From dee872e124e8d5de22b68c58f6f6c3f5e8889160 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 14 Jan 2022 22:09:45 +0530 Subject: bpf: Populate kfunc BTF ID sets in struct btf This patch prepares the kernel to support putting all kinds of kfunc BTF ID sets in the struct btf itself. The various kernel subsystems will make register_btf_kfunc_id_set call in the initcalls (for built-in code and modules). The 'hook' is one of the many program types, e.g. XDP and TC/SCHED_CLS, STRUCT_OPS, and 'types' are check (allowed or not), acquire, release, and ret_null (with PTR_TO_BTF_ID_OR_NULL return type). A maximum of BTF_KFUNC_SET_MAX_CNT (32) kfunc BTF IDs are permitted in a set of certain hook and type for vmlinux sets, since they are allocated on demand, and otherwise set as NULL. Module sets can only be registered once per hook and type, hence they are directly assigned. A new btf_kfunc_id_set_contains function is exposed for use in verifier, this new method is faster than the existing list searching method, and is also automatic. It also lets other code not care whether the set is unallocated or not. Note that module code can only do single register_btf_kfunc_id_set call per hook. This is why sorting is only done for in-kernel vmlinux sets, because there might be multiple sets for the same hook and type that must be concatenated, hence sorting them is required to ensure bsearch in btf_id_set_contains continues to work correctly. Next commit will update the kernel users to make use of this infrastructure. Finally, add __maybe_unused annotation for BTF ID macros for the !CONFIG_DEBUG_INFO_BTF case, so that they don't produce warnings during build time. The previous patch is also needed to provide synchronization against initialization for module BTF's kfunc_set_tab introduced here, as described below: The kfunc_set_tab pointer in struct btf is write-once (if we consider the registration phase (comprised of multiple register_btf_kfunc_id_set calls) as a single operation). In this sense, once it has been fully prepared, it isn't modified, only used for lookup (from the verifier context). For btf_vmlinux, it is initialized fully during the do_initcalls phase, which happens fairly early in the boot process, before any processes are present. This also eliminates the possibility of bpf_check being called at that point, thus relieving us of ensuring any synchronization between the registration and lookup function (btf_kfunc_id_set_contains). However, the case for module BTF is a bit tricky. The BTF is parsed, prepared, and published from the MODULE_STATE_COMING notifier callback. After this, the module initcalls are invoked, where our registration function will be called to populate the kfunc_set_tab for module BTF. At this point, BTF may be available to userspace while its corresponding module is still intializing. A BTF fd can then be passed to verifier using bpf syscall (e.g. for kfunc call insn). Hence, there is a race window where verifier may concurrently try to lookup the kfunc_set_tab. To prevent this race, we must ensure the operations are serialized, or waiting for the __init functions to complete. In the earlier registration API, this race was alleviated as verifier bpf_check_mod_kfunc_call didn't find the kfunc BTF ID until it was added by the registration function (called usually at the end of module __init function after all module resources have been initialized). If the verifier made the check_kfunc_call before kfunc BTF ID was added to the list, it would fail verification (saying call isn't allowed). The access to list was protected using a mutex. Now, it would still fail verification, but for a different reason (returning ENXIO due to the failed btf_try_get_module call in add_kfunc_call), because if the __init call is in progress the module will be in the middle of MODULE_STATE_COMING -> MODULE_STATE_LIVE transition, and the BTF_MODULE_LIVE flag for btf_module instance will not be set, so the btf_try_get_module call will fail. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20220114163953.1455836-3-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/btf.h | 39 +++++++++++++++++++++++++++++++++++++++ include/linux/btf_ids.h | 13 +++++++------ 2 files changed, 46 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/btf.h b/include/linux/btf.h index 0c74348cbc9d..c451f8e2612a 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -12,11 +12,33 @@ #define BTF_TYPE_EMIT(type) ((void)(type *)0) #define BTF_TYPE_EMIT_ENUM(enum_val) ((void)enum_val) +enum btf_kfunc_type { + BTF_KFUNC_TYPE_CHECK, + BTF_KFUNC_TYPE_ACQUIRE, + BTF_KFUNC_TYPE_RELEASE, + BTF_KFUNC_TYPE_RET_NULL, + BTF_KFUNC_TYPE_MAX, +}; + struct btf; struct btf_member; struct btf_type; union bpf_attr; struct btf_show; +struct btf_id_set; + +struct btf_kfunc_id_set { + struct module *owner; + union { + struct { + struct btf_id_set *check_set; + struct btf_id_set *acquire_set; + struct btf_id_set *release_set; + struct btf_id_set *ret_null_set; + }; + struct btf_id_set *sets[BTF_KFUNC_TYPE_MAX]; + }; +}; extern const struct file_operations btf_fops; @@ -307,6 +329,11 @@ const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id); const char *btf_name_by_offset(const struct btf *btf, u32 offset); struct btf *btf_parse_vmlinux(void); struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog); +bool btf_kfunc_id_set_contains(const struct btf *btf, + enum bpf_prog_type prog_type, + enum btf_kfunc_type type, u32 kfunc_btf_id); +int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, + const struct btf_kfunc_id_set *s); #else static inline const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) @@ -318,6 +345,18 @@ static inline const char *btf_name_by_offset(const struct btf *btf, { return NULL; } +static inline bool btf_kfunc_id_set_contains(const struct btf *btf, + enum bpf_prog_type prog_type, + enum btf_kfunc_type type, + u32 kfunc_btf_id) +{ + return false; +} +static inline int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, + const struct btf_kfunc_id_set *s) +{ + return 0; +} #endif struct kfunc_btf_id_set { diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index 919c0fde1c51..bc5d9cc34e4c 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -11,6 +11,7 @@ struct btf_id_set { #ifdef CONFIG_DEBUG_INFO_BTF #include /* for __PASTE */ +#include /* for __maybe_unused */ /* * Following macros help to define lists of BTF IDs placed @@ -146,14 +147,14 @@ extern struct btf_id_set name; #else -#define BTF_ID_LIST(name) static u32 name[5]; +#define BTF_ID_LIST(name) static u32 __maybe_unused name[5]; #define BTF_ID(prefix, name) #define BTF_ID_UNUSED -#define BTF_ID_LIST_GLOBAL(name, n) u32 name[n]; -#define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 name[1]; -#define BTF_ID_LIST_GLOBAL_SINGLE(name, prefix, typename) u32 name[1]; -#define BTF_SET_START(name) static struct btf_id_set name = { 0 }; -#define BTF_SET_START_GLOBAL(name) static struct btf_id_set name = { 0 }; +#define BTF_ID_LIST_GLOBAL(name, n) u32 __maybe_unused name[n]; +#define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 __maybe_unused name[1]; +#define BTF_ID_LIST_GLOBAL_SINGLE(name, prefix, typename) u32 __maybe_unused name[1]; +#define BTF_SET_START(name) static struct btf_id_set __maybe_unused name = { 0 }; +#define BTF_SET_START_GLOBAL(name) static struct btf_id_set __maybe_unused name = { 0 }; #define BTF_SET_END(name) #endif /* CONFIG_DEBUG_INFO_BTF */ -- cgit v1.2.3 From b202d84422223b7222cba5031d182f20b37e146e Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 14 Jan 2022 22:09:46 +0530 Subject: bpf: Remove check_kfunc_call callback and old kfunc BTF ID API Completely remove the old code for check_kfunc_call to help it work with modules, and also the callback itself. The previous commit adds infrastructure to register all sets and put them in vmlinux or module BTF, and concatenates all related sets organized by the hook and the type. Once populated, these sets remain immutable for the lifetime of the struct btf. Also, since we don't need the 'owner' module anywhere when doing check_kfunc_call, drop the 'btf_modp' module parameter from find_kfunc_desc_btf. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20220114163953.1455836-4-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 8 -------- include/linux/btf.h | 44 -------------------------------------------- 2 files changed, 52 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 6e947cd91152..6d7346c54d83 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -573,7 +573,6 @@ struct bpf_verifier_ops { const struct btf_type *t, int off, int size, enum bpf_access_type atype, u32 *next_btf_id); - bool (*check_kfunc_call)(u32 kfunc_btf_id, struct module *owner); }; struct bpf_prog_offload_ops { @@ -1719,7 +1718,6 @@ int bpf_prog_test_run_raw_tp(struct bpf_prog *prog, int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); -bool bpf_prog_test_check_kfunc_call(u32 kfunc_id, struct module *owner); bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info); @@ -1971,12 +1969,6 @@ static inline int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, return -ENOTSUPP; } -static inline bool bpf_prog_test_check_kfunc_call(u32 kfunc_id, - struct module *owner) -{ - return false; -} - static inline void bpf_map_put(struct bpf_map *map) { } diff --git a/include/linux/btf.h b/include/linux/btf.h index c451f8e2612a..b12cfe3b12bb 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -359,48 +359,4 @@ static inline int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, } #endif -struct kfunc_btf_id_set { - struct list_head list; - struct btf_id_set *set; - struct module *owner; -}; - -struct kfunc_btf_id_list { - struct list_head list; - struct mutex mutex; -}; - -#ifdef CONFIG_DEBUG_INFO_BTF_MODULES -void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l, - struct kfunc_btf_id_set *s); -void unregister_kfunc_btf_id_set(struct kfunc_btf_id_list *l, - struct kfunc_btf_id_set *s); -bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id, - struct module *owner); - -extern struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list; -extern struct kfunc_btf_id_list prog_test_kfunc_list; -#else -static inline void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l, - struct kfunc_btf_id_set *s) -{ -} -static inline void unregister_kfunc_btf_id_set(struct kfunc_btf_id_list *l, - struct kfunc_btf_id_set *s) -{ -} -static inline bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, - u32 kfunc_id, struct module *owner) -{ - return false; -} - -static struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list __maybe_unused; -static struct kfunc_btf_id_list prog_test_kfunc_list __maybe_unused; -#endif - -#define DEFINE_KFUNC_BTF_ID_SET(set, name) \ - struct kfunc_btf_id_set name = { LIST_HEAD_INIT(name.list), (set), \ - THIS_MODULE } - #endif -- cgit v1.2.3 From d583691c47dc0424ebe926000339a6d6cd590ff7 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 14 Jan 2022 22:09:47 +0530 Subject: bpf: Introduce mem, size argument pair support for kfunc BPF helpers can associate two adjacent arguments together to pass memory of certain size, using ARG_PTR_TO_MEM and ARG_CONST_SIZE arguments. Since we don't use bpf_func_proto for kfunc, we need to leverage BTF to implement similar support. The ARG_CONST_SIZE processing for helpers is refactored into a common check_mem_size_reg helper that is shared with kfunc as well. kfunc ptr_to_mem support follows logic similar to global functions, where verification is done as if pointer is not null, even when it may be null. This leads to a simple to follow rule for writing kfunc: always check the argument pointer for NULL, except when it is PTR_TO_CTX. Also, the PTR_TO_CTX case is also only safe when the helper expecting pointer to program ctx is not exposed to other programs where same struct is not ctx type. In that case, the type check will fall through to other cases and would permit passing other types of pointers, possibly NULL at runtime. Currently, we require the size argument to be suffixed with "__sz" in the parameter name. This information is then recorded in kernel BTF and verified during function argument checking. In the future we can use BTF tagging instead, and modify the kernel function definitions. This will be a purely kernel-side change. This allows us to have some form of backwards compatibility for structures that are passed in to the kernel function with their size, and allow variable length structures to be passed in if they are accompanied by a size parameter. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20220114163953.1455836-5-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 143401d4c9d9..857fd687bdc2 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -521,6 +521,8 @@ bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt); int check_ctx_reg(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno); +int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, + u32 regno); int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, u32 mem_size); -- cgit v1.2.3 From 5c073f26f9dc78a6c8194b23eac7537c9692c7d7 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 14 Jan 2022 22:09:48 +0530 Subject: bpf: Add reference tracking support to kfunc This patch adds verifier support for PTR_TO_BTF_ID return type of kfunc to be a reference, by reusing acquire_reference_state/release_reference support for existing in-kernel bpf helpers. We make use of the three kfunc types: - BTF_KFUNC_TYPE_ACQUIRE Return true if kfunc_btf_id is an acquire kfunc. This will acquire_reference_state for the returned PTR_TO_BTF_ID (this is the only allow return value). Note that acquire kfunc must always return a PTR_TO_BTF_ID{_OR_NULL}, otherwise the program is rejected. - BTF_KFUNC_TYPE_RELEASE Return true if kfunc_btf_id is a release kfunc. This will release the reference to the passed in PTR_TO_BTF_ID which has a reference state (from earlier acquire kfunc). The btf_check_func_arg_match returns the regno (of argument register, hence > 0) if the kfunc is a release kfunc, and a proper referenced PTR_TO_BTF_ID is being passed to it. This is similar to how helper call check uses bpf_call_arg_meta to store the ref_obj_id that is later used to release the reference. Similar to in-kernel helper, we only allow passing one referenced PTR_TO_BTF_ID as an argument. It can also be passed in to normal kfunc, but in case of release kfunc there must always be one PTR_TO_BTF_ID argument that is referenced. - BTF_KFUNC_TYPE_RET_NULL For kfunc returning PTR_TO_BTF_ID, tells if it can be NULL, hence force caller to mark the pointer not null (using check) before accessing it. Note that taking into account the case fixed by commit 93c230e3f5bd ("bpf: Enforce id generation for all may-be-null register type") we assign a non-zero id for mark_ptr_or_null_reg logic. Later, if more return types are supported by kfunc, which have a _OR_NULL variant, it might be better to move this id generation under a common reg_type_may_be_null check, similar to the case in the commit. Referenced PTR_TO_BTF_ID is currently only limited to kfunc, but can be extended in the future to other BPF helpers as well. For now, we can rely on the btf_struct_ids_match check to ensure we get the pointer to the expected struct type. In the future, care needs to be taken to avoid ambiguity for reference PTR_TO_BTF_ID passed to release function, in case multiple candidates can release same BTF ID. e.g. there might be two release kfuncs (or kfunc and helper): foo(struct abc *p); bar(struct abc *p); ... such that both release a PTR_TO_BTF_ID with btf_id of struct abc. In this case we would need to track the acquire function corresponding to the release function to avoid type confusion, and store this information in the register state so that an incorrect program can be rejected. This is not a problem right now, hence it is left as an exercise for the future patch introducing such a case in the kernel. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20220114163953.1455836-6-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 857fd687bdc2..ac4797155412 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -566,4 +566,9 @@ static inline u32 type_flag(u32 type) return type & ~BPF_BASE_TYPE_MASK; } +static inline enum bpf_prog_type resolve_prog_type(struct bpf_prog *prog) +{ + return prog->aux->dst_prog ? prog->aux->dst_prog->type : prog->type; +} + #endif /* _LINUX_BPF_VERIFIER_H */ -- cgit v1.2.3 From b4c2b9593a1c4c3a718370e34af28e817fd5e5c6 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 14 Jan 2022 22:09:49 +0530 Subject: net/netfilter: Add unstable CT lookup helpers for XDP and TC-BPF This change adds conntrack lookup helpers using the unstable kfunc call interface for the XDP and TC-BPF hooks. The primary usecase is implementing a synproxy in XDP, see Maxim's patchset [0]. Export get_net_ns_by_id as nf_conntrack_bpf.c needs to call it. This object is only built when CONFIG_DEBUG_INFO_BTF_MODULES is enabled. [0]: https://lore.kernel.org/bpf/20211019144655.3483197-1-maximmi@nvidia.com Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20220114163953.1455836-7-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/net/netfilter/nf_conntrack_bpf.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) create mode 100644 include/net/netfilter/nf_conntrack_bpf.h (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_bpf.h b/include/net/netfilter/nf_conntrack_bpf.h new file mode 100644 index 000000000000..a473b56842c5 --- /dev/null +++ b/include/net/netfilter/nf_conntrack_bpf.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _NF_CONNTRACK_BPF_H +#define _NF_CONNTRACK_BPF_H + +#include +#include + +#if (IS_BUILTIN(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) || \ + (IS_MODULE(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)) + +extern int register_nf_conntrack_bpf(void); + +#else + +static inline int register_nf_conntrack_bpf(void) +{ + return 0; +} + +#endif + +#endif /* _NF_CONNTRACK_BPF_H */ -- cgit v1.2.3 From e40fbbf0572c5e41dc87ad79001748ed399ce32d Mon Sep 17 00:00:00 2001 From: Usama Arif Date: Wed, 19 Jan 2022 11:44:40 +0000 Subject: uapi/bpf: Add missing description and returns for helper documentation Both description and returns section will become mandatory for helpers and syscalls in a later commit to generate man pages. This commit also adds in the documentation that BPF_PROG_RUN is an alias for BPF_PROG_TEST_RUN for anyone searching for the syscall in the generated man pages. Signed-off-by: Usama Arif Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20220119114442.1452088-1-usama.arif@bytedance.com --- include/uapi/linux/bpf.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index b0383d371b9a..a9c96c21330a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -330,6 +330,8 @@ union bpf_iter_link_info { * *ctx_out*, *data_in* and *data_out* must be NULL. * *repeat* must be zero. * + * BPF_PROG_RUN is an alias for BPF_PROG_TEST_RUN. + * * Return * Returns zero on success. On error, -1 is returned and *errno* * is set appropriately. @@ -1775,6 +1777,8 @@ union bpf_attr { * 0 on success, or a negative error in case of failure. * * u64 bpf_get_current_pid_tgid(void) + * Description + * Get the current pid and tgid. * Return * A 64-bit integer containing the current tgid and pid, and * created as such: @@ -1782,6 +1786,8 @@ union bpf_attr { * *current_task*\ **->pid**. * * u64 bpf_get_current_uid_gid(void) + * Description + * Get the current uid and gid. * Return * A 64-bit integer containing the current GID and UID, and * created as such: *current_gid* **<< 32 \|** *current_uid*. @@ -2256,6 +2262,8 @@ union bpf_attr { * The 32-bit hash. * * u64 bpf_get_current_task(void) + * Description + * Get the current task. * Return * A pointer to the current task struct. * @@ -2369,6 +2377,8 @@ union bpf_attr { * indicate that the hash is outdated and to trigger a * recalculation the next time the kernel tries to access this * hash or when the **bpf_get_hash_recalc**\ () helper is called. + * Return + * void. * * long bpf_get_numa_node_id(void) * Description @@ -2466,6 +2476,8 @@ union bpf_attr { * A 8-byte long unique number or 0 if *sk* is NULL. * * u32 bpf_get_socket_uid(struct sk_buff *skb) + * Description + * Get the owner UID of the socked associated to *skb*. * Return * The owner UID of the socket associated to *skb*. If the socket * is **NULL**, or if it is not a full socket (i.e. if it is a @@ -3240,6 +3252,9 @@ union bpf_attr { * The id is returned or 0 in case the id could not be retrieved. * * u64 bpf_get_current_cgroup_id(void) + * Description + * Get the current cgroup id based on the cgroup within which + * the current task is running. * Return * A 64-bit integer containing the current cgroup id based * on the cgroup within which the current task is running. -- cgit v1.2.3 From f10d059661968b01ef61a8b516775f95a18ab8ae Mon Sep 17 00:00:00 2001 From: YiFei Zhu Date: Thu, 16 Dec 2021 02:04:25 +0000 Subject: bpf: Make BPF_PROG_RUN_ARRAY return -err instead of allow boolean Right now BPF_PROG_RUN_ARRAY and related macros return 1 or 0 for whether the prog array allows or rejects whatever is being hooked. The caller of these macros then return -EPERM or continue processing based on thw macro's return value. Unforunately this is inflexible, since -EPERM is the only err that can be returned. This patch should be a no-op; it prepares for the next patch. The returning of the -EPERM is moved to inside the macros, so the outer functions are directly returning what the macros returned if they are non-zero. Signed-off-by: YiFei Zhu Reviewed-by: Stanislav Fomichev Link: https://lore.kernel.org/r/788abcdca55886d1f43274c918eaa9f792a9f33b.1639619851.git.zhuyifei@google.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 6d7346c54d83..83da1764fcfe 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1277,7 +1277,7 @@ static inline void bpf_reset_run_ctx(struct bpf_run_ctx *old_ctx) typedef u32 (*bpf_prog_run_fn)(const struct bpf_prog *prog, const void *ctx); -static __always_inline u32 +static __always_inline int BPF_PROG_RUN_ARRAY_CG_FLAGS(const struct bpf_prog_array __rcu *array_rcu, const void *ctx, bpf_prog_run_fn run_prog, u32 *ret_flags) @@ -1287,7 +1287,7 @@ BPF_PROG_RUN_ARRAY_CG_FLAGS(const struct bpf_prog_array __rcu *array_rcu, const struct bpf_prog_array *array; struct bpf_run_ctx *old_run_ctx; struct bpf_cg_run_ctx run_ctx; - u32 ret = 1; + int ret = 0; u32 func_ret; migrate_disable(); @@ -1298,7 +1298,8 @@ BPF_PROG_RUN_ARRAY_CG_FLAGS(const struct bpf_prog_array __rcu *array_rcu, while ((prog = READ_ONCE(item->prog))) { run_ctx.prog_item = item; func_ret = run_prog(prog, ctx); - ret &= (func_ret & 1); + if (!(func_ret & 1)) + ret = -EPERM; *(ret_flags) |= (func_ret >> 1); item++; } @@ -1308,7 +1309,7 @@ BPF_PROG_RUN_ARRAY_CG_FLAGS(const struct bpf_prog_array __rcu *array_rcu, return ret; } -static __always_inline u32 +static __always_inline int BPF_PROG_RUN_ARRAY_CG(const struct bpf_prog_array __rcu *array_rcu, const void *ctx, bpf_prog_run_fn run_prog) { @@ -1317,7 +1318,7 @@ BPF_PROG_RUN_ARRAY_CG(const struct bpf_prog_array __rcu *array_rcu, const struct bpf_prog_array *array; struct bpf_run_ctx *old_run_ctx; struct bpf_cg_run_ctx run_ctx; - u32 ret = 1; + int ret = 0; migrate_disable(); rcu_read_lock(); @@ -1326,7 +1327,8 @@ BPF_PROG_RUN_ARRAY_CG(const struct bpf_prog_array __rcu *array_rcu, old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); while ((prog = READ_ONCE(item->prog))) { run_ctx.prog_item = item; - ret &= run_prog(prog, ctx); + if (!run_prog(prog, ctx)) + ret = -EPERM; item++; } bpf_reset_run_ctx(old_run_ctx); @@ -1394,7 +1396,7 @@ out: u32 _ret; \ _ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(array, ctx, func, &_flags); \ _cn = _flags & BPF_RET_SET_CN; \ - if (_ret) \ + if (!_ret) \ _ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS); \ else \ _ret = (_cn ? NET_XMIT_DROP : -EPERM); \ -- cgit v1.2.3 From c4dcfdd406aa2167396ac215e351e5e4dfd7efe3 Mon Sep 17 00:00:00 2001 From: YiFei Zhu Date: Thu, 16 Dec 2021 02:04:26 +0000 Subject: bpf: Move getsockopt retval to struct bpf_cg_run_ctx The retval value is moved to struct bpf_cg_run_ctx for ease of access in different prog types with different context structs layouts. The helper implementation (to be added in a later patch in the series) can simply perform a container_of from current->bpf_ctx to retrieve bpf_cg_run_ctx. Unfortunately, there is no easy way to access the current task_struct via the verifier BPF bytecode rewrite, aside from possibly calling a helper, so a pointer to current task is added to struct bpf_sockopt_kern so that the rewritten BPF bytecode can access struct bpf_cg_run_ctx with an indirection. For backward compatibility, if a getsockopt program rejects a syscall by returning 0, an -EPERM will be generated, by having the BPF_PROG_RUN_ARRAY_CG family macros automatically set the retval to -EPERM. Unlike prior to this patch, this -EPERM will be visible to ctx->retval for any other hooks down the line in the prog array. Additionally, the restriction that getsockopt filters can only set the retval to 0 is removed, considering that certain getsockopt implementations may return optlen. Filters are now able to set the value arbitrarily. Signed-off-by: YiFei Zhu Reviewed-by: Stanislav Fomichev Link: https://lore.kernel.org/r/73b0325f5c29912ccea7ea57ec1ed4d388fc1d37.1639619851.git.zhuyifei@google.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 20 +++++++++++--------- include/linux/filter.h | 5 ++++- 2 files changed, 15 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 83da1764fcfe..7b0c11f414d0 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1245,6 +1245,7 @@ struct bpf_run_ctx {}; struct bpf_cg_run_ctx { struct bpf_run_ctx run_ctx; const struct bpf_prog_array_item *prog_item; + int retval; }; struct bpf_trace_run_ctx { @@ -1280,16 +1281,16 @@ typedef u32 (*bpf_prog_run_fn)(const struct bpf_prog *prog, const void *ctx); static __always_inline int BPF_PROG_RUN_ARRAY_CG_FLAGS(const struct bpf_prog_array __rcu *array_rcu, const void *ctx, bpf_prog_run_fn run_prog, - u32 *ret_flags) + int retval, u32 *ret_flags) { const struct bpf_prog_array_item *item; const struct bpf_prog *prog; const struct bpf_prog_array *array; struct bpf_run_ctx *old_run_ctx; struct bpf_cg_run_ctx run_ctx; - int ret = 0; u32 func_ret; + run_ctx.retval = retval; migrate_disable(); rcu_read_lock(); array = rcu_dereference(array_rcu); @@ -1299,27 +1300,28 @@ BPF_PROG_RUN_ARRAY_CG_FLAGS(const struct bpf_prog_array __rcu *array_rcu, run_ctx.prog_item = item; func_ret = run_prog(prog, ctx); if (!(func_ret & 1)) - ret = -EPERM; + run_ctx.retval = -EPERM; *(ret_flags) |= (func_ret >> 1); item++; } bpf_reset_run_ctx(old_run_ctx); rcu_read_unlock(); migrate_enable(); - return ret; + return run_ctx.retval; } static __always_inline int BPF_PROG_RUN_ARRAY_CG(const struct bpf_prog_array __rcu *array_rcu, - const void *ctx, bpf_prog_run_fn run_prog) + const void *ctx, bpf_prog_run_fn run_prog, + int retval) { const struct bpf_prog_array_item *item; const struct bpf_prog *prog; const struct bpf_prog_array *array; struct bpf_run_ctx *old_run_ctx; struct bpf_cg_run_ctx run_ctx; - int ret = 0; + run_ctx.retval = retval; migrate_disable(); rcu_read_lock(); array = rcu_dereference(array_rcu); @@ -1328,13 +1330,13 @@ BPF_PROG_RUN_ARRAY_CG(const struct bpf_prog_array __rcu *array_rcu, while ((prog = READ_ONCE(item->prog))) { run_ctx.prog_item = item; if (!run_prog(prog, ctx)) - ret = -EPERM; + run_ctx.retval = -EPERM; item++; } bpf_reset_run_ctx(old_run_ctx); rcu_read_unlock(); migrate_enable(); - return ret; + return run_ctx.retval; } static __always_inline u32 @@ -1394,7 +1396,7 @@ out: u32 _flags = 0; \ bool _cn; \ u32 _ret; \ - _ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(array, ctx, func, &_flags); \ + _ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(array, ctx, func, 0, &_flags); \ _cn = _flags & BPF_RET_SET_CN; \ if (!_ret) \ _ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS); \ diff --git a/include/linux/filter.h b/include/linux/filter.h index 71fa57b88bfc..d23e999dc032 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1356,7 +1356,10 @@ struct bpf_sockopt_kern { s32 level; s32 optname; s32 optlen; - s32 retval; + /* for retval in struct bpf_cg_run_ctx */ + struct task_struct *current_task; + /* Temporary "register" for indirect stores to ppos. */ + u64 tmp_reg; }; int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len); -- cgit v1.2.3 From b44123b4a3dcad4664d3a0f72c011ffd4c9c4d93 Mon Sep 17 00:00:00 2001 From: YiFei Zhu Date: Thu, 16 Dec 2021 02:04:27 +0000 Subject: bpf: Add cgroup helpers bpf_{get,set}_retval to get/set syscall return value The helpers continue to use int for retval because all the hooks are int-returning rather than long-returning. The return value of bpf_set_retval is int for future-proofing, in case in the future there may be errors trying to set the retval. After the previous patch, if a program rejects a syscall by returning 0, an -EPERM will be generated no matter if the retval is already set to -err. This patch change it being forced only if retval is not -err. This is because we want to support, for example, invoking bpf_set_retval(-EINVAL) and return 0, and have the syscall return value be -EINVAL not -EPERM. For BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY, the prior behavior is that, if the return value is NET_XMIT_DROP, the packet is silently dropped. We preserve this behavior for backward compatibility reasons, so even if an errno is set, the errno does not return to caller. However, setting a non-err to retval cannot propagate so this is not allowed and we return a -EFAULT in that case. Signed-off-by: YiFei Zhu Reviewed-by: Stanislav Fomichev Link: https://lore.kernel.org/r/b4013fd5d16bed0b01977c1fafdeae12e1de61fb.1639619851.git.zhuyifei@google.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 10 ++++++---- include/uapi/linux/bpf.h | 18 ++++++++++++++++++ 2 files changed, 24 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 7b0c11f414d0..dce54eb0aae8 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1299,7 +1299,7 @@ BPF_PROG_RUN_ARRAY_CG_FLAGS(const struct bpf_prog_array __rcu *array_rcu, while ((prog = READ_ONCE(item->prog))) { run_ctx.prog_item = item; func_ret = run_prog(prog, ctx); - if (!(func_ret & 1)) + if (!(func_ret & 1) && !IS_ERR_VALUE((long)run_ctx.retval)) run_ctx.retval = -EPERM; *(ret_flags) |= (func_ret >> 1); item++; @@ -1329,7 +1329,7 @@ BPF_PROG_RUN_ARRAY_CG(const struct bpf_prog_array __rcu *array_rcu, old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); while ((prog = READ_ONCE(item->prog))) { run_ctx.prog_item = item; - if (!run_prog(prog, ctx)) + if (!run_prog(prog, ctx) && !IS_ERR_VALUE((long)run_ctx.retval)) run_ctx.retval = -EPERM; item++; } @@ -1389,7 +1389,7 @@ out: * 0: NET_XMIT_SUCCESS skb should be transmitted * 1: NET_XMIT_DROP skb should be dropped and cn * 2: NET_XMIT_CN skb should be transmitted and cn - * 3: -EPERM skb should be dropped + * 3: -err skb should be dropped */ #define BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY(array, ctx, func) \ ({ \ @@ -1398,10 +1398,12 @@ out: u32 _ret; \ _ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(array, ctx, func, 0, &_flags); \ _cn = _flags & BPF_RET_SET_CN; \ + if (_ret && !IS_ERR_VALUE((long)_ret)) \ + _ret = -EFAULT; \ if (!_ret) \ _ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS); \ else \ - _ret = (_cn ? NET_XMIT_DROP : -EPERM); \ + _ret = (_cn ? NET_XMIT_DROP : _ret); \ _ret; \ }) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a9c96c21330a..fe2272defcd9 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5033,6 +5033,22 @@ union bpf_attr { * * Return * The number of arguments of the traced function. + * + * int bpf_get_retval(void) + * Description + * Get the syscall's return value that will be returned to userspace. + * + * This helper is currently supported by cgroup programs only. + * Return + * The syscall's return value. + * + * int bpf_set_retval(int retval) + * Description + * Set the syscall's return value that will be returned to userspace. + * + * This helper is currently supported by cgroup programs only. + * Return + * 0 on success, or a negative error in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5221,6 +5237,8 @@ union bpf_attr { FN(get_func_arg), \ FN(get_func_ret), \ FN(get_func_arg_cnt), \ + FN(get_retval), \ + FN(set_retval), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 748cd5729ac7421091316e32dcdffb0578563880 Mon Sep 17 00:00:00 2001 From: Di Zhu Date: Wed, 19 Jan 2022 09:40:04 +0800 Subject: bpf: support BPF_PROG_QUERY for progs attached to sockmap Right now there is no way to query whether BPF programs are attached to a sockmap or not. we can use the standard interface in libbpf to query, such as: bpf_prog_query(mapFd, BPF_SK_SKB_STREAM_PARSER, 0, NULL, ...); the mapFd is the fd of sockmap. Signed-off-by: Di Zhu Acked-by: Yonghong Song Reviewed-by: Jakub Sitnicki Link: https://lore.kernel.org/r/20220119014005.1209-1-zhudi2@huawei.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index dce54eb0aae8..80e3387ea3af 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2069,6 +2069,9 @@ int bpf_prog_test_run_syscall(struct bpf_prog *prog, 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); int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags); +int sock_map_bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr); + void sock_map_unhash(struct sock *sk); void sock_map_close(struct sock *sk, long timeout); #else @@ -2122,6 +2125,12 @@ static inline int sock_map_update_elem_sys(struct bpf_map *map, void *key, void { return -EOPNOTSUPP; } + +static inline int sock_map_bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return -EINVAL; +} #endif /* CONFIG_BPF_SYSCALL */ #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ -- cgit v1.2.3 From d16697cb6261d4cc23422e6b1cb2759df8aa76d0 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 21 Jan 2022 11:09:44 +0100 Subject: net: skbuff: add size metadata to skb_shared_info for xdp Introduce xdp_frags_size field in skb_shared_info data structure to store xdp_buff/xdp_frame frame paged size (xdp_frags_size will be used in xdp frags support). In order to not increase skb_shared_info size we will use a hole due to skb_shared_info alignment. Acked-by: Toke Hoiland-Jorgensen Acked-by: John Fastabend Acked-by: Jesper Dangaard Brouer Signed-off-by: Lorenzo Bianconi Link: https://lore.kernel.org/r/8a849819a3e0a143d540f78a3a5add76e17e980d.1642758637.git.lorenzo@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/skbuff.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index bf11e1fbd69b..8131d0de7559 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -557,6 +557,7 @@ struct skb_shared_info { * Warning : all fields before dataref are cleared in __alloc_skb() */ atomic_t dataref; + unsigned int xdp_frags_size; /* Intermediate layers must ensure that destructor_arg * remains valid until skb destructor */ -- cgit v1.2.3 From 2e88d4ff03013937028f5397268b21e10cf68713 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 21 Jan 2022 11:09:45 +0100 Subject: xdp: introduce flags field in xdp_buff/xdp_frame Introduce flags field in xdp_frame and xdp_buffer data structures to define additional buffer features. At the moment the only supported buffer feature is frags bit (XDP_FLAGS_HAS_FRAGS). frags bit is used to specify if this is a linear buffer (XDP_FLAGS_HAS_FRAGS not set) or a frags frame (XDP_FLAGS_HAS_FRAGS set). In the latter case the driver is expected to initialize the skb_shared_info structure at the end of the first buffer to link together subsequent buffers belonging to the same frame. Acked-by: Toke Hoiland-Jorgensen Acked-by: John Fastabend Acked-by: Jesper Dangaard Brouer Signed-off-by: Lorenzo Bianconi Link: https://lore.kernel.org/r/e389f14f3a162c0a5bc6a2e1aa8dd01a90be117d.1642758637.git.lorenzo@kernel.org Signed-off-by: Alexei Starovoitov --- include/net/xdp.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'include') diff --git a/include/net/xdp.h b/include/net/xdp.h index 8f0812e4996d..485e9495a690 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -66,6 +66,10 @@ struct xdp_txq_info { struct net_device *dev; }; +enum xdp_buff_flags { + XDP_FLAGS_HAS_FRAGS = BIT(0), /* non-linear xdp buff */ +}; + struct xdp_buff { void *data; void *data_end; @@ -74,13 +78,30 @@ struct xdp_buff { struct xdp_rxq_info *rxq; struct xdp_txq_info *txq; u32 frame_sz; /* frame size to deduce data_hard_end/reserved tailroom*/ + u32 flags; /* supported values defined in xdp_buff_flags */ }; +static __always_inline bool xdp_buff_has_frags(struct xdp_buff *xdp) +{ + return !!(xdp->flags & XDP_FLAGS_HAS_FRAGS); +} + +static __always_inline void xdp_buff_set_frags_flag(struct xdp_buff *xdp) +{ + xdp->flags |= XDP_FLAGS_HAS_FRAGS; +} + +static __always_inline void xdp_buff_clear_frags_flag(struct xdp_buff *xdp) +{ + xdp->flags &= ~XDP_FLAGS_HAS_FRAGS; +} + static __always_inline void xdp_init_buff(struct xdp_buff *xdp, u32 frame_sz, struct xdp_rxq_info *rxq) { xdp->frame_sz = frame_sz; xdp->rxq = rxq; + xdp->flags = 0; } static __always_inline void @@ -122,8 +143,14 @@ struct xdp_frame { */ struct xdp_mem_info mem; struct net_device *dev_rx; /* used by cpumap */ + u32 flags; /* supported values defined in xdp_buff_flags */ }; +static __always_inline bool xdp_frame_has_frags(struct xdp_frame *frame) +{ + return !!(frame->flags & XDP_FLAGS_HAS_FRAGS); +} + #define XDP_BULK_QUEUE_SIZE 16 struct xdp_frame_bulk { int count; @@ -180,6 +207,7 @@ void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp) xdp->data_end = frame->data + frame->len; xdp->data_meta = frame->data - frame->metasize; xdp->frame_sz = frame->frame_sz; + xdp->flags = frame->flags; } static inline @@ -206,6 +234,7 @@ int xdp_update_frame_from_buff(struct xdp_buff *xdp, xdp_frame->headroom = headroom - sizeof(*xdp_frame); xdp_frame->metasize = metasize; xdp_frame->frame_sz = xdp->frame_sz; + xdp_frame->flags = xdp->flags; return 0; } -- cgit v1.2.3 From d65a1906b31246492449eafe9cace188cb59e26c Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 21 Jan 2022 11:09:48 +0100 Subject: net: xdp: add xdp_update_skb_shared_info utility routine Introduce xdp_update_skb_shared_info routine to update frags array metadata in skb_shared_info data structure converting to a skb from a xdp_buff or xdp_frame. According to the current skb_shared_info architecture in xdp_frame/xdp_buff and to the xdp frags support, there is no need to run skb_add_rx_frag() and reset frags array converting the buffer to a skb since the frag array will be in the same position for xdp_buff/xdp_frame and for the skb, we just need to update memory metadata. Introduce XDP_FLAGS_PF_MEMALLOC flag in xdp_buff_flags in order to mark the xdp_buff or xdp_frame as under memory-pressure if pages of the frags array are under memory pressure. Doing so we can avoid looping over all fragments in xdp_update_skb_shared_info routine. The driver is expected to set the flag constructing the xdp_buffer using xdp_buff_set_frag_pfmemalloc utility routine. Rely on xdp_update_skb_shared_info in __xdp_build_skb_from_frame routine converting the non-linear xdp_frame to a skb after performing a XDP_REDIRECT. Acked-by: Toke Hoiland-Jorgensen Acked-by: John Fastabend Acked-by: Jesper Dangaard Brouer Signed-off-by: Lorenzo Bianconi Link: https://lore.kernel.org/r/bfd23fb8a8d7438724f7819c567cdf99ffd6226f.1642758637.git.lorenzo@kernel.org Signed-off-by: Alexei Starovoitov --- include/net/xdp.h | 33 ++++++++++++++++++++++++++++++++- 1 file changed, 32 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/xdp.h b/include/net/xdp.h index 485e9495a690..1f8641ec658e 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -67,7 +67,10 @@ struct xdp_txq_info { }; enum xdp_buff_flags { - XDP_FLAGS_HAS_FRAGS = BIT(0), /* non-linear xdp buff */ + XDP_FLAGS_HAS_FRAGS = BIT(0), /* non-linear xdp buff */ + XDP_FLAGS_FRAGS_PF_MEMALLOC = BIT(1), /* xdp paged memory is under + * pressure + */ }; struct xdp_buff { @@ -96,6 +99,16 @@ static __always_inline void xdp_buff_clear_frags_flag(struct xdp_buff *xdp) xdp->flags &= ~XDP_FLAGS_HAS_FRAGS; } +static __always_inline bool xdp_buff_is_frag_pfmemalloc(struct xdp_buff *xdp) +{ + return !!(xdp->flags & XDP_FLAGS_FRAGS_PF_MEMALLOC); +} + +static __always_inline void xdp_buff_set_frag_pfmemalloc(struct xdp_buff *xdp) +{ + xdp->flags |= XDP_FLAGS_FRAGS_PF_MEMALLOC; +} + static __always_inline void xdp_init_buff(struct xdp_buff *xdp, u32 frame_sz, struct xdp_rxq_info *rxq) { @@ -151,6 +164,11 @@ static __always_inline bool xdp_frame_has_frags(struct xdp_frame *frame) return !!(frame->flags & XDP_FLAGS_HAS_FRAGS); } +static __always_inline bool xdp_frame_is_frag_pfmemalloc(struct xdp_frame *frame) +{ + return !!(frame->flags & XDP_FLAGS_FRAGS_PF_MEMALLOC); +} + #define XDP_BULK_QUEUE_SIZE 16 struct xdp_frame_bulk { int count; @@ -186,6 +204,19 @@ static inline void xdp_scrub_frame(struct xdp_frame *frame) frame->dev_rx = NULL; } +static inline void +xdp_update_skb_shared_info(struct sk_buff *skb, u8 nr_frags, + unsigned int size, unsigned int truesize, + bool pfmemalloc) +{ + skb_shinfo(skb)->nr_frags = nr_frags; + + skb->len += size; + skb->data_len += size; + skb->truesize += truesize; + skb->pfmemalloc |= pfmemalloc; +} + /* Avoids inlining WARN macro in fast-path */ void xdp_warn(const char *msg, const char *func, const int line); #define XDP_WARN(msg) xdp_warn(msg, __func__, __LINE__) -- cgit v1.2.3 From 7c48cb0176c6d6d3b55029f7ff4ffa05faee6446 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 21 Jan 2022 11:09:50 +0100 Subject: xdp: add frags support to xdp_return_{buff/frame} Take into account if the received xdp_buff/xdp_frame is non-linear recycling/returning the frame memory to the allocator or into xdp_frame_bulk. Acked-by: Toke Hoiland-Jorgensen Acked-by: John Fastabend Signed-off-by: Lorenzo Bianconi Link: https://lore.kernel.org/r/a961069febc868508ce1bdf5e53a343eb4e57cb2.1642758637.git.lorenzo@kernel.org Signed-off-by: Alexei Starovoitov --- include/net/xdp.h | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/xdp.h b/include/net/xdp.h index 1f8641ec658e..8463dea8b4db 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -306,10 +306,24 @@ void __xdp_release_frame(void *data, struct xdp_mem_info *mem); static inline void xdp_release_frame(struct xdp_frame *xdpf) { struct xdp_mem_info *mem = &xdpf->mem; + struct skb_shared_info *sinfo; + int i; /* Curr only page_pool needs this */ - if (mem->type == MEM_TYPE_PAGE_POOL) - __xdp_release_frame(xdpf->data, mem); + if (mem->type != MEM_TYPE_PAGE_POOL) + return; + + if (likely(!xdp_frame_has_frags(xdpf))) + goto out; + + sinfo = xdp_get_shared_info_from_frame(xdpf); + for (i = 0; i < sinfo->nr_frags; i++) { + struct page *page = skb_frag_page(&sinfo->frags[i]); + + __xdp_release_frame(page_address(page), mem); + } +out: + __xdp_release_frame(xdpf->data, mem); } int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, -- cgit v1.2.3 From c2f2cdbeffda7b153c19e0f3d73149c41026c0db Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 21 Jan 2022 11:09:52 +0100 Subject: bpf: introduce BPF_F_XDP_HAS_FRAGS flag in prog_flags loading the ebpf program Introduce BPF_F_XDP_HAS_FRAGS and the related field in bpf_prog_aux in order to notify the driver the loaded program support xdp frags. Acked-by: Toke Hoiland-Jorgensen Acked-by: John Fastabend Signed-off-by: Lorenzo Bianconi Link: https://lore.kernel.org/r/db2e8075b7032a356003f407d1b0deb99adaa0ed.1642758637.git.lorenzo@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 5 +++++ 2 files changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 80e3387ea3af..e93ed028a030 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -933,6 +933,7 @@ struct bpf_prog_aux { bool func_proto_unreliable; bool sleepable; bool tail_call_reachable; + bool xdp_has_frags; struct hlist_node tramp_hlist; /* BTF_KIND_FUNC_PROTO for valid attach_btf_id */ const struct btf_type *attach_func_proto; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index fe2272defcd9..945649c67e03 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1113,6 +1113,11 @@ enum bpf_link_type { */ #define BPF_F_SLEEPABLE (1U << 4) +/* If BPF_F_XDP_HAS_FRAGS is used in BPF_PROG_LOAD command, the loaded program + * fully support xdp frags. + */ +#define BPF_F_XDP_HAS_FRAGS (1U << 5) + /* When BPF ldimm64's insn[0].src_reg != 0 then this can have * the following extensions: * -- cgit v1.2.3 From 0165cc817075cf701e4289838f1d925ff1911b3e Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 21 Jan 2022 11:09:54 +0100 Subject: bpf: introduce bpf_xdp_get_buff_len helper Introduce bpf_xdp_get_buff_len helper in order to return the xdp buffer total size (linear and paged area) Acked-by: Toke Hoiland-Jorgensen Acked-by: John Fastabend Signed-off-by: Lorenzo Bianconi Link: https://lore.kernel.org/r/aac9ac3504c84026cf66a3c71b7c5ae89bc991be.1642758637.git.lorenzo@kernel.org Signed-off-by: Alexei Starovoitov --- include/net/xdp.h | 14 ++++++++++++++ include/uapi/linux/bpf.h | 7 +++++++ 2 files changed, 21 insertions(+) (limited to 'include') diff --git a/include/net/xdp.h b/include/net/xdp.h index 8463dea8b4db..52b593321956 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -145,6 +145,20 @@ xdp_get_shared_info_from_buff(struct xdp_buff *xdp) return (struct skb_shared_info *)xdp_data_hard_end(xdp); } +static __always_inline unsigned int xdp_get_buff_len(struct xdp_buff *xdp) +{ + unsigned int len = xdp->data_end - xdp->data; + struct skb_shared_info *sinfo; + + if (likely(!xdp_buff_has_frags(xdp))) + goto out; + + sinfo = xdp_get_shared_info_from_buff(xdp); + len += sinfo->xdp_frags_size; +out: + return len; +} + struct xdp_frame { void *data; u16 len; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 945649c67e03..5a28772063f6 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5054,6 +5054,12 @@ union bpf_attr { * This helper is currently supported by cgroup programs only. * Return * 0 on success, or a negative error in case of failure. + * + * u64 bpf_xdp_get_buff_len(struct xdp_buff *xdp_md) + * Description + * Get the total size of a given xdp buff (linear and paged area) + * Return + * The total size of a given xdp buffer. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5244,6 +5250,7 @@ union bpf_attr { FN(get_func_arg_cnt), \ FN(get_retval), \ FN(set_retval), \ + FN(xdp_get_buff_len), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From bf25146a5595269810b1f47d048f114c5ff9f544 Mon Sep 17 00:00:00 2001 From: Eelco Chaudron Date: Fri, 21 Jan 2022 11:09:55 +0100 Subject: bpf: add frags support to the bpf_xdp_adjust_tail() API This change adds support for tail growing and shrinking for XDP frags. When called on a non-linear packet with a grow request, it will work on the last fragment of the packet. So the maximum grow size is the last fragments tailroom, i.e. no new buffer will be allocated. A XDP frags capable driver is expected to set frag_size in xdp_rxq_info data structure to notify the XDP core the fragment size. frag_size set to 0 is interpreted by the XDP core as tail growing is not allowed. Introduce __xdp_rxq_info_reg utility routine to initialize frag_size field. When shrinking, it will work from the last fragment, all the way down to the base buffer depending on the shrinking size. It's important to mention that once you shrink down the fragment(s) are freed, so you can not grow again to the original size. Acked-by: Toke Hoiland-Jorgensen Acked-by: John Fastabend Acked-by: Jakub Kicinski Co-developed-by: Lorenzo Bianconi Signed-off-by: Lorenzo Bianconi Signed-off-by: Eelco Chaudron Link: https://lore.kernel.org/r/eabda3485dda4f2f158b477729337327e609461d.1642758637.git.lorenzo@kernel.org Signed-off-by: Alexei Starovoitov --- include/net/xdp.h | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/xdp.h b/include/net/xdp.h index 52b593321956..b7721c3e4d1f 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -60,6 +60,7 @@ struct xdp_rxq_info { u32 reg_state; struct xdp_mem_info mem; unsigned int napi_id; + u32 frag_size; } ____cacheline_aligned; /* perf critical, avoid false-sharing */ struct xdp_txq_info { @@ -304,6 +305,8 @@ struct xdp_frame *xdp_convert_buff_to_frame(struct xdp_buff *xdp) return xdp_frame; } +void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, + struct xdp_buff *xdp); void xdp_return_frame(struct xdp_frame *xdpf); void xdp_return_frame_rx_napi(struct xdp_frame *xdpf); void xdp_return_buff(struct xdp_buff *xdp); @@ -340,8 +343,17 @@ out: __xdp_release_frame(xdpf->data, mem); } -int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, - struct net_device *dev, u32 queue_index, unsigned int napi_id); +int __xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, + struct net_device *dev, u32 queue_index, + unsigned int napi_id, u32 frag_size); +static inline int +xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, + struct net_device *dev, u32 queue_index, + unsigned int napi_id) +{ + return __xdp_rxq_info_reg(xdp_rxq, dev, queue_index, napi_id, 0); +} + void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq); void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq); bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq); -- cgit v1.2.3 From f45d5b6ce2e835834c94b8b700787984f02cd662 Mon Sep 17 00:00:00 2001 From: Toke Hoiland-Jorgensen Date: Fri, 21 Jan 2022 11:10:02 +0100 Subject: bpf: generalise tail call map compatibility check The check for tail call map compatibility ensures that tail calls only happen between maps of the same type. To ensure backwards compatibility for XDP frags we need a similar type of check for cpumap and devmap programs, so move the state from bpf_array_aux into bpf_map, add xdp_has_frags to the check, and apply the same check to cpumap and devmap. Acked-by: John Fastabend Co-developed-by: Lorenzo Bianconi Signed-off-by: Lorenzo Bianconi Signed-off-by: Toke Hoiland-Jorgensen Link: https://lore.kernel.org/r/f19fd97c0328a39927f3ad03e1ca6b43fd53cdfd.1642758637.git.lorenzo@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 30 +++++++++++++++++++----------- 1 file changed, 19 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e93ed028a030..e8ec8d2f2fe3 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -194,6 +194,17 @@ struct bpf_map { struct work_struct work; struct mutex freeze_mutex; atomic64_t writecnt; + /* 'Ownership' of program-containing map is claimed by the first program + * that is going to use this map or by the first program which FD is + * stored in the map to make sure that all callers and callees have the + * same prog type, JITed flag and xdp_has_frags flag. + */ + struct { + spinlock_t lock; + enum bpf_prog_type type; + bool jited; + bool xdp_has_frags; + } owner; }; static inline bool map_value_has_spin_lock(const struct bpf_map *map) @@ -994,16 +1005,6 @@ struct bpf_prog_aux { }; struct bpf_array_aux { - /* 'Ownership' of prog array is claimed by the first program that - * is going to use this map or by the first program which FD is - * stored in the map to make sure that all callers and callees have - * the same prog type and JITed flag. - */ - struct { - spinlock_t lock; - enum bpf_prog_type type; - bool jited; - } owner; /* Programs with direct jumps into programs part of this array. */ struct list_head poke_progs; struct bpf_map *map; @@ -1178,7 +1179,14 @@ struct bpf_event_entry { struct rcu_head rcu; }; -bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp); +static inline bool map_type_contains_progs(struct bpf_map *map) +{ + return map->map_type == BPF_MAP_TYPE_PROG_ARRAY || + map->map_type == BPF_MAP_TYPE_DEVMAP || + map->map_type == BPF_MAP_TYPE_CPUMAP; +} + +bool bpf_prog_map_compatible(struct bpf_map *map, const struct bpf_prog *fp); int bpf_prog_calc_tag(struct bpf_prog *fp); const struct bpf_func_proto *bpf_get_trace_printk_proto(void); -- cgit v1.2.3 From 3f364222d032eea6b245780e845ad213dab28cdd Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Fri, 21 Jan 2022 11:10:03 +0100 Subject: net: xdp: introduce bpf_xdp_pointer utility routine Similar to skb_header_pointer, introduce bpf_xdp_pointer utility routine to return a pointer to a given position in the xdp_buff if the requested area (offset + len) is contained in a contiguous memory area otherwise it will be copied in a bounce buffer provided by the caller. Similar to the tc counterpart, introduce the two following xdp helpers: - bpf_xdp_load_bytes - bpf_xdp_store_bytes Reviewed-by: Eelco Chaudron Acked-by: Toke Hoiland-Jorgensen Acked-by: John Fastabend Acked-by: Jakub Kicinski Signed-off-by: Lorenzo Bianconi Link: https://lore.kernel.org/r/ab285c1efdd5b7a9d361348b1e7d3ef49f6382b3.1642758637.git.lorenzo@kernel.org Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 5a28772063f6..16a7574292a5 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5060,6 +5060,22 @@ union bpf_attr { * Get the total size of a given xdp buff (linear and paged area) * Return * The total size of a given xdp buffer. + * + * long bpf_xdp_load_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len) + * Description + * This helper is provided as an easy way to load data from a + * xdp buffer. It can be used to load *len* bytes from *offset* from + * the frame associated to *xdp_md*, into the buffer pointed by + * *buf*. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_xdp_store_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len) + * Description + * Store *len* bytes from buffer *buf* into the frame + * associated to *xdp_md*, at *offset*. + * Return + * 0 on success, or a negative error in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5251,6 +5267,8 @@ union bpf_attr { FN(get_retval), \ FN(set_retval), \ FN(xdp_get_buff_len), \ + FN(xdp_load_bytes), \ + FN(xdp_store_bytes), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3