From: Pu Lehui pulehui@huawei.com

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4NI6R CVE: NA

--------------------------------

BPF program call helper functions according to bpf_func_id. Misorder id of helper function will destroy the consistency of BPF program, making it unusable in other versions. Let's backport __BPF_FUNC_MAPPER and the corresponding annotation from mainline.

Signed-off-by: Pu Lehui pulehui@huawei.com Reviewed-by: Kuohai Xu xukuohai@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- include/uapi/linux/bpf.h | 599 ++++++++++++++++++++++++++++++--- tools/include/uapi/linux/bpf.h | 599 ++++++++++++++++++++++++++++++--- 2 files changed, 1116 insertions(+), 82 deletions(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 9a347aefbb40a..075487d409704 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2039,52 +2039,52 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle) + * int bpf_rc_repeat(void *ctx) * 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** (). + * report a successfully decoded repeat key message. This delays + * the generation of a key up event for previously generated + * key down event. * - * Some protocols include a toggle bit, in case the button was - * released and pressed again between consecutive scancodes. + * 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. * - * 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) + * 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 repeat key message. This delays - * the generation of a key up event for previously generated - * key down event. + * 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 IR protocols like NEC have a special IR message for - * repeating last button, for when a button is held down. + * 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 * - * uint64_t bpf_skb_cgroup_id(struct sk_buff *skb) + * u64 bpf_skb_cgroup_id(struct sk_buff *skb) * Description * Return the cgroup v2 id of the socket associated with the *skb*. * This is roughly similar to the **bpf_get_cgroup_classid**\ () @@ -2100,6 +2100,38 @@ union bpf_attr { * 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. + * + * void *bpf_get_local_storage(void *map, u64 flags) + * Description + * Get the pointer to the local storage area. + * The type and the size of the local storage is defined + * by the *map* argument. + * The *flags* meaning is specific for each map type, + * and has to be 0 for cgroup local storage. + * + * Depending on the BPF program type, a local storage area + * can be shared between multiple instances of the BPF program, + * running simultaneously. + * + * A user should care about the synchronization by himself. + * For example, by using the **BPF_STX_XADD** instruction to alter + * the shared data. + * Return + * A pointer to the local storage area. + * + * int bpf_sk_select_reuseport(struct sk_reuseport_md *reuse, struct bpf_map *map, void *key, u64 flags) + * Description + * Select a **SO_REUSEPORT** socket from a + * **BPF_MAP_TYPE_REUSEPORT_ARRAY** *map*. + * It checks the selected socket is matching the incoming + * request in the socket buffer. + * Return + * 0 on success, or a negative error in case of failure. + * * u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level) * Description * Return id of cgroup v2 that is ancestor of cgroup associated @@ -2118,36 +2150,492 @@ union bpf_attr { * Return * The id is returned or 0 in case the id could not be retrieved. * - * u64 bpf_get_current_cgroup_id(void) + * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags) + * Description + * Look for TCP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-**NULL**, released via **bpf_sk_release**\ (). + * + * The *ctx* should point to the context of the program, such as + * the skb or socket (depending on the hook in use). This is used + * to determine the base network namespace for the lookup. + * + * *tuple_size* must be one of: + * + * **sizeof**\ (*tuple*\ **->ipv4**) + * Look for an IPv4 socket. + * **sizeof**\ (*tuple*\ **->ipv6**) + * Look for an IPv6 socket. + * + * If the *netns* is a negative signed 32-bit integer, then the + * socket lookup table in the netns associated with the *ctx* will + * will be used. For the TC hooks, this is the netns of the device + * in the skb. For socket hooks, this is the netns of the socket. + * If *netns* is any other signed 32-bit value greater than or + * equal to zero then it specifies the ID of the netns relative to + * the netns associated with the *ctx*. *netns* values beyond the + * range of 32-bit integers are reserved for future use. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * Return + * Pointer to **struct bpf_sock**, or **NULL** in case of failure. + * For sockets with reuseport option, the **struct bpf_sock** + * result is from *reuse*\ **->socks**\ [] using the hash of the + * tuple. + * + * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags) + * Description + * Look for UDP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-**NULL**, released via **bpf_sk_release**\ (). + * + * The *ctx* should point to the context of the program, such as + * the skb or socket (depending on the hook in use). This is used + * to determine the base network namespace for the lookup. + * + * *tuple_size* must be one of: + * + * **sizeof**\ (*tuple*\ **->ipv4**) + * Look for an IPv4 socket. + * **sizeof**\ (*tuple*\ **->ipv6**) + * Look for an IPv6 socket. + * + * If the *netns* is a negative signed 32-bit integer, then the + * socket lookup table in the netns associated with the *ctx* will + * will be used. For the TC hooks, this is the netns of the device + * in the skb. For socket hooks, this is the netns of the socket. + * If *netns* is any other signed 32-bit value greater than or + * equal to zero then it specifies the ID of the netns relative to + * the netns associated with the *ctx*. *netns* values beyond the + * range of 32-bit integers are reserved for future use. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * Return + * Pointer to **struct bpf_sock**, or **NULL** in case of failure. + * For sockets with reuseport option, the **struct bpf_sock** + * result is from *reuse*\ **->socks**\ [] using the hash of the + * tuple. + * + * int bpf_sk_release(struct bpf_sock *sock) + * Description + * Release the reference held by *sock*. *sock* must be a + * non-**NULL** pointer that was returned from + * **bpf_sk_lookup_xxx**\ (). + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags) + * Description + * Push an element *value* in *map*. *flags* is one of: + * + * **BPF_EXIST** + * If the queue/stack is full, the oldest element is + * removed to make room for this. * Return - * A 64-bit integer containing the current cgroup id based - * on the cgroup within which the current task is running. + * 0 on success, or a negative error in case of failure. + * + * int bpf_map_pop_elem(struct bpf_map *map, void *value) + * Description + * Pop an element from *map*. + * Return + * 0 on success, or a negative error in case of failure. * - * void* get_local_storage(void *map, u64 flags) + * int bpf_map_peek_elem(struct bpf_map *map, void *value) + * Description + * Get an element from *map* without removing it. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_msg_push_data(struct sk_msg_buff *msg, u32 start, u32 len, u64 flags) * Description - * Get the pointer to the local storage area. - * The type and the size of the local storage is defined - * by the *map* argument. - * The *flags* meaning is specific for each map type, - * and has to be 0 for cgroup local storage. + * For socket policies, insert *len* bytes into *msg* at offset + * *start*. * - * Depending on the bpf program type, a local storage area - * can be shared between multiple instances of the bpf program, - * running simultaneously. + * If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a + * *msg* it may want to insert metadata or options into the *msg*. + * This can later be read and used by any of the lower layer BPF + * hooks. * - * A user should care about the synchronization by himself. - * For example, by using the BPF_STX_XADD instruction to alter - * the shared data. + * This helper may fail if under memory pressure (a malloc + * fails) in these cases BPF programs will get an appropriate + * error and BPF programs will need to handle them. * Return - * Pointer to the local storage area. + * 0 on success, or a negative error in case of failure. * - * int bpf_sk_select_reuseport(struct sk_reuseport_md *reuse, struct bpf_map *map, void *key, u64 flags) + * int bpf_msg_pop_data(struct sk_msg_buff *msg, u32 start, u32 len, u64 flags) * Description - * Select a SO_REUSEPORT sk from a BPF_MAP_TYPE_REUSEPORT_ARRAY map - * It checks the selected sk is matching the incoming - * request in the skb. + * Will remove *len* bytes from a *msg* starting at byte *start*. + * This may result in **ENOMEM** errors under certain situations if + * an allocation and copy are required due to a full ring buffer. + * However, the helper will try to avoid doing the allocation + * if possible. Other errors can occur if input parameters are + * invalid either due to *start* byte not being valid part of *msg* + * payload and/or *pop* value being to large. * Return * 0 on success, or a negative error in case of failure. + * + * int bpf_rc_pointer_rel(void *ctx, s32 rel_x, s32 rel_y) + * Description + * This helper is used in programs implementing IR decoding, to + * report a successfully decoded pointer movement. + * + * 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 + * + * int bpf_spin_lock(struct bpf_spin_lock *lock) + * Description + * Acquire a spinlock represented by the pointer *lock*, which is + * stored as part of a value of a map. Taking the lock allows to + * safely update the rest of the fields in that value. The + * spinlock can (and must) later be released with a call to + * **bpf_spin_unlock**\ (\ *lock*\ ). + * + * Spinlocks in BPF programs come with a number of restrictions + * and constraints: + * + * * **bpf_spin_lock** objects are only allowed inside maps of + * types **BPF_MAP_TYPE_HASH** and **BPF_MAP_TYPE_ARRAY** (this + * list could be extended in the future). + * * BTF description of the map is mandatory. + * * The BPF program can take ONE lock at a time, since taking two + * or more could cause dead locks. + * * Only one **struct bpf_spin_lock** is allowed per map element. + * * When the lock is taken, calls (either BPF to BPF or helpers) + * are not allowed. + * * The **BPF_LD_ABS** and **BPF_LD_IND** instructions are not + * allowed inside a spinlock-ed region. + * * The BPF program MUST call **bpf_spin_unlock**\ () to release + * the lock, on all execution paths, before it returns. + * * The BPF program can access **struct bpf_spin_lock** only via + * the **bpf_spin_lock**\ () and **bpf_spin_unlock**\ () + * helpers. Loading or storing data into the **struct + * bpf_spin_lock** *lock*\ **;** field of a map is not allowed. + * * To use the **bpf_spin_lock**\ () helper, the BTF description + * of the map value must be a struct and have **struct + * bpf_spin_lock** *anyname*\ **;** field at the top level. + * Nested lock inside another struct is not allowed. + * * The **struct bpf_spin_lock** *lock* field in a map value must + * be aligned on a multiple of 4 bytes in that value. + * * Syscall with command **BPF_MAP_LOOKUP_ELEM** does not copy + * the **bpf_spin_lock** field to user space. + * * Syscall with command **BPF_MAP_UPDATE_ELEM**, or update from + * a BPF program, do not update the **bpf_spin_lock** field. + * * **bpf_spin_lock** cannot be on the stack or inside a + * networking packet (it can only be inside of a map values). + * * **bpf_spin_lock** is available to root only. + * * Tracing programs and socket filter programs cannot use + * **bpf_spin_lock**\ () due to insufficient preemption checks + * (but this may change in the future). + * * **bpf_spin_lock** is not allowed in inner maps of map-in-map. + * Return + * 0 + * + * int bpf_spin_unlock(struct bpf_spin_lock *lock) + * Description + * Release the *lock* previously locked by a call to + * **bpf_spin_lock**\ (\ *lock*\ ). + * Return + * 0 + * + * struct bpf_sock *bpf_sk_fullsock(struct bpf_sock *sk) + * Description + * This helper gets a **struct bpf_sock** pointer such + * that all the fields in this **bpf_sock** can be accessed. + * Return + * A **struct bpf_sock** pointer on success, or **NULL** in + * case of failure. + * + * struct bpf_tcp_sock *bpf_tcp_sock(struct bpf_sock *sk) + * Description + * This helper gets a **struct bpf_tcp_sock** pointer from a + * **struct bpf_sock** pointer. + * Return + * A **struct bpf_tcp_sock** pointer on success, or **NULL** in + * case of failure. + * + * int bpf_skb_ecn_set_ce(struct sk_buff *skb) + * Description + * Set ECN (Explicit Congestion Notification) field of IP header + * to **CE** (Congestion Encountered) if current value is **ECT** + * (ECN Capable Transport). Otherwise, do nothing. Works with IPv6 + * and IPv4. + * Return + * 1 if the **CE** flag is set (either by the current helper call + * or because it was already present), 0 if it is not set. + * + * struct bpf_sock *bpf_get_listener_sock(struct bpf_sock *sk) + * Description + * Return a **struct bpf_sock** pointer in **TCP_LISTEN** state. + * **bpf_sk_release**\ () is unnecessary and not allowed. + * Return + * A **struct bpf_sock** pointer on success, or **NULL** in + * case of failure. + * + * struct bpf_sock *bpf_skc_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags) + * Description + * Look for TCP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-**NULL**, released via **bpf_sk_release**\ (). + * + * This function is identical to **bpf_sk_lookup_tcp**\ (), except + * that it also returns timewait or request sockets. Use + * **bpf_sk_fullsock**\ () or **bpf_tcp_sock**\ () to access the + * full structure. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * Return + * Pointer to **struct bpf_sock**, or **NULL** in case of failure. + * For sockets with reuseport option, the **struct bpf_sock** + * result is from *reuse*\ **->socks**\ [] using the hash of the + * tuple. + * + * int bpf_tcp_check_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len) + * Description + * Check whether *iph* and *th* contain a valid SYN cookie ACK for + * the listening socket in *sk*. + * + * *iph* points to the start of the IPv4 or IPv6 header, while + * *iph_len* contains **sizeof**\ (**struct iphdr**) or + * **sizeof**\ (**struct ip6hdr**). + * + * *th* points to the start of the TCP header, while *th_len* + * contains **sizeof**\ (**struct tcphdr**). + * + * Return + * 0 if *iph* and *th* are a valid SYN cookie ACK, or a negative + * error otherwise. + * + * int bpf_sysctl_get_name(struct bpf_sysctl *ctx, char *buf, size_t buf_len, u64 flags) + * Description + * Get name of sysctl in /proc/sys/ and copy it into provided by + * program buffer *buf* of size *buf_len*. + * + * The buffer is always NUL terminated, unless it's zero-sized. + * + * If *flags* is zero, full name (e.g. "net/ipv4/tcp_mem") is + * copied. Use **BPF_F_SYSCTL_BASE_NAME** flag to copy base name + * only (e.g. "tcp_mem"). + * Return + * Number of character copied (not including the trailing NUL). + * + * **-E2BIG** if the buffer wasn't big enough (*buf* will contain + * truncated name in this case). + * + * int bpf_sysctl_get_current_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len) + * Description + * Get current value of sysctl as it is presented in /proc/sys + * (incl. newline, etc), and copy it as a string into provided + * by program buffer *buf* of size *buf_len*. + * + * The whole value is copied, no matter what file position user + * space issued e.g. sys_read at. + * + * The buffer is always NUL terminated, unless it's zero-sized. + * Return + * Number of character copied (not including the trailing NUL). + * + * **-E2BIG** if the buffer wasn't big enough (*buf* will contain + * truncated name in this case). + * + * **-EINVAL** if current value was unavailable, e.g. because + * sysctl is uninitialized and read returns -EIO for it. + * + * int bpf_sysctl_get_new_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len) + * Description + * Get new value being written by user space to sysctl (before + * the actual write happens) and copy it as a string into + * provided by program buffer *buf* of size *buf_len*. + * + * User space may write new value at file position > 0. + * + * The buffer is always NUL terminated, unless it's zero-sized. + * Return + * Number of character copied (not including the trailing NUL). + * + * **-E2BIG** if the buffer wasn't big enough (*buf* will contain + * truncated name in this case). + * + * **-EINVAL** if sysctl is being read. + * + * int bpf_sysctl_set_new_value(struct bpf_sysctl *ctx, const char *buf, size_t buf_len) + * Description + * Override new value being written by user space to sysctl with + * value provided by program in buffer *buf* of size *buf_len*. + * + * *buf* should contain a string in same form as provided by user + * space on sysctl write. + * + * User space may write new value at file position > 0. To override + * the whole sysctl value file position should be set to zero. + * Return + * 0 on success. + * + * **-E2BIG** if the *buf_len* is too big. + * + * **-EINVAL** if sysctl is being read. + * + * int bpf_strtol(const char *buf, size_t buf_len, u64 flags, long *res) + * Description + * Convert the initial part of the string from buffer *buf* of + * size *buf_len* to a long integer according to the given base + * and save the result in *res*. + * + * The string may begin with an arbitrary amount of white space + * (as determined by **isspace**\ (3)) followed by a single + * optional '**-**' sign. + * + * Five least significant bits of *flags* encode base, other bits + * are currently unused. + * + * Base must be either 8, 10, 16 or 0 to detect it automatically + * similar to user space **strtol**\ (3). + * Return + * Number of characters consumed on success. Must be positive but + * no more than *buf_len*. + * + * **-EINVAL** if no valid digits were found or unsupported base + * was provided. + * + * **-ERANGE** if resulting value was out of range. + * + * int bpf_strtoul(const char *buf, size_t buf_len, u64 flags, unsigned long *res) + * Description + * Convert the initial part of the string from buffer *buf* of + * size *buf_len* to an unsigned long integer according to the + * given base and save the result in *res*. + * + * The string may begin with an arbitrary amount of white space + * (as determined by **isspace**\ (3)). + * + * Five least significant bits of *flags* encode base, other bits + * are currently unused. + * + * Base must be either 8, 10, 16 or 0 to detect it automatically + * similar to user space **strtoul**\ (3). + * Return + * Number of characters consumed on success. Must be positive but + * no more than *buf_len*. + * + * **-EINVAL** if no valid digits were found or unsupported base + * was provided. + * + * **-ERANGE** if resulting value was out of range. + * + * void *bpf_sk_storage_get(struct bpf_map *map, struct bpf_sock *sk, void *value, u64 flags) + * Description + * Get a bpf-local-storage from a *sk*. + * + * Logically, it could be thought of getting the value from + * a *map* with *sk* as the **key**. From this + * perspective, the usage is not much different from + * **bpf_map_lookup_elem**\ (*map*, **&**\ *sk*) except this + * helper enforces the key must be a full socket and the map must + * be a **BPF_MAP_TYPE_SK_STORAGE** also. + * + * Underneath, the value is stored locally at *sk* instead of + * the *map*. The *map* is used as the bpf-local-storage + * "type". The bpf-local-storage "type" (i.e. the *map*) is + * searched against all bpf-local-storages residing at *sk*. + * + * An optional *flags* (**BPF_SK_STORAGE_GET_F_CREATE**) can be + * used such that a new bpf-local-storage will be + * created if one does not exist. *value* can be used + * together with **BPF_SK_STORAGE_GET_F_CREATE** to specify + * the initial value of a bpf-local-storage. If *value* is + * **NULL**, the new bpf-local-storage will be zero initialized. + * Return + * A bpf-local-storage pointer is returned on success. + * + * **NULL** if not found or there was an error in adding + * a new bpf-local-storage. + * + * int bpf_sk_storage_delete(struct bpf_map *map, struct bpf_sock *sk) + * Description + * Delete a bpf-local-storage from a *sk*. + * Return + * 0 on success. + * + * **-ENOENT** if the bpf-local-storage cannot be found. + * + * int bpf_send_signal(u32 sig) + * Description + * Send signal *sig* to the current task. + * Return + * 0 on success or successfully queued. + * + * **-EBUSY** if work queue under nmi is full. + * + * **-EINVAL** if *sig* is invalid. + * + * **-EPERM** if no permission to send the *sig*. + * + * **-EAGAIN** if bpf program can try again. + * + * s64 bpf_tcp_gen_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len) + * Description + * Try to issue a SYN cookie for the packet with corresponding + * IP/TCP headers, *iph* and *th*, on the listening socket in *sk*. + * + * *iph* points to the start of the IPv4 or IPv6 header, while + * *iph_len* contains **sizeof**\ (**struct iphdr**) or + * **sizeof**\ (**struct ip6hdr**). + * + * *th* points to the start of the TCP header, while *th_len* + * contains the length of the TCP header. + * + * Return + * On success, lower 32 bits hold the generated SYN cookie in + * followed by 16 bits which hold the MSS value for that cookie, + * and the top 16 bits are unused. + * + * On failure, the returned value is one of the following: + * + * **-EINVAL** SYN cookie cannot be issued due to error + * + * **-ENOENT** SYN cookie should not be issued (no SYN flood) + * + * **-EOPNOTSUPP** kernel configuration does not enable SYN cookies + * + * **-EPROTONOSUPPORT** IP packet version is not 4 or 6 + * + * int bpf_skb_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size) + * Description + * Write raw *data* blob into a special BPF perf event held by + * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf + * event must have the following attributes: **PERF_SAMPLE_RAW** + * as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and + * **PERF_COUNT_SW_BPF_OUTPUT** as **config**. + * + * The *flags* are used to indicate the index in *map* for which + * the value must be put, masked with **BPF_F_INDEX_MASK**. + * Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU** + * to indicate that the index of the current CPU core should be + * used. + * + * The value to write, of *size*, is passed through eBPF stack and + * pointed by *data*. + * + * *ctx* is a pointer to in-kernel struct sk_buff. + * + * This helper is similar to **bpf_perf_event_output**\ () but + * restricted to raw_tracepoint bpf programs. + * Return + * 0 on success, or a negative error in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2233,7 +2721,36 @@ union bpf_attr { FN(get_current_cgroup_id), \ FN(get_local_storage), \ FN(sk_select_reuseport), \ - FN(skb_ancestor_cgroup_id), + FN(skb_ancestor_cgroup_id), \ + FN(sk_lookup_tcp), \ + FN(sk_lookup_udp), \ + FN(sk_release), \ + FN(map_push_elem), \ + FN(map_pop_elem), \ + FN(map_peek_elem), \ + FN(msg_push_data), \ + FN(msg_pop_data), \ + FN(rc_pointer_rel), \ + FN(spin_lock), \ + FN(spin_unlock), \ + FN(sk_fullsock), \ + FN(tcp_sock), \ + FN(skb_ecn_set_ce), \ + FN(get_listener_sock), \ + FN(skc_lookup_tcp), \ + FN(tcp_check_syncookie), \ + FN(sysctl_get_name), \ + FN(sysctl_get_current_value), \ + FN(sysctl_get_new_value), \ + FN(sysctl_set_new_value), \ + FN(strtol), \ + FN(strtoul), \ + FN(sk_storage_get), \ + FN(sk_storage_delete), \ + FN(send_signal), \ + FN(tcp_gen_syncookie), \ + FN(skb_output), + /* For BPF prog consistency, Don't add it casually */

/* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 58454e7693f43..abfb085d61c5a 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2042,52 +2042,52 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle) + * int bpf_rc_repeat(void *ctx) * 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** (). + * report a successfully decoded repeat key message. This delays + * the generation of a key up event for previously generated + * key down event. * - * Some protocols include a toggle bit, in case the button was - * released and pressed again between consecutive scancodes. + * 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. * - * 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) + * 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 repeat key message. This delays - * the generation of a key up event for previously generated - * key down event. + * 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 IR protocols like NEC have a special IR message for - * repeating last button, for when a button is held down. + * 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 * - * uint64_t bpf_skb_cgroup_id(struct sk_buff *skb) + * u64 bpf_skb_cgroup_id(struct sk_buff *skb) * Description * Return the cgroup v2 id of the socket associated with the *skb*. * This is roughly similar to the **bpf_get_cgroup_classid**\ () @@ -2103,6 +2103,38 @@ union bpf_attr { * 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. + * + * void *bpf_get_local_storage(void *map, u64 flags) + * Description + * Get the pointer to the local storage area. + * The type and the size of the local storage is defined + * by the *map* argument. + * The *flags* meaning is specific for each map type, + * and has to be 0 for cgroup local storage. + * + * Depending on the BPF program type, a local storage area + * can be shared between multiple instances of the BPF program, + * running simultaneously. + * + * A user should care about the synchronization by himself. + * For example, by using the **BPF_STX_XADD** instruction to alter + * the shared data. + * Return + * A pointer to the local storage area. + * + * int bpf_sk_select_reuseport(struct sk_reuseport_md *reuse, struct bpf_map *map, void *key, u64 flags) + * Description + * Select a **SO_REUSEPORT** socket from a + * **BPF_MAP_TYPE_REUSEPORT_ARRAY** *map*. + * It checks the selected socket is matching the incoming + * request in the socket buffer. + * Return + * 0 on success, or a negative error in case of failure. + * * u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level) * Description * Return id of cgroup v2 that is ancestor of cgroup associated @@ -2121,36 +2153,492 @@ union bpf_attr { * Return * The id is returned or 0 in case the id could not be retrieved. * - * u64 bpf_get_current_cgroup_id(void) + * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags) + * Description + * Look for TCP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-**NULL**, released via **bpf_sk_release**\ (). + * + * The *ctx* should point to the context of the program, such as + * the skb or socket (depending on the hook in use). This is used + * to determine the base network namespace for the lookup. + * + * *tuple_size* must be one of: + * + * **sizeof**\ (*tuple*\ **->ipv4**) + * Look for an IPv4 socket. + * **sizeof**\ (*tuple*\ **->ipv6**) + * Look for an IPv6 socket. + * + * If the *netns* is a negative signed 32-bit integer, then the + * socket lookup table in the netns associated with the *ctx* will + * will be used. For the TC hooks, this is the netns of the device + * in the skb. For socket hooks, this is the netns of the socket. + * If *netns* is any other signed 32-bit value greater than or + * equal to zero then it specifies the ID of the netns relative to + * the netns associated with the *ctx*. *netns* values beyond the + * range of 32-bit integers are reserved for future use. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * Return + * Pointer to **struct bpf_sock**, or **NULL** in case of failure. + * For sockets with reuseport option, the **struct bpf_sock** + * result is from *reuse*\ **->socks**\ [] using the hash of the + * tuple. + * + * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags) + * Description + * Look for UDP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-**NULL**, released via **bpf_sk_release**\ (). + * + * The *ctx* should point to the context of the program, such as + * the skb or socket (depending on the hook in use). This is used + * to determine the base network namespace for the lookup. + * + * *tuple_size* must be one of: + * + * **sizeof**\ (*tuple*\ **->ipv4**) + * Look for an IPv4 socket. + * **sizeof**\ (*tuple*\ **->ipv6**) + * Look for an IPv6 socket. + * + * If the *netns* is a negative signed 32-bit integer, then the + * socket lookup table in the netns associated with the *ctx* will + * will be used. For the TC hooks, this is the netns of the device + * in the skb. For socket hooks, this is the netns of the socket. + * If *netns* is any other signed 32-bit value greater than or + * equal to zero then it specifies the ID of the netns relative to + * the netns associated with the *ctx*. *netns* values beyond the + * range of 32-bit integers are reserved for future use. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * Return + * Pointer to **struct bpf_sock**, or **NULL** in case of failure. + * For sockets with reuseport option, the **struct bpf_sock** + * result is from *reuse*\ **->socks**\ [] using the hash of the + * tuple. + * + * int bpf_sk_release(struct bpf_sock *sock) + * Description + * Release the reference held by *sock*. *sock* must be a + * non-**NULL** pointer that was returned from + * **bpf_sk_lookup_xxx**\ (). + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags) + * Description + * Push an element *value* in *map*. *flags* is one of: + * + * **BPF_EXIST** + * If the queue/stack is full, the oldest element is + * removed to make room for this. * Return - * A 64-bit integer containing the current cgroup id based - * on the cgroup within which the current task is running. + * 0 on success, or a negative error in case of failure. + * + * int bpf_map_pop_elem(struct bpf_map *map, void *value) + * Description + * Pop an element from *map*. + * Return + * 0 on success, or a negative error in case of failure. * - * void* get_local_storage(void *map, u64 flags) + * int bpf_map_peek_elem(struct bpf_map *map, void *value) + * Description + * Get an element from *map* without removing it. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_msg_push_data(struct sk_msg_buff *msg, u32 start, u32 len, u64 flags) * Description - * Get the pointer to the local storage area. - * The type and the size of the local storage is defined - * by the *map* argument. - * The *flags* meaning is specific for each map type, - * and has to be 0 for cgroup local storage. + * For socket policies, insert *len* bytes into *msg* at offset + * *start*. * - * Depending on the bpf program type, a local storage area - * can be shared between multiple instances of the bpf program, - * running simultaneously. + * If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a + * *msg* it may want to insert metadata or options into the *msg*. + * This can later be read and used by any of the lower layer BPF + * hooks. * - * A user should care about the synchronization by himself. - * For example, by using the BPF_STX_XADD instruction to alter - * the shared data. + * This helper may fail if under memory pressure (a malloc + * fails) in these cases BPF programs will get an appropriate + * error and BPF programs will need to handle them. * Return - * Pointer to the local storage area. + * 0 on success, or a negative error in case of failure. * - * int bpf_sk_select_reuseport(struct sk_reuseport_md *reuse, struct bpf_map *map, void *key, u64 flags) + * int bpf_msg_pop_data(struct sk_msg_buff *msg, u32 start, u32 len, u64 flags) * Description - * Select a SO_REUSEPORT sk from a BPF_MAP_TYPE_REUSEPORT_ARRAY map - * It checks the selected sk is matching the incoming - * request in the skb. + * Will remove *len* bytes from a *msg* starting at byte *start*. + * This may result in **ENOMEM** errors under certain situations if + * an allocation and copy are required due to a full ring buffer. + * However, the helper will try to avoid doing the allocation + * if possible. Other errors can occur if input parameters are + * invalid either due to *start* byte not being valid part of *msg* + * payload and/or *pop* value being to large. * Return * 0 on success, or a negative error in case of failure. + * + * int bpf_rc_pointer_rel(void *ctx, s32 rel_x, s32 rel_y) + * Description + * This helper is used in programs implementing IR decoding, to + * report a successfully decoded pointer movement. + * + * 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 + * + * int bpf_spin_lock(struct bpf_spin_lock *lock) + * Description + * Acquire a spinlock represented by the pointer *lock*, which is + * stored as part of a value of a map. Taking the lock allows to + * safely update the rest of the fields in that value. The + * spinlock can (and must) later be released with a call to + * **bpf_spin_unlock**\ (\ *lock*\ ). + * + * Spinlocks in BPF programs come with a number of restrictions + * and constraints: + * + * * **bpf_spin_lock** objects are only allowed inside maps of + * types **BPF_MAP_TYPE_HASH** and **BPF_MAP_TYPE_ARRAY** (this + * list could be extended in the future). + * * BTF description of the map is mandatory. + * * The BPF program can take ONE lock at a time, since taking two + * or more could cause dead locks. + * * Only one **struct bpf_spin_lock** is allowed per map element. + * * When the lock is taken, calls (either BPF to BPF or helpers) + * are not allowed. + * * The **BPF_LD_ABS** and **BPF_LD_IND** instructions are not + * allowed inside a spinlock-ed region. + * * The BPF program MUST call **bpf_spin_unlock**\ () to release + * the lock, on all execution paths, before it returns. + * * The BPF program can access **struct bpf_spin_lock** only via + * the **bpf_spin_lock**\ () and **bpf_spin_unlock**\ () + * helpers. Loading or storing data into the **struct + * bpf_spin_lock** *lock*\ **;** field of a map is not allowed. + * * To use the **bpf_spin_lock**\ () helper, the BTF description + * of the map value must be a struct and have **struct + * bpf_spin_lock** *anyname*\ **;** field at the top level. + * Nested lock inside another struct is not allowed. + * * The **struct bpf_spin_lock** *lock* field in a map value must + * be aligned on a multiple of 4 bytes in that value. + * * Syscall with command **BPF_MAP_LOOKUP_ELEM** does not copy + * the **bpf_spin_lock** field to user space. + * * Syscall with command **BPF_MAP_UPDATE_ELEM**, or update from + * a BPF program, do not update the **bpf_spin_lock** field. + * * **bpf_spin_lock** cannot be on the stack or inside a + * networking packet (it can only be inside of a map values). + * * **bpf_spin_lock** is available to root only. + * * Tracing programs and socket filter programs cannot use + * **bpf_spin_lock**\ () due to insufficient preemption checks + * (but this may change in the future). + * * **bpf_spin_lock** is not allowed in inner maps of map-in-map. + * Return + * 0 + * + * int bpf_spin_unlock(struct bpf_spin_lock *lock) + * Description + * Release the *lock* previously locked by a call to + * **bpf_spin_lock**\ (\ *lock*\ ). + * Return + * 0 + * + * struct bpf_sock *bpf_sk_fullsock(struct bpf_sock *sk) + * Description + * This helper gets a **struct bpf_sock** pointer such + * that all the fields in this **bpf_sock** can be accessed. + * Return + * A **struct bpf_sock** pointer on success, or **NULL** in + * case of failure. + * + * struct bpf_tcp_sock *bpf_tcp_sock(struct bpf_sock *sk) + * Description + * This helper gets a **struct bpf_tcp_sock** pointer from a + * **struct bpf_sock** pointer. + * Return + * A **struct bpf_tcp_sock** pointer on success, or **NULL** in + * case of failure. + * + * int bpf_skb_ecn_set_ce(struct sk_buff *skb) + * Description + * Set ECN (Explicit Congestion Notification) field of IP header + * to **CE** (Congestion Encountered) if current value is **ECT** + * (ECN Capable Transport). Otherwise, do nothing. Works with IPv6 + * and IPv4. + * Return + * 1 if the **CE** flag is set (either by the current helper call + * or because it was already present), 0 if it is not set. + * + * struct bpf_sock *bpf_get_listener_sock(struct bpf_sock *sk) + * Description + * Return a **struct bpf_sock** pointer in **TCP_LISTEN** state. + * **bpf_sk_release**\ () is unnecessary and not allowed. + * Return + * A **struct bpf_sock** pointer on success, or **NULL** in + * case of failure. + * + * struct bpf_sock *bpf_skc_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags) + * Description + * Look for TCP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-**NULL**, released via **bpf_sk_release**\ (). + * + * This function is identical to **bpf_sk_lookup_tcp**\ (), except + * that it also returns timewait or request sockets. Use + * **bpf_sk_fullsock**\ () or **bpf_tcp_sock**\ () to access the + * full structure. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * Return + * Pointer to **struct bpf_sock**, or **NULL** in case of failure. + * For sockets with reuseport option, the **struct bpf_sock** + * result is from *reuse*\ **->socks**\ [] using the hash of the + * tuple. + * + * int bpf_tcp_check_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len) + * Description + * Check whether *iph* and *th* contain a valid SYN cookie ACK for + * the listening socket in *sk*. + * + * *iph* points to the start of the IPv4 or IPv6 header, while + * *iph_len* contains **sizeof**\ (**struct iphdr**) or + * **sizeof**\ (**struct ip6hdr**). + * + * *th* points to the start of the TCP header, while *th_len* + * contains **sizeof**\ (**struct tcphdr**). + * + * Return + * 0 if *iph* and *th* are a valid SYN cookie ACK, or a negative + * error otherwise. + * + * int bpf_sysctl_get_name(struct bpf_sysctl *ctx, char *buf, size_t buf_len, u64 flags) + * Description + * Get name of sysctl in /proc/sys/ and copy it into provided by + * program buffer *buf* of size *buf_len*. + * + * The buffer is always NUL terminated, unless it's zero-sized. + * + * If *flags* is zero, full name (e.g. "net/ipv4/tcp_mem") is + * copied. Use **BPF_F_SYSCTL_BASE_NAME** flag to copy base name + * only (e.g. "tcp_mem"). + * Return + * Number of character copied (not including the trailing NUL). + * + * **-E2BIG** if the buffer wasn't big enough (*buf* will contain + * truncated name in this case). + * + * int bpf_sysctl_get_current_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len) + * Description + * Get current value of sysctl as it is presented in /proc/sys + * (incl. newline, etc), and copy it as a string into provided + * by program buffer *buf* of size *buf_len*. + * + * The whole value is copied, no matter what file position user + * space issued e.g. sys_read at. + * + * The buffer is always NUL terminated, unless it's zero-sized. + * Return + * Number of character copied (not including the trailing NUL). + * + * **-E2BIG** if the buffer wasn't big enough (*buf* will contain + * truncated name in this case). + * + * **-EINVAL** if current value was unavailable, e.g. because + * sysctl is uninitialized and read returns -EIO for it. + * + * int bpf_sysctl_get_new_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len) + * Description + * Get new value being written by user space to sysctl (before + * the actual write happens) and copy it as a string into + * provided by program buffer *buf* of size *buf_len*. + * + * User space may write new value at file position > 0. + * + * The buffer is always NUL terminated, unless it's zero-sized. + * Return + * Number of character copied (not including the trailing NUL). + * + * **-E2BIG** if the buffer wasn't big enough (*buf* will contain + * truncated name in this case). + * + * **-EINVAL** if sysctl is being read. + * + * int bpf_sysctl_set_new_value(struct bpf_sysctl *ctx, const char *buf, size_t buf_len) + * Description + * Override new value being written by user space to sysctl with + * value provided by program in buffer *buf* of size *buf_len*. + * + * *buf* should contain a string in same form as provided by user + * space on sysctl write. + * + * User space may write new value at file position > 0. To override + * the whole sysctl value file position should be set to zero. + * Return + * 0 on success. + * + * **-E2BIG** if the *buf_len* is too big. + * + * **-EINVAL** if sysctl is being read. + * + * int bpf_strtol(const char *buf, size_t buf_len, u64 flags, long *res) + * Description + * Convert the initial part of the string from buffer *buf* of + * size *buf_len* to a long integer according to the given base + * and save the result in *res*. + * + * The string may begin with an arbitrary amount of white space + * (as determined by **isspace**\ (3)) followed by a single + * optional '**-**' sign. + * + * Five least significant bits of *flags* encode base, other bits + * are currently unused. + * + * Base must be either 8, 10, 16 or 0 to detect it automatically + * similar to user space **strtol**\ (3). + * Return + * Number of characters consumed on success. Must be positive but + * no more than *buf_len*. + * + * **-EINVAL** if no valid digits were found or unsupported base + * was provided. + * + * **-ERANGE** if resulting value was out of range. + * + * int bpf_strtoul(const char *buf, size_t buf_len, u64 flags, unsigned long *res) + * Description + * Convert the initial part of the string from buffer *buf* of + * size *buf_len* to an unsigned long integer according to the + * given base and save the result in *res*. + * + * The string may begin with an arbitrary amount of white space + * (as determined by **isspace**\ (3)). + * + * Five least significant bits of *flags* encode base, other bits + * are currently unused. + * + * Base must be either 8, 10, 16 or 0 to detect it automatically + * similar to user space **strtoul**\ (3). + * Return + * Number of characters consumed on success. Must be positive but + * no more than *buf_len*. + * + * **-EINVAL** if no valid digits were found or unsupported base + * was provided. + * + * **-ERANGE** if resulting value was out of range. + * + * void *bpf_sk_storage_get(struct bpf_map *map, struct bpf_sock *sk, void *value, u64 flags) + * Description + * Get a bpf-local-storage from a *sk*. + * + * Logically, it could be thought of getting the value from + * a *map* with *sk* as the **key**. From this + * perspective, the usage is not much different from + * **bpf_map_lookup_elem**\ (*map*, **&**\ *sk*) except this + * helper enforces the key must be a full socket and the map must + * be a **BPF_MAP_TYPE_SK_STORAGE** also. + * + * Underneath, the value is stored locally at *sk* instead of + * the *map*. The *map* is used as the bpf-local-storage + * "type". The bpf-local-storage "type" (i.e. the *map*) is + * searched against all bpf-local-storages residing at *sk*. + * + * An optional *flags* (**BPF_SK_STORAGE_GET_F_CREATE**) can be + * used such that a new bpf-local-storage will be + * created if one does not exist. *value* can be used + * together with **BPF_SK_STORAGE_GET_F_CREATE** to specify + * the initial value of a bpf-local-storage. If *value* is + * **NULL**, the new bpf-local-storage will be zero initialized. + * Return + * A bpf-local-storage pointer is returned on success. + * + * **NULL** if not found or there was an error in adding + * a new bpf-local-storage. + * + * int bpf_sk_storage_delete(struct bpf_map *map, struct bpf_sock *sk) + * Description + * Delete a bpf-local-storage from a *sk*. + * Return + * 0 on success. + * + * **-ENOENT** if the bpf-local-storage cannot be found. + * + * int bpf_send_signal(u32 sig) + * Description + * Send signal *sig* to the current task. + * Return + * 0 on success or successfully queued. + * + * **-EBUSY** if work queue under nmi is full. + * + * **-EINVAL** if *sig* is invalid. + * + * **-EPERM** if no permission to send the *sig*. + * + * **-EAGAIN** if bpf program can try again. + * + * s64 bpf_tcp_gen_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len) + * Description + * Try to issue a SYN cookie for the packet with corresponding + * IP/TCP headers, *iph* and *th*, on the listening socket in *sk*. + * + * *iph* points to the start of the IPv4 or IPv6 header, while + * *iph_len* contains **sizeof**\ (**struct iphdr**) or + * **sizeof**\ (**struct ip6hdr**). + * + * *th* points to the start of the TCP header, while *th_len* + * contains the length of the TCP header. + * + * Return + * On success, lower 32 bits hold the generated SYN cookie in + * followed by 16 bits which hold the MSS value for that cookie, + * and the top 16 bits are unused. + * + * On failure, the returned value is one of the following: + * + * **-EINVAL** SYN cookie cannot be issued due to error + * + * **-ENOENT** SYN cookie should not be issued (no SYN flood) + * + * **-EOPNOTSUPP** kernel configuration does not enable SYN cookies + * + * **-EPROTONOSUPPORT** IP packet version is not 4 or 6 + * + * int bpf_skb_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size) + * Description + * Write raw *data* blob into a special BPF perf event held by + * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf + * event must have the following attributes: **PERF_SAMPLE_RAW** + * as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and + * **PERF_COUNT_SW_BPF_OUTPUT** as **config**. + * + * The *flags* are used to indicate the index in *map* for which + * the value must be put, masked with **BPF_F_INDEX_MASK**. + * Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU** + * to indicate that the index of the current CPU core should be + * used. + * + * The value to write, of *size*, is passed through eBPF stack and + * pointed by *data*. + * + * *ctx* is a pointer to in-kernel struct sk_buff. + * + * This helper is similar to **bpf_perf_event_output**\ () but + * restricted to raw_tracepoint bpf programs. + * Return + * 0 on success, or a negative error in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2236,7 +2724,36 @@ union bpf_attr { FN(get_current_cgroup_id), \ FN(get_local_storage), \ FN(sk_select_reuseport), \ - FN(skb_ancestor_cgroup_id), + FN(skb_ancestor_cgroup_id), \ + FN(sk_lookup_tcp), \ + FN(sk_lookup_udp), \ + FN(sk_release), \ + FN(map_push_elem), \ + FN(map_pop_elem), \ + FN(map_peek_elem), \ + FN(msg_push_data), \ + FN(msg_pop_data), \ + FN(rc_pointer_rel), \ + FN(spin_lock), \ + FN(spin_unlock), \ + FN(sk_fullsock), \ + FN(tcp_sock), \ + FN(skb_ecn_set_ce), \ + FN(get_listener_sock), \ + FN(skc_lookup_tcp), \ + FN(tcp_check_syncookie), \ + FN(sysctl_get_name), \ + FN(sysctl_get_current_value), \ + FN(sysctl_get_new_value), \ + FN(sysctl_set_new_value), \ + FN(strtol), \ + FN(strtoul), \ + FN(sk_storage_get), \ + FN(sk_storage_delete), \ + FN(send_signal), \ + FN(tcp_gen_syncookie), \ + FN(skb_output), + /* For BPF prog consistency, Don't add it casually */

/* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call

From: Daniel Borkmann daniel@iogearbox.net

mainline inclusion from mainline-v5.5-rc1 commit 75a1a607bb7e6d918be3aca11ec2214a275392f4 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4NI6R CVE: NA

--------------------------------

Add two new probe_kernel_read_strict() and strncpy_from_unsafe_strict() helpers which by default alias to the __probe_kernel_read() and the __strncpy_from_unsafe(), respectively, but can be overridden by archs which have non-overlapping address ranges for kernel space and user space in order to bail out with -EFAULT when attempting to probe user memory including non-canonical user access addresses [0]:

4-level page tables: user-space mem: 0x0000000000000000 - 0x00007fffffffffff non-canonical: 0x0000800000000000 - 0xffff7fffffffffff

5-level page tables: user-space mem: 0x0000000000000000 - 0x00ffffffffffffff non-canonical: 0x0100000000000000 - 0xfeffffffffffffff

The idea is that these helpers are complementary to the probe_user_read() and strncpy_from_unsafe_user() which probe user-only memory. Both added helpers here do the same, but for kernel-only addresses.

Both set of helpers are going to be used for BPF tracing. They also explicitly avoid throwing the splat for non-canonical user addresses from 00c42373d397 ("x86-64: add warning for non-canonical user access address dereferences").

For compat, the current probe_kernel_read() and strncpy_from_unsafe() are left as-is.

[0] Documentation/x86/x86_64/mm.txt

Signed-off-by: Daniel Borkmann daniel@iogearbox.net Signed-off-by: Alexei Starovoitov ast@kernel.org Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Masami Hiramatsu mhiramat@kernel.org Cc: x86@kernel.org Link: https://lore.kernel.org/bpf/eefeefd769aa5a013531f491a71f0936779e916b.1572649... Signed-off-by: Pu Lehui pulehui@huawei.com Reviewed-by: Kuohai Xu xukuohai@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- arch/x86/mm/Makefile | 2 +- arch/x86/mm/maccess.c | 43 +++++++++++++++++++++++++++++++++++++++++ include/linux/uaccess.h | 4 ++++ mm/maccess.c | 25 +++++++++++++++++++++++- 4 files changed, 72 insertions(+), 2 deletions(-) create mode 100644 arch/x86/mm/maccess.c

diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 4b101dd6e52f3..14623619df2e8 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -13,7 +13,7 @@ CFLAGS_REMOVE_mem_encrypt_identity.o = -pg endif

obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \ - pat.o pgtable.o physaddr.o setup_nx.o tlb.o cpu_entry_area.o + pat.o pgtable.o physaddr.o setup_nx.o tlb.o cpu_entry_area.o maccess.o

# Make sure __phys_addr has no stackprotector nostackp := $(call cc-option, -fno-stack-protector) diff --git a/arch/x86/mm/maccess.c b/arch/x86/mm/maccess.c new file mode 100644 index 0000000000000..f5b85bdc0535c --- /dev/null +++ b/arch/x86/mm/maccess.c @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/uaccess.h> +#include <linux/kernel.h> + +#ifdef CONFIG_X86_64 +static __always_inline u64 canonical_address(u64 vaddr, u8 vaddr_bits) +{ + return ((s64)vaddr << (64 - vaddr_bits)) >> (64 - vaddr_bits); +} + +static __always_inline bool invalid_probe_range(u64 vaddr) +{ + /* + * Range covering the highest possible canonical userspace address + * as well as non-canonical address range. For the canonical range + * we also need to include the userspace guard page. + */ + return vaddr < TASK_SIZE_MAX + PAGE_SIZE || + canonical_address(vaddr, boot_cpu_data.x86_virt_bits) != vaddr; +} +#else +static __always_inline bool invalid_probe_range(u64 vaddr) +{ + return vaddr < TASK_SIZE_MAX; +} +#endif + +long probe_kernel_read_strict(void *dst, const void *src, size_t size) +{ + if (unlikely(invalid_probe_range((unsigned long)src))) + return -EFAULT; + + return __probe_kernel_read(dst, src, size); +} + +long strncpy_from_unsafe_strict(char *dst, const void *unsafe_addr, long count) +{ + if (unlikely(invalid_probe_range((unsigned long)unsafe_addr))) + return -EFAULT; + + return __strncpy_from_unsafe(dst, unsafe_addr, count); +} diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 29ebf7f1e47cb..a0061e018ce8a 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -237,6 +237,7 @@ static inline unsigned long __copy_from_user_inatomic_nocache(void *to, * happens, handle that and return -EFAULT. */ extern long probe_kernel_read(void *dst, const void *src, size_t size); +extern long probe_kernel_read_strict(void *dst, const void *src, size_t size); extern long __probe_kernel_read(void *dst, const void *src, size_t size);

/* @@ -275,6 +276,9 @@ extern long notrace probe_user_write(void __user *dst, const void *src, size_t s extern long notrace __probe_user_write(void __user *dst, const void *src, size_t size);

extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); +extern long strncpy_from_unsafe_strict(char *dst, const void *unsafe_addr, + long count); +extern long __strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); extern long strncpy_from_unsafe_user(char *dst, const void __user *unsafe_addr, long count); extern long strnlen_unsafe_user(const void __user *unsafe_addr, long count); diff --git a/mm/maccess.c b/mm/maccess.c index 35381585318f6..bafa89a9fbc79 100644 --- a/mm/maccess.c +++ b/mm/maccess.c @@ -42,11 +42,20 @@ probe_write_common(void __user *dst, const void *src, size_t size) * do_page_fault() doesn't attempt to take mmap_sem. This makes * probe_kernel_read() suitable for use within regions where the caller * already holds mmap_sem, or other locks which nest inside mmap_sem. + * + * probe_kernel_read_strict() is the same as probe_kernel_read() except for + * the case where architectures have non-overlapping user and kernel address + * ranges: probe_kernel_read_strict() will additionally return -EFAULT for + * probing memory on a user address range where probe_user_read() is supposed + * to be used instead. */

long __weak probe_kernel_read(void *dst, const void *src, size_t size) __attribute__((alias("__probe_kernel_read")));

+long __weak probe_kernel_read_strict(void *dst, const void *src, size_t size) + __attribute__((alias("__probe_kernel_read"))); + long __probe_kernel_read(void *dst, const void *src, size_t size) { long ret; @@ -156,8 +165,22 @@ EXPORT_SYMBOL_GPL(probe_user_write); * * If @count is smaller than the length of the string, copies @count-1 bytes, * sets the last byte of @dst buffer to NUL and returns @count. + * + * strncpy_from_unsafe_strict() is the same as strncpy_from_unsafe() except + * for the case where architectures have non-overlapping user and kernel address + * ranges: strncpy_from_unsafe_strict() will additionally return -EFAULT for + * probing memory on a user address range where strncpy_from_unsafe_user() is + * supposed to be used instead. */ -long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count) + +long __weak strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count) + __attribute__((alias("__strncpy_from_unsafe"))); + +long __weak strncpy_from_unsafe_strict(char *dst, const void *unsafe_addr, + long count) + __attribute__((alias("__strncpy_from_unsafe"))); + +long __strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count) { mm_segment_t old_fs = get_fs(); const void *src = unsafe_addr;

From: Daniel Borkmann daniel@iogearbox.net

mainline inclusion from mainline-v5.5-rc1 commit 6ae08ae3dea2cfa03dd3665a3c8475c2d429ef47 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4NI6R CVE: NA

--------------------------------

The current bpf_probe_read() and bpf_probe_read_str() helpers are broken in that they assume they can be used for probing memory access for kernel space addresses /as well as/ user space addresses.

However, plain use of probe_kernel_read() for both cases will attempt to always access kernel space address space given access is performed under KERNEL_DS and some archs in-fact have overlapping address spaces where a kernel pointer and user pointer would have the /same/ address value and therefore accessing application memory via bpf_probe_read{,_str}() would read garbage values.

Lets fix BPF side by making use of recently added 3d7081822f7f ("uaccess: Add non-pagefault user-space read functions"). Unfortunately, the only way to fix this status quo is to add dedicated bpf_probe_read_{user,kernel}() and bpf_probe_read_{user,kernel}_str() helpers. The bpf_probe_read{,_str}() helpers are kept as-is to retain their current behavior.

The two *_user() variants attempt the access always under USER_DS set, the two *_kernel() variants will -EFAULT when accessing user memory if the underlying architecture has non-overlapping address ranges, also avoiding throwing the kernel warning via 00c42373d397 ("x86-64: add warning for non-canonical user access address dereferences").

Fixes: a5e8c07059d0 ("bpf: add bpf_probe_read_str helper") Fixes: 2541517c32be ("tracing, perf: Implement BPF programs attached to kprobes") Signed-off-by: Daniel Borkmann daniel@iogearbox.net Signed-off-by: Alexei Starovoitov ast@kernel.org Acked-by: Andrii Nakryiko andriin@fb.com Link: https://lore.kernel.org/bpf/796ee46e948bc808d54891a1108435f8652c6ca4.1572649... Conflicts: kernel/trace/bpf_trace.c Signed-off-by: Pu Lehui pulehui@huawei.com Reviewed-by: Kuohai Xu xukuohai@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- include/uapi/linux/bpf.h | 122 +++++++++++----- kernel/trace/bpf_trace.c | 169 +++++++++++++++++----- tools/include/uapi/linux/bpf.h | 122 +++++++++++----- tools/testing/selftests/bpf/bpf_helpers.h | 8 + 4 files changed, 304 insertions(+), 117 deletions(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 075487d409704..a2d71d15ff3c3 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -466,10 +466,13 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_probe_read(void *dst, u32 size, const void *src) + * int bpf_probe_read(void *dst, u32 size, const void *unsafe_ptr) * Description * For tracing programs, safely attempt to read *size* bytes from - * address *src* and store the data in *dst*. + * kernel space address *unsafe_ptr* and store the data in *dst*. + * + * Generally, use bpf_probe_read_user() or bpf_probe_read_kernel() + * instead. * Return * 0 on success, or a negative error in case of failure. * @@ -1329,45 +1332,14 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_probe_read_str(void *dst, int size, const void *unsafe_ptr) + * int bpf_probe_read_str(void *dst, u32 size, const void *unsafe_ptr) * Description - * Copy a NUL terminated string from an unsafe address - * *unsafe_ptr* to *dst*. The *size* should include the - * terminating NUL byte. In case the string length is smaller than - * *size*, the target is not padded with further NUL bytes. If the - * string length is larger than *size*, just *size*-1 bytes are - * copied and the last byte is set to NUL. - * - * On success, the length of the copied string is returned. This - * makes this helper useful in tracing programs for reading - * strings, and more importantly to get its length at runtime. See - * the following snippet: - * - * :: - * - * SEC("kprobe/sys_open") - * void bpf_sys_open(struct pt_regs *ctx) - * { - * char buf[PATHLEN]; // PATHLEN is defined to 256 - * int res = bpf_probe_read_str(buf, sizeof(buf), - * ctx->di); - * - * // Consume buf, for example push it to - * // userspace via bpf_perf_event_output(); we - * // can use res (the string length) as event - * // size, after checking its boundaries. - * } - * - * In comparison, using **bpf_probe_read()** helper here instead - * to read the string would require to estimate the length at - * compile time, and would often result in copying more memory - * than necessary. + * Copy a NUL terminated string from an unsafe kernel address + * *unsafe_ptr* to *dst*. See bpf_probe_read_kernel_str() for + * more details. * - * Another useful use case is when parsing individual process - * arguments or individual environment variables navigating - * *current*\ **->mm->arg_start** and *current*\ - * **->mm->env_start**: using this helper and the return value, - * one can quickly iterate at the right offset of the memory area. + * Generally, use bpf_probe_read_user_str() or bpf_probe_read_kernel_str() + * instead. * Return * On success, the strictly positive length of the string, * including the trailing NUL character. On error, a negative @@ -2636,6 +2608,72 @@ union bpf_attr { * restricted to raw_tracepoint bpf programs. * Return * 0 on success, or a negative error in case of failure. + * + * int bpf_probe_read_user(void *dst, u32 size, const void *unsafe_ptr) + * Description + * Safely attempt to read *size* bytes from user space address + * *unsafe_ptr* and store the data in *dst*. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr) + * Description + * Safely attempt to read *size* bytes from kernel space address + * *unsafe_ptr* and store the data in *dst*. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_probe_read_user_str(void *dst, u32 size, const void *unsafe_ptr) + * Description + * Copy a NUL terminated string from an unsafe user address + * *unsafe_ptr* to *dst*. The *size* should include the + * terminating NUL byte. In case the string length is smaller than + * *size*, the target is not padded with further NUL bytes. If the + * string length is larger than *size*, just *size*-1 bytes are + * copied and the last byte is set to NUL. + * + * On success, the length of the copied string is returned. This + * makes this helper useful in tracing programs for reading + * strings, and more importantly to get its length at runtime. See + * the following snippet: + * + * :: + * + * SEC("kprobe/sys_open") + * void bpf_sys_open(struct pt_regs *ctx) + * { + * char buf[PATHLEN]; // PATHLEN is defined to 256 + * int res = bpf_probe_read_user_str(buf, sizeof(buf), + * ctx->di); + * + * // Consume buf, for example push it to + * // userspace via bpf_perf_event_output(); we + * // can use res (the string length) as event + * // size, after checking its boundaries. + * } + * + * In comparison, using **bpf_probe_read_user()** helper here + * instead to read the string would require to estimate the length + * at compile time, and would often result in copying more memory + * than necessary. + * + * Another useful use case is when parsing individual process + * arguments or individual environment variables navigating + * *current*\ **->mm->arg_start** and *current*\ + * **->mm->env_start**: using this helper and the return value, + * one can quickly iterate at the right offset of the memory area. + * Return + * On success, the strictly positive length of the string, + * including the trailing NUL character. On error, a negative + * value. + * + * int bpf_probe_read_kernel_str(void *dst, u32 size, const void *unsafe_ptr) + * Description + * Copy a NUL terminated string from an unsafe kernel address *unsafe_ptr* + * to *dst*. Same semantics as with bpf_probe_read_user_str() apply. + * Return + * On success, the strictly positive length of the string, including + * the trailing NUL character. On error, a negative value. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2749,7 +2787,11 @@ union bpf_attr { FN(sk_storage_delete), \ FN(send_signal), \ FN(tcp_gen_syncookie), \ - FN(skb_output), + FN(skb_output), \ + FN(probe_read_user), \ + FN(probe_read_kernel), \ + FN(probe_read_user_str), \ + FN(probe_read_kernel_str), /* For BPF prog consistency, Don't add it casually */

/* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index daa5e74bee70b..9a53096b79a01 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -133,19 +133,136 @@ static const struct bpf_func_proto bpf_override_return_proto = { }; #endif

-BPF_CALL_3(bpf_probe_read, void *, dst, u32, size, const void *, unsafe_ptr) +BPF_CALL_3(bpf_probe_read_user, void *, dst, u32, size, + const void __user *, unsafe_ptr) +{ + int ret = probe_user_read(dst, unsafe_ptr, size); + + if (unlikely(ret < 0)) + memset(dst, 0, size); + + return ret; +} + +static const struct bpf_func_proto bpf_probe_read_user_proto = { + .func = bpf_probe_read_user, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_UNINIT_MEM, + .arg2_type = ARG_CONST_SIZE_OR_ZERO, + .arg3_type = ARG_ANYTHING, +}; + +BPF_CALL_3(bpf_probe_read_user_str, void *, dst, u32, size, + const void __user *, unsafe_ptr) +{ + int ret = strncpy_from_unsafe_user(dst, unsafe_ptr, size); + + if (unlikely(ret < 0)) + memset(dst, 0, size); + + return ret; +} + +static const struct bpf_func_proto bpf_probe_read_user_str_proto = { + .func = bpf_probe_read_user_str, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_UNINIT_MEM, + .arg2_type = ARG_CONST_SIZE_OR_ZERO, + .arg3_type = ARG_ANYTHING, +}; + +static __always_inline int +bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr, + const bool compat) { int ret;

- ret = probe_kernel_read(dst, unsafe_ptr, size); + ret = compat ? probe_kernel_read(dst, unsafe_ptr, size) : + probe_kernel_read_strict(dst, unsafe_ptr, size); if (unlikely(ret < 0)) memset(dst, 0, size);

return ret; }

-static const struct bpf_func_proto bpf_probe_read_proto = { - .func = bpf_probe_read, +BPF_CALL_3(bpf_probe_read_kernel, void *, dst, u32, size, + const void *, unsafe_ptr) +{ + return bpf_probe_read_kernel_common(dst, size, unsafe_ptr, false); +} + +static const struct bpf_func_proto bpf_probe_read_kernel_proto = { + .func = bpf_probe_read_kernel, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_UNINIT_MEM, + .arg2_type = ARG_CONST_SIZE_OR_ZERO, + .arg3_type = ARG_ANYTHING, +}; + +BPF_CALL_3(bpf_probe_read_compat, void *, dst, u32, size, + const void *, unsafe_ptr) +{ + return bpf_probe_read_kernel_common(dst, size, unsafe_ptr, true); +} + +static const struct bpf_func_proto bpf_probe_read_compat_proto = { + .func = bpf_probe_read_compat, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_UNINIT_MEM, + .arg2_type = ARG_CONST_SIZE_OR_ZERO, + .arg3_type = ARG_ANYTHING, +}; + +static __always_inline int +bpf_probe_read_kernel_str_common(void *dst, u32 size, const void *unsafe_ptr, + const bool compat) +{ + int ret; + + /* + * The strncpy_from_unsafe_*() call will likely not fill the entire + * buffer, but that's okay in this circumstance as we're probing + * arbitrary memory anyway similar to bpf_probe_read_*() and might + * as well probe the stack. Thus, memory is explicitly cleared + * only in error case, so that improper users ignoring return + * code altogether don't copy garbage; otherwise length of string + * is returned that can be used for bpf_perf_event_output() et al. + */ + ret = compat ? strncpy_from_unsafe(dst, unsafe_ptr, size) : + strncpy_from_unsafe_strict(dst, unsafe_ptr, size); + if (unlikely(ret < 0)) + memset(dst, 0, size); + + return ret; +} + +BPF_CALL_3(bpf_probe_read_kernel_str, void *, dst, u32, size, + const void *, unsafe_ptr) +{ + return bpf_probe_read_kernel_str_common(dst, size, unsafe_ptr, false); +} + +static const struct bpf_func_proto bpf_probe_read_kernel_str_proto = { + .func = bpf_probe_read_kernel_str, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_UNINIT_MEM, + .arg2_type = ARG_CONST_SIZE_OR_ZERO, + .arg3_type = ARG_ANYTHING, +}; + +BPF_CALL_3(bpf_probe_read_compat_str, void *, dst, u32, size, + const void *, unsafe_ptr) +{ + return bpf_probe_read_kernel_str_common(dst, size, unsafe_ptr, true); +} + +static const struct bpf_func_proto bpf_probe_read_compat_str_proto = { + .func = bpf_probe_read_compat_str, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, @@ -552,36 +669,6 @@ static const struct bpf_func_proto bpf_current_task_under_cgroup_proto = { .arg2_type = ARG_ANYTHING, };

-BPF_CALL_3(bpf_probe_read_str, void *, dst, u32, size, - const void *, unsafe_ptr) -{ - int ret; - - /* - * The strncpy_from_unsafe() call will likely not fill the entire - * buffer, but that's okay in this circumstance as we're probing - * arbitrary memory anyway similar to bpf_probe_read() and might - * as well probe the stack. Thus, memory is explicitly cleared - * only in error case, so that improper users ignoring return - * code altogether don't copy garbage; otherwise length of string - * is returned that can be used for bpf_perf_event_output() et al. - */ - ret = strncpy_from_unsafe(dst, unsafe_ptr, size); - if (unlikely(ret < 0)) - memset(dst, 0, size); - - return ret; -} - -static const struct bpf_func_proto bpf_probe_read_str_proto = { - .func = bpf_probe_read_str, - .gpl_only = true, - .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_UNINIT_MEM, - .arg2_type = ARG_CONST_SIZE_OR_ZERO, - .arg3_type = ARG_ANYTHING, -}; - static const struct bpf_func_proto * tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -592,8 +679,6 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_map_update_elem_proto; case BPF_FUNC_map_delete_elem: return &bpf_map_delete_elem_proto; - case BPF_FUNC_probe_read: - return &bpf_probe_read_proto; case BPF_FUNC_ktime_get_ns: return &bpf_ktime_get_ns_proto; case BPF_FUNC_tail_call: @@ -620,8 +705,18 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_current_task_under_cgroup_proto; case BPF_FUNC_get_prandom_u32: return &bpf_get_prandom_u32_proto; + case BPF_FUNC_probe_read_user: + return &bpf_probe_read_user_proto; + case BPF_FUNC_probe_read_kernel: + return &bpf_probe_read_kernel_proto; + case BPF_FUNC_probe_read: + return &bpf_probe_read_compat_proto; + case BPF_FUNC_probe_read_user_str: + return &bpf_probe_read_user_str_proto; + case BPF_FUNC_probe_read_kernel_str: + return &bpf_probe_read_kernel_str_proto; case BPF_FUNC_probe_read_str: - return &bpf_probe_read_str_proto; + return &bpf_probe_read_compat_str_proto; #ifdef CONFIG_CGROUPS case BPF_FUNC_get_current_cgroup_id: return &bpf_get_current_cgroup_id_proto; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index abfb085d61c5a..5aec1766c2cd7 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -462,10 +462,13 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_probe_read(void *dst, u32 size, const void *src) + * int bpf_probe_read(void *dst, u32 size, const void *unsafe_ptr) * Description * For tracing programs, safely attempt to read *size* bytes from - * address *src* and store the data in *dst*. + * kernel space address *unsafe_ptr* and store the data in *dst*. + * + * Generally, use bpf_probe_read_user() or bpf_probe_read_kernel() + * instead. * Return * 0 on success, or a negative error in case of failure. * @@ -1325,45 +1328,14 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_probe_read_str(void *dst, int size, const void *unsafe_ptr) + * int bpf_probe_read_str(void *dst, u32 size, const void *unsafe_ptr) * Description - * Copy a NUL terminated string from an unsafe address - * *unsafe_ptr* to *dst*. The *size* should include the - * terminating NUL byte. In case the string length is smaller than - * *size*, the target is not padded with further NUL bytes. If the - * string length is larger than *size*, just *size*-1 bytes are - * copied and the last byte is set to NUL. - * - * On success, the length of the copied string is returned. This - * makes this helper useful in tracing programs for reading - * strings, and more importantly to get its length at runtime. See - * the following snippet: - * - * :: - * - * SEC("kprobe/sys_open") - * void bpf_sys_open(struct pt_regs *ctx) - * { - * char buf[PATHLEN]; // PATHLEN is defined to 256 - * int res = bpf_probe_read_str(buf, sizeof(buf), - * ctx->di); - * - * // Consume buf, for example push it to - * // userspace via bpf_perf_event_output(); we - * // can use res (the string length) as event - * // size, after checking its boundaries. - * } - * - * In comparison, using **bpf_probe_read()** helper here instead - * to read the string would require to estimate the length at - * compile time, and would often result in copying more memory - * than necessary. + * Copy a NUL terminated string from an unsafe kernel address + * *unsafe_ptr* to *dst*. See bpf_probe_read_kernel_str() for + * more details. * - * Another useful use case is when parsing individual process - * arguments or individual environment variables navigating - * *current*\ **->mm->arg_start** and *current*\ - * **->mm->env_start**: using this helper and the return value, - * one can quickly iterate at the right offset of the memory area. + * Generally, use bpf_probe_read_user_str() or bpf_probe_read_kernel_str() + * instead. * Return * On success, the strictly positive length of the string, * including the trailing NUL character. On error, a negative @@ -2639,6 +2611,72 @@ union bpf_attr { * restricted to raw_tracepoint bpf programs. * Return * 0 on success, or a negative error in case of failure. + * + * int bpf_probe_read_user(void *dst, u32 size, const void *unsafe_ptr) + * Description + * Safely attempt to read *size* bytes from user space address + * *unsafe_ptr* and store the data in *dst*. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr) + * Description + * Safely attempt to read *size* bytes from kernel space address + * *unsafe_ptr* and store the data in *dst*. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_probe_read_user_str(void *dst, u32 size, const void *unsafe_ptr) + * Description + * Copy a NUL terminated string from an unsafe user address + * *unsafe_ptr* to *dst*. The *size* should include the + * terminating NUL byte. In case the string length is smaller than + * *size*, the target is not padded with further NUL bytes. If the + * string length is larger than *size*, just *size*-1 bytes are + * copied and the last byte is set to NUL. + * + * On success, the length of the copied string is returned. This + * makes this helper useful in tracing programs for reading + * strings, and more importantly to get its length at runtime. See + * the following snippet: + * + * :: + * + * SEC("kprobe/sys_open") + * void bpf_sys_open(struct pt_regs *ctx) + * { + * char buf[PATHLEN]; // PATHLEN is defined to 256 + * int res = bpf_probe_read_user_str(buf, sizeof(buf), + * ctx->di); + * + * // Consume buf, for example push it to + * // userspace via bpf_perf_event_output(); we + * // can use res (the string length) as event + * // size, after checking its boundaries. + * } + * + * In comparison, using **bpf_probe_read_user()** helper here + * instead to read the string would require to estimate the length + * at compile time, and would often result in copying more memory + * than necessary. + * + * Another useful use case is when parsing individual process + * arguments or individual environment variables navigating + * *current*\ **->mm->arg_start** and *current*\ + * **->mm->env_start**: using this helper and the return value, + * one can quickly iterate at the right offset of the memory area. + * Return + * On success, the strictly positive length of the string, + * including the trailing NUL character. On error, a negative + * value. + * + * int bpf_probe_read_kernel_str(void *dst, u32 size, const void *unsafe_ptr) + * Description + * Copy a NUL terminated string from an unsafe kernel address *unsafe_ptr* + * to *dst*. Same semantics as with bpf_probe_read_user_str() apply. + * Return + * On success, the strictly positive length of the string, including + * the trailing NUL character. On error, a negative value. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2752,7 +2790,11 @@ union bpf_attr { FN(sk_storage_delete), \ FN(send_signal), \ FN(tcp_gen_syncookie), \ - FN(skb_output), + FN(skb_output), \ + FN(probe_read_user), \ + FN(probe_read_kernel), \ + FN(probe_read_user_str), \ + FN(probe_read_kernel_str), /* For BPF prog consistency, Don't add it casually */

/* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index 556688e820264..29610a656350b 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -145,6 +145,14 @@ static unsigned long long (*bpf_skb_cgroup_id)(void *ctx) = (void *) BPF_FUNC_skb_cgroup_id; static unsigned long long (*bpf_skb_ancestor_cgroup_id)(void *ctx, int level) = (void *) BPF_FUNC_skb_ancestor_cgroup_id; +static int (*bpf_probe_read_user)(void *dst, int size, void *unsafe_ptr) = + (void *) BPF_FUNC_probe_read_user; +static int (*bpf_probe_read_kernel)(void *dst, int size, void *unsafe_ptr) = + (void *) BPF_FUNC_probe_read_kernel; +static int (*bpf_probe_read_user_str)(void *dst, int size, void *unsafe_ptr) = + (void *) BPF_FUNC_probe_read_user_str; +static int (*bpf_probe_read_kernel_str)(void *dst, int size, void *unsafe_ptr) = + (void *) BPF_FUNC_probe_read_kernel_str;

/* llvm builtin functions that eBPF C program may use to * emit BPF_LD_ABS and BPF_LD_IND instructions