -EINVAL; + qp = vi->curr_queue_pairs - vi->xdp_queue_pairs + smp_processor_id(); sq = &vi->sq[qp]; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 8452f72087ef..7f17785a59d7 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1185,13 +1185,13 @@ struct dev_ifalias { * This function is used to set or query state related to XDP on the * netdevice and manage BPF offload. See definition of * enum bpf_netdev_command for details. - * int (*ndo_xdp_xmit)(struct net_device *dev, int n, struct xdp_frame **xdp); + * int (*ndo_xdp_xmit)(struct net_device *dev, int n, struct xdp_frame **xdp, + * u32 flags); * This function is used to submit @n XDP packets for transmit on a * netdevice. Returns number of frames successfully transmitted, frames * that got dropped are freed/returned via xdp_return_frame(). * Returns negative number, means general error invoking ndo, meaning * no frames were xmit'ed and core-caller will free all frames. - * TODO: Consider add flag to allow sending flush operation. * void (*ndo_xdp_flush)(struct net_device *dev); * This function is used to inform the driver to flush a particular * xdp tx queue. Must be called on same CPU as xdp_xmit. @@ -1380,7 +1380,8 @@ struct net_device_ops { int (*ndo_bpf)(struct net_device *dev, struct netdev_bpf *bpf); int (*ndo_xdp_xmit)(struct net_device *dev, int n, - struct xdp_frame **xdp); + struct xdp_frame **xdp, + u32 flags); void (*ndo_xdp_flush)(struct net_device *dev); }; diff --git a/include/net/xdp.h b/include/net/xdp.h index 7ad779237ae8..0c45f0f943ed 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -40,6 +40,11 @@ enum xdp_mem_type { MEM_TYPE_MAX, }; +/* XDP flags for ndo_xdp_xmit */ +#define XDP_XMIT_FLAGS_NONE 0U +#define XDP_XMIT_FLUSH (1U << 0) /* doorbell signal consumer */ +#define XDP_XMIT_FLAGS_MASK XDP_XMIT_FLUSH + struct xdp_mem_info { u32 type; /* enum xdp_mem_type, but known size type */ u32 id; diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 1fe3fe60508a..037e234056f7 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -232,7 +232,7 @@ static int bq_xmit_all(struct bpf_dtab_netdev *obj, prefetch(xdpf); } - sent = dev->netdev_ops->ndo_xdp_xmit(dev, bq->count, bq->q); + sent = dev->netdev_ops->ndo_xdp_xmit(dev, bq->count, bq->q, 0); if (sent < 0) { err = sent; sent = 0; diff --git a/net/core/filter.c b/net/core/filter.c index 28e864777c0f..56e40dafdde7 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3056,7 +3056,7 @@ static int __bpf_tx_xdp(struct net_device *dev, if (unlikely(!xdpf)) return -EOVERFLOW; - sent = dev->netdev_ops->ndo_xdp_xmit(dev, 1, &xdpf); + sent = dev->netdev_ops->ndo_xdp_xmit(dev, 1, &xdpf, 0); if (sent <= 0) return sent; dev->netdev_ops->ndo_xdp_flush(dev); -- cgit v1.2.3 From c1ece6b245bd12a57124da78abafbf8a511394d6 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Thu, 31 May 2018 11:00:23 +0200 Subject: bpf/xdp: devmap can avoid calling ndo_xdp_flush The XDP_REDIRECT map devmap can avoid using ndo_xdp_flush, by instead instructing ndo_xdp_xmit to flush via XDP_XMIT_FLUSH flag in appropriate places. Notice after this patch it is possible to remove ndo_xdp_flush completely, as this is the last user of ndo_xdp_flush. This is left for later patches, to keep driver changes separate. Signed-off-by: Jesper Dangaard Brouer Acked-by: Song Liu Signed-off-by: Alexei Starovoitov --- kernel/bpf/devmap.c | 19 ++++++------------- 1 file changed, 6 insertions(+), 13 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 037e234056f7..a7cc7b3494a9 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -217,7 +217,7 @@ void __dev_map_insert_ctx(struct bpf_map *map, u32 bit) } static int bq_xmit_all(struct bpf_dtab_netdev *obj, - struct xdp_bulk_queue *bq) + struct xdp_bulk_queue *bq, u32 flags) { struct net_device *dev = obj->dev; int sent = 0, drops = 0, err = 0; @@ -232,7 +232,7 @@ static int bq_xmit_all(struct bpf_dtab_netdev *obj, prefetch(xdpf); } - sent = dev->netdev_ops->ndo_xdp_xmit(dev, bq->count, bq->q, 0); + sent = dev->netdev_ops->ndo_xdp_xmit(dev, bq->count, bq->q, flags); if (sent < 0) { err = sent; sent = 0; @@ -276,7 +276,6 @@ void __dev_map_flush(struct bpf_map *map) for_each_set_bit(bit, bitmap, map->max_entries) { struct bpf_dtab_netdev *dev = READ_ONCE(dtab->netdev_map[bit]); struct xdp_bulk_queue *bq; - struct net_device *netdev; /* This is possible if the dev entry is removed by user space * between xdp redirect and flush op. @@ -287,10 +286,7 @@ void __dev_map_flush(struct bpf_map *map) __clear_bit(bit, bitmap); bq = this_cpu_ptr(dev->bulkq); - bq_xmit_all(dev, bq); - netdev = dev->dev; - if (likely(netdev->netdev_ops->ndo_xdp_flush)) - netdev->netdev_ops->ndo_xdp_flush(netdev); + bq_xmit_all(dev, bq, XDP_XMIT_FLUSH); } } @@ -320,7 +316,7 @@ static int bq_enqueue(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf, struct xdp_bulk_queue *bq = this_cpu_ptr(obj->bulkq); if (unlikely(bq->count == DEV_MAP_BULK_SIZE)) - bq_xmit_all(obj, bq); + bq_xmit_all(obj, bq, 0); /* Ingress dev_rx will be the same for all xdp_frame's in * bulk_queue, because bq stored per-CPU and must be flushed @@ -359,8 +355,7 @@ static void *dev_map_lookup_elem(struct bpf_map *map, void *key) static void dev_map_flush_old(struct bpf_dtab_netdev *dev) { - if (dev->dev->netdev_ops->ndo_xdp_flush) { - struct net_device *fl = dev->dev; + if (dev->dev->netdev_ops->ndo_xdp_xmit) { struct xdp_bulk_queue *bq; unsigned long *bitmap; @@ -371,9 +366,7 @@ static void dev_map_flush_old(struct bpf_dtab_netdev *dev) __clear_bit(dev->bit, bitmap); bq = per_cpu_ptr(dev->bulkq, cpu); - bq_xmit_all(dev, bq); - - fl->netdev_ops->ndo_xdp_flush(dev->dev); + bq_xmit_all(dev, bq, XDP_XMIT_FLUSH); } } } -- cgit v1.2.3 From bf6fa2c893c5237b48569a13fa3c673041430b6c Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sun, 3 Jun 2018 15:59:41 -0700 Subject: bpf: implement bpf_get_current_cgroup_id() helper bpf has been used extensively for tracing. For example, bcc contains an almost full set of bpf-based tools to trace kernel and user functions/events. Most tracing tools are currently either filtered based on pid or system-wide. Containers have been used quite extensively in industry and cgroup is often used together to provide resource isolation and protection. Several processes may run inside the same container. It is often desirable to get container-level tracing results as well, e.g. syscall count, function count, I/O activity, etc. This patch implements a new helper, bpf_get_current_cgroup_id(), which will return cgroup id based on the cgroup within which the current task is running. The later patch will provide an example to show that userspace can get the same cgroup id so it could configure a filter or policy in the bpf program based on task cgroup id. The helper is currently implemented for tracing. It can be added to other program types as well when needed. Acked-by: Alexei Starovoitov Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 8 +++++++- kernel/bpf/core.c | 1 + kernel/bpf/helpers.c | 15 +++++++++++++++ kernel/trace/bpf_trace.c | 2 ++ 5 files changed, 26 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index bbe297436e5d..995c3b1e59bf 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -746,6 +746,7 @@ extern const struct bpf_func_proto bpf_get_stackid_proto; extern const struct bpf_func_proto bpf_get_stack_proto; extern const struct bpf_func_proto bpf_sock_map_update_proto; extern const struct bpf_func_proto bpf_sock_hash_update_proto; +extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto; /* Shared helpers among cBPF and eBPF. */ void bpf_user_rnd_init_once(void); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index f0b6608b1f1c..18712b0dbfe7 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2070,6 +2070,11 @@ union bpf_attr { * **CONFIG_SOCK_CGROUP_DATA** configuration option. * Return * The id is returned or 0 in case the id could not be retrieved. + * + * u64 bpf_get_current_cgroup_id(void) + * Return + * A 64-bit integer containing the current cgroup id based + * on the cgroup within which the current task is running. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2151,7 +2156,8 @@ union bpf_attr { FN(lwt_seg6_action), \ FN(rc_repeat), \ FN(rc_keydown), \ - FN(skb_cgroup_id), + FN(skb_cgroup_id), \ + FN(get_current_cgroup_id), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 527587de8a67..9f1493705f40 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1765,6 +1765,7 @@ const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak; const struct bpf_func_proto bpf_get_current_comm_proto __weak; const struct bpf_func_proto bpf_sock_map_update_proto __weak; const struct bpf_func_proto bpf_sock_hash_update_proto __weak; +const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak; const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void) { diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 3d24e238221e..73065e2d23c2 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -179,3 +179,18 @@ const struct bpf_func_proto bpf_get_current_comm_proto = { .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE, }; + +#ifdef CONFIG_CGROUPS +BPF_CALL_0(bpf_get_current_cgroup_id) +{ + struct cgroup *cgrp = task_dfl_cgroup(current); + + return cgrp->kn->id.id; +} + +const struct bpf_func_proto bpf_get_current_cgroup_id_proto = { + .func = bpf_get_current_cgroup_id, + .gpl_only = false, + .ret_type = RET_INTEGER, +}; +#endif diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 752992ce3513..e2ab5b7f29d2 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -564,6 +564,8 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_prandom_u32_proto; case BPF_FUNC_probe_read_str: return &bpf_probe_read_str_proto; + case BPF_FUNC_get_current_cgroup_id: + return &bpf_get_current_cgroup_id_proto; default: return NULL; } -- cgit v1.2.3 From 34ea38ca27991466a8fff849514b4181b42ae2eb Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Mon, 4 Jun 2018 08:53:41 -0700 Subject: bpf: guard bpf_get_current_cgroup_id() with CONFIG_CGROUPS Commit bf6fa2c893c5 ("bpf: implement bpf_get_current_cgroup_id() helper") introduced a new helper bpf_get_current_cgroup_id(). The helper has a dependency on CONFIG_CGROUPS. When CONFIG_CGROUPS is not defined, using the helper will result the following verifier error: kernel subsystem misconfigured func bpf_get_current_cgroup_id#80 which is hard for users to interpret. Guarding the reference to bpf_get_current_cgroup_id_proto with CONFIG_CGROUPS will result in below better message: unknown func bpf_get_current_cgroup_id#80 Fixes: bf6fa2c893c5 ("bpf: implement bpf_get_current_cgroup_id() helper") Suggested-by: Daniel Borkmann Signed-off-by: Yonghong Song Signed-off-by: Daniel Borkmann --- kernel/trace/bpf_trace.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index e2ab5b7f29d2..0ae6829804bc 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -564,8 +564,10 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_prandom_u32_proto; case BPF_FUNC_probe_read_str: return &bpf_probe_read_str_proto; +#ifdef CONFIG_CGROUPS case BPF_FUNC_get_current_cgroup_id: return &bpf_get_current_cgroup_id_proto; +#endif default: return NULL; } -- cgit v1.2.3