From a9b59159d338d414acaa8e2f569d129d51c76452 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Wed, 24 Jun 2020 15:20:39 -0700 Subject: bpf: Do not allow btf_ctx_access with __int128 types To ensure btf_ctx_access() is safe the verifier checks that the BTF arg type is an int, enum, or pointer. When the function does the BTF arg lookup it uses the calculation 'arg = off / 8' using the fact that registers are 8B. This requires that the first arg is in the first reg, the second in the second, and so on. However, for __int128 the arg will consume two registers by default LLVM implementation. So this will cause the arg layout assumed by the 'arg = off / 8' calculation to be incorrect. Because __int128 is uncommon this patch applies the easiest fix and will force int types to be sizeof(u64) or smaller so that they will fit in a single register. v2: remove unneeded parens per Andrii's feedback Fixes: 9e15db66136a1 ("bpf: Implement accurate raw_tp context access via BTF") Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/159303723962.11287.13309537171132420717.stgit@john-Precision-5820-Tower --- include/linux/btf.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/btf.h b/include/linux/btf.h index 5c1ea99b480f..8b81fbb4497c 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -82,6 +82,11 @@ static inline bool btf_type_is_int(const struct btf_type *t) return BTF_INFO_KIND(t->info) == BTF_KIND_INT; } +static inline bool btf_type_is_small_int(const struct btf_type *t) +{ + return btf_type_is_int(t) && t->size <= sizeof(u64); +} + static inline bool btf_type_is_enum(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM; -- cgit v1.2.3 From 3aa91625007807bfca4155df1867a5c924a08662 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Jun 2020 15:03:56 +0200 Subject: dma-mapping: Add a new dma_need_sync API Add a new API to check if calls to dma_sync_single_for_{device,cpu} are required for a given DMA streaming mapping. Signed-off-by: Christoph Hellwig Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20200629130359.2690853-2-hch@lst.de --- Documentation/core-api/dma-api.rst | 8 ++++++++ include/linux/dma-direct.h | 1 + include/linux/dma-mapping.h | 5 +++++ kernel/dma/direct.c | 6 ++++++ kernel/dma/mapping.c | 10 ++++++++++ 5 files changed, 30 insertions(+) (limited to 'include/linux') diff --git a/Documentation/core-api/dma-api.rst b/Documentation/core-api/dma-api.rst index 2d8d2fed7317..f41620439ef3 100644 --- a/Documentation/core-api/dma-api.rst +++ b/Documentation/core-api/dma-api.rst @@ -204,6 +204,14 @@ Returns the maximum size of a mapping for the device. The size parameter of the mapping functions like dma_map_single(), dma_map_page() and others should not be larger than the returned value. +:: + + bool + dma_need_sync(struct device *dev, dma_addr_t dma_addr); + +Returns %true if dma_sync_single_for_{device,cpu} calls are required to +transfer memory ownership. Returns %false if those calls can be skipped. + :: unsigned long diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 136f984df0d9..8b006730687b 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -87,4 +87,5 @@ int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma, void *cpu_addr, dma_addr_t dma_addr, size_t size, unsigned long attrs); int dma_direct_supported(struct device *dev, u64 mask); +bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr); #endif /* _LINUX_DMA_DIRECT_H */ diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 78f677cf45ab..a33ed3954ed4 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -461,6 +461,7 @@ int dma_set_mask(struct device *dev, u64 mask); int dma_set_coherent_mask(struct device *dev, u64 mask); u64 dma_get_required_mask(struct device *dev); size_t dma_max_mapping_size(struct device *dev); +bool dma_need_sync(struct device *dev, dma_addr_t dma_addr); unsigned long dma_get_merge_boundary(struct device *dev); #else /* CONFIG_HAS_DMA */ static inline dma_addr_t dma_map_page_attrs(struct device *dev, @@ -571,6 +572,10 @@ static inline size_t dma_max_mapping_size(struct device *dev) { return 0; } +static inline bool dma_need_sync(struct device *dev, dma_addr_t dma_addr) +{ + return false; +} static inline unsigned long dma_get_merge_boundary(struct device *dev) { return 0; diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 0a4881e59aa7..ecb922a0bfa0 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -530,3 +530,9 @@ size_t dma_direct_max_mapping_size(struct device *dev) return swiotlb_max_mapping_size(dev); return SIZE_MAX; } + +bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr) +{ + return !dev_is_dma_coherent(dev) || + is_swiotlb_buffer(dma_to_phys(dev, dma_addr)); +} diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 98e3d873792e..a8c18c9a796f 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -397,6 +397,16 @@ size_t dma_max_mapping_size(struct device *dev) } EXPORT_SYMBOL_GPL(dma_max_mapping_size); +bool dma_need_sync(struct device *dev, dma_addr_t dma_addr) +{ + const struct dma_map_ops *ops = get_dma_ops(dev); + + if (dma_is_direct(ops)) + return dma_direct_need_sync(dev, dma_addr); + return ops->sync_single_for_cpu || ops->sync_single_for_device; +} +EXPORT_SYMBOL_GPL(dma_need_sync); + unsigned long dma_get_merge_boundary(struct device *dev) { const struct dma_map_ops *ops = get_dma_ops(dev); -- cgit v1.2.3 From 4ac2add65974e4efafb8d4ccd8fc5660417ea312 Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Mon, 29 Jun 2020 10:56:26 +0100 Subject: bpf: flow_dissector: Check value of unused flags to BPF_PROG_DETACH Using BPF_PROG_DETACH on a flow dissector program supports neither attach_flags nor attach_bpf_fd. Yet no value is enforced for them. Enforce that attach_flags are zero, and require the current program to be passed via attach_bpf_fd. This allows us to remove the check for CAP_SYS_ADMIN, since userspace can now no longer remove arbitrary flow dissector programs. Fixes: b27f7bb590ba ("flow_dissector: Move out netns_bpf prog callbacks") Signed-off-by: Lorenz Bauer Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200629095630.7933-3-lmb@cloudflare.com --- include/linux/bpf-netns.h | 5 +++-- kernel/bpf/net_namespace.c | 19 +++++++++++++++---- kernel/bpf/syscall.c | 4 +--- 3 files changed, 19 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-netns.h b/include/linux/bpf-netns.h index 4052d649f36d..47d5b0c708c9 100644 --- a/include/linux/bpf-netns.h +++ b/include/linux/bpf-netns.h @@ -33,7 +33,7 @@ int netns_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); int netns_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog); -int netns_bpf_prog_detach(const union bpf_attr *attr); +int netns_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); int netns_bpf_link_create(const union bpf_attr *attr, struct bpf_prog *prog); #else @@ -49,7 +49,8 @@ static inline int netns_bpf_prog_attach(const union bpf_attr *attr, return -EOPNOTSUPP; } -static inline int netns_bpf_prog_detach(const union bpf_attr *attr) +static inline int netns_bpf_prog_detach(const union bpf_attr *attr, + enum bpf_prog_type ptype) { return -EOPNOTSUPP; } diff --git a/kernel/bpf/net_namespace.c b/kernel/bpf/net_namespace.c index 03045f45afec..3dbc29b6f51d 100644 --- a/kernel/bpf/net_namespace.c +++ b/kernel/bpf/net_namespace.c @@ -269,7 +269,8 @@ out_unlock: /* Must be called with netns_bpf_mutex held. */ static int __netns_bpf_prog_detach(struct net *net, - enum netns_bpf_attach_type type) + enum netns_bpf_attach_type type, + struct bpf_prog *old) { struct bpf_prog *attached; @@ -278,7 +279,7 @@ static int __netns_bpf_prog_detach(struct net *net, return -EINVAL; attached = net->bpf.progs[type]; - if (!attached) + if (!attached || attached != old) return -ENOENT; netns_bpf_run_array_detach(net, type); net->bpf.progs[type] = NULL; @@ -286,19 +287,29 @@ static int __netns_bpf_prog_detach(struct net *net, return 0; } -int netns_bpf_prog_detach(const union bpf_attr *attr) +int netns_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) { enum netns_bpf_attach_type type; + struct bpf_prog *prog; int ret; + if (attr->target_fd) + return -EINVAL; + type = to_netns_bpf_attach_type(attr->attach_type); if (type < 0) return -EINVAL; + prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); + if (IS_ERR(prog)) + return PTR_ERR(prog); + mutex_lock(&netns_bpf_mutex); - ret = __netns_bpf_prog_detach(current->nsproxy->net_ns, type); + ret = __netns_bpf_prog_detach(current->nsproxy->net_ns, type, prog); mutex_unlock(&netns_bpf_mutex); + bpf_prog_put(prog); + return ret; } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 7d946435587d..28c6ef759037 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2897,9 +2897,7 @@ static int bpf_prog_detach(const union bpf_attr *attr) case BPF_PROG_TYPE_LIRC_MODE2: return lirc_prog_detach(attr); case BPF_PROG_TYPE_FLOW_DISSECTOR: - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - return netns_bpf_prog_detach(attr); + return netns_bpf_prog_detach(attr, ptype); case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_CGROUP_SKB: case BPF_PROG_TYPE_CGROUP_SOCK: -- cgit v1.2.3 From bb0de3131f4c60a9bf976681e0fe4d1e55c7a821 Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Mon, 29 Jun 2020 10:56:28 +0100 Subject: bpf: sockmap: Require attach_bpf_fd when detaching a program The sockmap code currently ignores the value of attach_bpf_fd when detaching a program. This is contrary to the usual behaviour of checking that attach_bpf_fd represents the currently attached program. Ensure that attach_bpf_fd is indeed the currently attached program. It turns out that all sockmap selftests already do this, which indicates that this is unlikely to cause breakage. Fixes: 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Lorenz Bauer Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200629095630.7933-5-lmb@cloudflare.com --- include/linux/bpf.h | 13 +++++++++++-- include/linux/skmsg.h | 13 +++++++++++++ kernel/bpf/syscall.c | 2 +- net/core/sock_map.c | 50 +++++++++++++++++++++++++++++++++++++++++++++----- 4 files changed, 70 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 07052d44bca1..9750a1902ee5 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1543,13 +1543,16 @@ static inline void bpf_map_offload_map_free(struct bpf_map *map) #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ #if defined(CONFIG_BPF_STREAM_PARSER) -int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, u32 which); +int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, + struct bpf_prog *old, u32 which); int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog); +int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); void sock_map_unhash(struct sock *sk); void sock_map_close(struct sock *sk, long timeout); #else static inline int sock_map_prog_update(struct bpf_map *map, - struct bpf_prog *prog, u32 which) + struct bpf_prog *prog, + struct bpf_prog *old, u32 which) { return -EOPNOTSUPP; } @@ -1559,6 +1562,12 @@ static inline int sock_map_get_from_fd(const union bpf_attr *attr, { return -EINVAL; } + +static inline int sock_map_prog_detach(const union bpf_attr *attr, + enum bpf_prog_type ptype) +{ + return -EOPNOTSUPP; +} #endif /* CONFIG_BPF_STREAM_PARSER */ #if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 08674cd14d5a..1e9ed840b9fc 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -430,6 +430,19 @@ static inline void psock_set_prog(struct bpf_prog **pprog, bpf_prog_put(prog); } +static inline int psock_replace_prog(struct bpf_prog **pprog, + struct bpf_prog *prog, + struct bpf_prog *old) +{ + if (cmpxchg(pprog, old, prog) != old) + return -ENOENT; + + if (old) + bpf_prog_put(old); + + return 0; +} + static inline void psock_progs_drop(struct sk_psock_progs *progs) { psock_set_prog(&progs->msg_parser, NULL); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 28c6ef759037..a74fce8ce043 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2893,7 +2893,7 @@ static int bpf_prog_detach(const union bpf_attr *attr) switch (ptype) { case BPF_PROG_TYPE_SK_MSG: case BPF_PROG_TYPE_SK_SKB: - return sock_map_get_from_fd(attr, NULL); + return sock_map_prog_detach(attr, ptype); case BPF_PROG_TYPE_LIRC_MODE2: return lirc_prog_detach(attr); case BPF_PROG_TYPE_FLOW_DISSECTOR: diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 58016a5c63ff..0971f17e8e54 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -77,7 +77,42 @@ int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); - ret = sock_map_prog_update(map, prog, attr->attach_type); + ret = sock_map_prog_update(map, prog, NULL, attr->attach_type); + fdput(f); + return ret; +} + +int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) +{ + u32 ufd = attr->target_fd; + struct bpf_prog *prog; + struct bpf_map *map; + struct fd f; + int ret; + + if (attr->attach_flags || attr->replace_bpf_fd) + return -EINVAL; + + f = fdget(ufd); + map = __bpf_map_get(f); + if (IS_ERR(map)) + return PTR_ERR(map); + + prog = bpf_prog_get(attr->attach_bpf_fd); + if (IS_ERR(prog)) { + ret = PTR_ERR(prog); + goto put_map; + } + + if (prog->type != ptype) { + ret = -EINVAL; + goto put_prog; + } + + ret = sock_map_prog_update(map, NULL, prog, attr->attach_type); +put_prog: + bpf_prog_put(prog); +put_map: fdput(f); return ret; } @@ -1206,27 +1241,32 @@ static struct sk_psock_progs *sock_map_progs(struct bpf_map *map) } int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, - u32 which) + struct bpf_prog *old, u32 which) { struct sk_psock_progs *progs = sock_map_progs(map); + struct bpf_prog **pprog; if (!progs) return -EOPNOTSUPP; switch (which) { case BPF_SK_MSG_VERDICT: - psock_set_prog(&progs->msg_parser, prog); + pprog = &progs->msg_parser; break; case BPF_SK_SKB_STREAM_PARSER: - psock_set_prog(&progs->skb_parser, prog); + pprog = &progs->skb_parser; break; case BPF_SK_SKB_STREAM_VERDICT: - psock_set_prog(&progs->skb_verdict, prog); + pprog = &progs->skb_verdict; break; default: return -EOPNOTSUPP; } + if (old) + return psock_replace_prog(pprog, prog, old); + + psock_set_prog(pprog, prog); return 0; } -- cgit v1.2.3