diff options
author | Jakub Kicinski <kuba@kernel.org> | 2022-03-22 10:36:56 -0700 |
---|---|---|
committer | Jakub Kicinski <kuba@kernel.org> | 2022-03-22 11:18:49 -0700 |
commit | 0db8640df59512dbd423c32077919f10cf35ebc6 (patch) | |
tree | a8e0d6806763ce5c3c84a5a2c29a1cbdb58f5129 /include | |
parent | 4a0cb83ba6e0cd73a50fa4f84736846bf0029f2b (diff) | |
parent | 7f0059b58f0257d895fafd2f2e3afe3bbdf21e64 (diff) | |
download | linux-0db8640df59512dbd423c32077919f10cf35ebc6.tar.bz2 |
Merge https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Alexei Starovoitov says:
====================
pull-request: bpf-next 2022-03-21 v2
We've added 137 non-merge commits during the last 17 day(s) which contain
a total of 143 files changed, 7123 insertions(+), 1092 deletions(-).
The main changes are:
1) Custom SEC() handling in libbpf, from Andrii.
2) subskeleton support, from Delyan.
3) Use btf_tag to recognize __percpu pointers in the verifier, from Hao.
4) Fix net.core.bpf_jit_harden race, from Hou.
5) Fix bpf_sk_lookup remote_port on big-endian, from Jakub.
6) Introduce fprobe (multi kprobe) _without_ arch bits, from Masami.
The arch specific bits will come later.
7) Introduce multi_kprobe bpf programs on top of fprobe, from Jiri.
8) Enable non-atomic allocations in local storage, from Joanne.
9) Various var_off ptr_to_btf_id fixed, from Kumar.
10) bpf_ima_file_hash helper, from Roberto.
11) Add "live packet" mode for XDP in BPF_PROG_RUN, from Toke.
* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (137 commits)
selftests/bpf: Fix kprobe_multi test.
Revert "rethook: x86: Add rethook x86 implementation"
Revert "arm64: rethook: Add arm64 rethook implementation"
Revert "powerpc: Add rethook support"
Revert "ARM: rethook: Add rethook arm implementation"
bpftool: Fix a bug in subskeleton code generation
bpf: Fix bpf_prog_pack when PMU_SIZE is not defined
bpf: Fix bpf_prog_pack for multi-node setup
bpf: Fix warning for cast from restricted gfp_t in verifier
bpf, arm: Fix various typos in comments
libbpf: Close fd in bpf_object__reuse_map
bpftool: Fix print error when show bpf map
bpf: Fix kprobe_multi return probe backtrace
Revert "bpf: Add support to inline bpf_get_func_ip helper on x86"
bpf: Simplify check in btf_parse_hdr()
selftests/bpf/test_lirc_mode2.sh: Exit with proper code
bpf: Check for NULL return from bpf_get_btf_vmlinux
selftests/bpf: Test skipping stacktrace
bpf: Adjust BPF stack helper functions to accommodate skip > 0
bpf: Select proper size for bpf_prog_pack
...
====================
Link: https://lore.kernel.org/r/20220322050159.5507-1-alexei.starovoitov@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'include')
-rw-r--r-- | include/linux/bpf.h | 11 | ||||
-rw-r--r-- | include/linux/bpf_local_storage.h | 7 | ||||
-rw-r--r-- | include/linux/bpf_types.h | 1 | ||||
-rw-r--r-- | include/linux/bpf_verifier.h | 4 | ||||
-rw-r--r-- | include/linux/compiler-clang.h | 25 | ||||
-rw-r--r-- | include/linux/compiler-gcc.h | 3 | ||||
-rw-r--r-- | include/linux/compiler_types.h | 18 | ||||
-rw-r--r-- | include/linux/filter.h | 3 | ||||
-rw-r--r-- | include/linux/fprobe.h | 105 | ||||
-rw-r--r-- | include/linux/ftrace.h | 3 | ||||
-rw-r--r-- | include/linux/kprobes.h | 3 | ||||
-rw-r--r-- | include/linux/rethook.h | 100 | ||||
-rw-r--r-- | include/linux/sched.h | 3 | ||||
-rw-r--r-- | include/linux/skbuff.h | 10 | ||||
-rw-r--r-- | include/linux/skmsg.h | 13 | ||||
-rw-r--r-- | include/linux/sort.h | 2 | ||||
-rw-r--r-- | include/linux/trace_events.h | 7 | ||||
-rw-r--r-- | include/linux/types.h | 1 | ||||
-rw-r--r-- | include/net/xdp.h | 14 | ||||
-rw-r--r-- | include/uapi/linux/bpf.h | 80 |
20 files changed, 362 insertions, 51 deletions
diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 57cb6af3177a..bdb5298735ce 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -334,7 +334,15 @@ enum bpf_type_flag { /* MEM is in user address space. */ MEM_USER = BIT(3 + BPF_BASE_TYPE_BITS), - __BPF_TYPE_LAST_FLAG = MEM_USER, + /* MEM is a percpu memory. MEM_PERCPU tags PTR_TO_BTF_ID. When tagged + * with MEM_PERCPU, PTR_TO_BTF_ID _cannot_ be directly accessed. In + * order to drop this tag, it must be passed into bpf_per_cpu_ptr() + * or bpf_this_cpu_ptr(), which will return the pointer corresponding + * to the specified cpu. + */ + MEM_PERCPU = BIT(4 + BPF_BASE_TYPE_BITS), + + __BPF_TYPE_LAST_FLAG = MEM_PERCPU, }; /* Max number of base types. */ @@ -516,7 +524,6 @@ enum bpf_reg_type { */ PTR_TO_MEM, /* reg points to valid memory region */ PTR_TO_BUF, /* reg points to a read/write buffer */ - PTR_TO_PERCPU_BTF_ID, /* reg points to a percpu kernel variable */ PTR_TO_FUNC, /* reg points to a bpf program function */ __BPF_REG_TYPE_MAX, diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h index 37b3906af8b1..493e63258497 100644 --- a/include/linux/bpf_local_storage.h +++ b/include/linux/bpf_local_storage.h @@ -154,16 +154,17 @@ void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem); struct bpf_local_storage_elem * bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, void *value, - bool charge_mem); + bool charge_mem, gfp_t gfp_flags); int bpf_local_storage_alloc(void *owner, struct bpf_local_storage_map *smap, - struct bpf_local_storage_elem *first_selem); + struct bpf_local_storage_elem *first_selem, + gfp_t gfp_flags); struct bpf_local_storage_data * bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, - void *value, u64 map_flags); + void *value, u64 map_flags, gfp_t gfp_flags); void bpf_local_storage_free_rcu(struct rcu_head *rcu); diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 48a91c51c015..3e24ad0c4b3c 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -140,3 +140,4 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_XDP, xdp) #ifdef CONFIG_PERF_EVENTS BPF_LINK_TYPE(BPF_LINK_TYPE_PERF_EVENT, perf) #endif +BPF_LINK_TYPE(BPF_LINK_TYPE_KPROBE_MULTI, kprobe_multi) diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 7a7be8c057f2..c1fc4af47f69 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -521,6 +521,10 @@ bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt); int check_ptr_off_reg(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno); +int check_func_arg_reg_off(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, int regno, + enum bpf_arg_type arg_type, + bool is_release_func); 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, diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index 3c4de9b6c6e3..babb1347148c 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -68,3 +68,28 @@ #define __nocfi __attribute__((__no_sanitize__("cfi"))) #define __cficanonical __attribute__((__cfi_canonical_jump_table__)) + +/* + * Turn individual warnings and errors on and off locally, depending + * on version. + */ +#define __diag_clang(version, severity, s) \ + __diag_clang_ ## version(__diag_clang_ ## severity s) + +/* Severity used in pragma directives */ +#define __diag_clang_ignore ignored +#define __diag_clang_warn warning +#define __diag_clang_error error + +#define __diag_str1(s) #s +#define __diag_str(s) __diag_str1(s) +#define __diag(s) _Pragma(__diag_str(clang diagnostic s)) + +#if CONFIG_CLANG_VERSION >= 110000 +#define __diag_clang_11(s) __diag(s) +#else +#define __diag_clang_11(s) +#endif + +#define __diag_ignore_all(option, comment) \ + __diag_clang(11, ignore, option) diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index ccbbd31b3aae..d364c98a4a80 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -151,6 +151,9 @@ #define __diag_GCC_8(s) #endif +#define __diag_ignore_all(option, comment) \ + __diag_GCC(8, ignore, option) + /* * Prior to 9.1, -Wno-alloc-size-larger-than (and therefore the "alloc_size" * attribute) do not work, and must be disabled. diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 3f31ff400432..1bc760ba400c 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -4,6 +4,13 @@ #ifndef __ASSEMBLY__ +#if defined(CONFIG_DEBUG_INFO_BTF) && defined(CONFIG_PAHOLE_HAS_BTF_TAG) && \ + __has_attribute(btf_type_tag) +# define BTF_TYPE_TAG(value) __attribute__((btf_type_tag(#value))) +#else +# define BTF_TYPE_TAG(value) /* nothing */ +#endif + #ifdef __CHECKER__ /* address spaces */ # define __kernel __attribute__((address_space(0))) @@ -31,14 +38,11 @@ static inline void __chk_io_ptr(const volatile void __iomem *ptr) { } # define __kernel # ifdef STRUCTLEAK_PLUGIN # define __user __attribute__((user)) -# elif defined(CONFIG_DEBUG_INFO_BTF) && defined(CONFIG_PAHOLE_HAS_BTF_TAG) && \ - __has_attribute(btf_type_tag) -# define __user __attribute__((btf_type_tag("user"))) # else -# define __user +# define __user BTF_TYPE_TAG(user) # endif # define __iomem -# define __percpu +# define __percpu BTF_TYPE_TAG(percpu) # define __rcu # define __chk_user_ptr(x) (void)0 # define __chk_io_ptr(x) (void)0 @@ -371,4 +375,8 @@ struct ftrace_likely_data { #define __diag_error(compiler, version, option, comment) \ __diag_ ## compiler(version, error, option) +#ifndef __diag_ignore_all +#define __diag_ignore_all(option, comment) +#endif + #endif /* __LINUX_COMPILER_TYPES_H */ diff --git a/include/linux/filter.h b/include/linux/filter.h index 9bf26307247f..ed0c0ff42ad5 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -566,6 +566,7 @@ struct bpf_prog { gpl_compatible:1, /* Is filter GPL compatible? */ cb_access:1, /* Is control block accessed? */ dst_needed:1, /* Do we need dst entry? */ + blinding_requested:1, /* needs constant blinding */ blinded:1, /* Was blinded */ is_func:1, /* program is a bpf function */ kprobe_override:1, /* Do we override a kprobe? */ @@ -573,7 +574,7 @@ struct bpf_prog { enforce_expected_attach_type:1, /* Enforce expected_attach_type checking at attach time */ call_get_stack:1, /* Do we call bpf_get_stack() or bpf_get_stackid() */ call_get_func_ip:1, /* Do we call get_func_ip() */ - delivery_time_access:1; /* Accessed __sk_buff->delivery_time_type */ + tstamp_type_access:1; /* Accessed __sk_buff->tstamp_type */ enum bpf_prog_type type; /* Type of BPF program */ enum bpf_attach_type expected_attach_type; /* For some prog types */ u32 len; /* Number of filter blocks */ diff --git a/include/linux/fprobe.h b/include/linux/fprobe.h new file mode 100644 index 000000000000..1c2bde0ead73 --- /dev/null +++ b/include/linux/fprobe.h @@ -0,0 +1,105 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Simple ftrace probe wrapper */ +#ifndef _LINUX_FPROBE_H +#define _LINUX_FPROBE_H + +#include <linux/compiler.h> +#include <linux/ftrace.h> +#include <linux/rethook.h> + +/** + * struct fprobe - ftrace based probe. + * @ops: The ftrace_ops. + * @nmissed: The counter for missing events. + * @flags: The status flag. + * @rethook: The rethook data structure. (internal data) + * @entry_handler: The callback function for function entry. + * @exit_handler: The callback function for function exit. + */ +struct fprobe { +#ifdef CONFIG_FUNCTION_TRACER + /* + * If CONFIG_FUNCTION_TRACER is not set, CONFIG_FPROBE is disabled too. + * But user of fprobe may keep embedding the struct fprobe on their own + * code. To avoid build error, this will keep the fprobe data structure + * defined here, but remove ftrace_ops data structure. + */ + struct ftrace_ops ops; +#endif + unsigned long nmissed; + unsigned int flags; + struct rethook *rethook; + + void (*entry_handler)(struct fprobe *fp, unsigned long entry_ip, struct pt_regs *regs); + void (*exit_handler)(struct fprobe *fp, unsigned long entry_ip, struct pt_regs *regs); +}; + +/* This fprobe is soft-disabled. */ +#define FPROBE_FL_DISABLED 1 + +/* + * This fprobe handler will be shared with kprobes. + * This flag must be set before registering. + */ +#define FPROBE_FL_KPROBE_SHARED 2 + +static inline bool fprobe_disabled(struct fprobe *fp) +{ + return (fp) ? fp->flags & FPROBE_FL_DISABLED : false; +} + +static inline bool fprobe_shared_with_kprobes(struct fprobe *fp) +{ + return (fp) ? fp->flags & FPROBE_FL_KPROBE_SHARED : false; +} + +#ifdef CONFIG_FPROBE +int register_fprobe(struct fprobe *fp, const char *filter, const char *notfilter); +int register_fprobe_ips(struct fprobe *fp, unsigned long *addrs, int num); +int register_fprobe_syms(struct fprobe *fp, const char **syms, int num); +int unregister_fprobe(struct fprobe *fp); +#else +static inline int register_fprobe(struct fprobe *fp, const char *filter, const char *notfilter) +{ + return -EOPNOTSUPP; +} +static inline int register_fprobe_ips(struct fprobe *fp, unsigned long *addrs, int num) +{ + return -EOPNOTSUPP; +} +static inline int register_fprobe_syms(struct fprobe *fp, const char **syms, int num) +{ + return -EOPNOTSUPP; +} +static inline int unregister_fprobe(struct fprobe *fp) +{ + return -EOPNOTSUPP; +} +#endif + +/** + * disable_fprobe() - Disable fprobe + * @fp: The fprobe to be disabled. + * + * This will soft-disable @fp. Note that this doesn't remove the ftrace + * hooks from the function entry. + */ +static inline void disable_fprobe(struct fprobe *fp) +{ + if (fp) + fp->flags |= FPROBE_FL_DISABLED; +} + +/** + * enable_fprobe() - Enable fprobe + * @fp: The fprobe to be enabled. + * + * This will soft-enable @fp. + */ +static inline void enable_fprobe(struct fprobe *fp) +{ + if (fp) + fp->flags &= ~FPROBE_FL_DISABLED; +} + +#endif diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 9999e29187de..60847cbce0da 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -512,6 +512,8 @@ struct dyn_ftrace { int ftrace_set_filter_ip(struct ftrace_ops *ops, unsigned long ip, int remove, int reset); +int ftrace_set_filter_ips(struct ftrace_ops *ops, unsigned long *ips, + unsigned int cnt, int remove, int reset); int ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf, int len, int reset); int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf, @@ -802,6 +804,7 @@ static inline unsigned long ftrace_location(unsigned long ip) #define ftrace_regex_open(ops, flag, inod, file) ({ -ENODEV; }) #define ftrace_set_early_filter(ops, buf, enable) do { } while (0) #define ftrace_set_filter_ip(ops, ip, remove, reset) ({ -ENODEV; }) +#define ftrace_set_filter_ips(ops, ips, cnt, remove, reset) ({ -ENODEV; }) #define ftrace_set_filter(ops, buf, len, reset) ({ -ENODEV; }) #define ftrace_set_notrace(ops, buf, len, reset) ({ -ENODEV; }) #define ftrace_free_filter(ops) do { } while (0) diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 19b884353b15..5f1859836deb 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -427,6 +427,9 @@ static inline struct kprobe *kprobe_running(void) { return NULL; } +#define kprobe_busy_begin() do {} while (0) +#define kprobe_busy_end() do {} while (0) + static inline int register_kprobe(struct kprobe *p) { return -EOPNOTSUPP; diff --git a/include/linux/rethook.h b/include/linux/rethook.h new file mode 100644 index 000000000000..c8ac1e5afcd1 --- /dev/null +++ b/include/linux/rethook.h @@ -0,0 +1,100 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Return hooking with list-based shadow stack. + */ +#ifndef _LINUX_RETHOOK_H +#define _LINUX_RETHOOK_H + +#include <linux/compiler.h> +#include <linux/freelist.h> +#include <linux/kallsyms.h> +#include <linux/llist.h> +#include <linux/rcupdate.h> +#include <linux/refcount.h> + +struct rethook_node; + +typedef void (*rethook_handler_t) (struct rethook_node *, void *, struct pt_regs *); + +/** + * struct rethook - The rethook management data structure. + * @data: The user-defined data storage. + * @handler: The user-defined return hook handler. + * @pool: The pool of struct rethook_node. + * @ref: The reference counter. + * @rcu: The rcu_head for deferred freeing. + * + * Don't embed to another data structure, because this is a self-destructive + * data structure when all rethook_node are freed. + */ +struct rethook { + void *data; + rethook_handler_t handler; + struct freelist_head pool; + refcount_t ref; + struct rcu_head rcu; +}; + +/** + * struct rethook_node - The rethook shadow-stack entry node. + * @freelist: The freelist, linked to struct rethook::pool. + * @rcu: The rcu_head for deferred freeing. + * @llist: The llist, linked to a struct task_struct::rethooks. + * @rethook: The pointer to the struct rethook. + * @ret_addr: The storage for the real return address. + * @frame: The storage for the frame pointer. + * + * You can embed this to your extended data structure to store any data + * on each entry of the shadow stack. + */ +struct rethook_node { + union { + struct freelist_node freelist; + struct rcu_head rcu; + }; + struct llist_node llist; + struct rethook *rethook; + unsigned long ret_addr; + unsigned long frame; +}; + +struct rethook *rethook_alloc(void *data, rethook_handler_t handler); +void rethook_free(struct rethook *rh); +void rethook_add_node(struct rethook *rh, struct rethook_node *node); +struct rethook_node *rethook_try_get(struct rethook *rh); +void rethook_recycle(struct rethook_node *node); +void rethook_hook(struct rethook_node *node, struct pt_regs *regs, bool mcount); +unsigned long rethook_find_ret_addr(struct task_struct *tsk, unsigned long frame, + struct llist_node **cur); + +/* Arch dependent code must implement arch_* and trampoline code */ +void arch_rethook_prepare(struct rethook_node *node, struct pt_regs *regs, bool mcount); +void arch_rethook_trampoline(void); + +/** + * is_rethook_trampoline() - Check whether the address is rethook trampoline + * @addr: The address to be checked + * + * Return true if the @addr is the rethook trampoline address. + */ +static inline bool is_rethook_trampoline(unsigned long addr) +{ + return addr == (unsigned long)dereference_symbol_descriptor(arch_rethook_trampoline); +} + +/* If the architecture needs to fixup the return address, implement it. */ +void arch_rethook_fixup_return(struct pt_regs *regs, + unsigned long correct_ret_addr); + +/* Generic trampoline handler, arch code must prepare asm stub */ +unsigned long rethook_trampoline_handler(struct pt_regs *regs, + unsigned long frame); + +#ifdef CONFIG_RETHOOK +void rethook_flush_task(struct task_struct *tk); +#else +#define rethook_flush_task(tsk) do { } while (0) +#endif + +#endif + diff --git a/include/linux/sched.h b/include/linux/sched.h index 75ba8aa60248..7034f53404e3 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1481,6 +1481,9 @@ struct task_struct { #ifdef CONFIG_KRETPROBES struct llist_head kretprobe_instances; #endif +#ifdef CONFIG_RETHOOK + struct llist_head rethooks; +#endif #ifdef CONFIG_ARCH_HAS_PARANOID_L1D_FLUSH /* diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 26538ceb4b01..3a30cae8b0a5 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -992,10 +992,10 @@ struct sk_buff { __u8 csum_complete_sw:1; __u8 csum_level:2; __u8 dst_pending_confirm:1; - __u8 mono_delivery_time:1; + __u8 mono_delivery_time:1; /* See SKB_MONO_DELIVERY_TIME_MASK */ #ifdef CONFIG_NET_CLS_ACT __u8 tc_skip_classify:1; - __u8 tc_at_ingress:1; + __u8 tc_at_ingress:1; /* See TC_AT_INGRESS_MASK */ #endif #ifdef CONFIG_IPV6_NDISC_NODETYPE __u8 ndisc_nodetype:2; @@ -1094,7 +1094,9 @@ struct sk_buff { #endif #define PKT_TYPE_OFFSET offsetof(struct sk_buff, __pkt_type_offset) -/* if you move pkt_vlan_present around you also must adapt these constants */ +/* if you move pkt_vlan_present, tc_at_ingress, or mono_delivery_time + * around, you also must adapt these constants. + */ #ifdef __BIG_ENDIAN_BITFIELD #define PKT_VLAN_PRESENT_BIT 7 #define TC_AT_INGRESS_MASK (1 << 0) @@ -1105,8 +1107,6 @@ struct sk_buff { #define SKB_MONO_DELIVERY_TIME_MASK (1 << 5) #endif #define PKT_VLAN_PRESENT_OFFSET offsetof(struct sk_buff, __pkt_vlan_present_offset) -#define TC_AT_INGRESS_OFFSET offsetof(struct sk_buff, __pkt_vlan_present_offset) -#define SKB_MONO_DELIVERY_TIME_OFFSET offsetof(struct sk_buff, __pkt_vlan_present_offset) #ifdef __KERNEL__ /* diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index fdb5375f0562..c5a2d6f50f25 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -304,21 +304,16 @@ static inline void sock_drop(struct sock *sk, struct sk_buff *skb) kfree_skb(skb); } -static inline void drop_sk_msg(struct sk_psock *psock, struct sk_msg *msg) -{ - if (msg->skb) - sock_drop(psock->sk, msg->skb); - kfree(msg); -} - static inline void sk_psock_queue_msg(struct sk_psock *psock, struct sk_msg *msg) { spin_lock_bh(&psock->ingress_lock); if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) list_add_tail(&msg->list, &psock->ingress_msg); - else - drop_sk_msg(psock, msg); + else { + sk_msg_free(psock->sk, msg); + kfree(msg); + } spin_unlock_bh(&psock->ingress_lock); } diff --git a/include/linux/sort.h b/include/linux/sort.h index b5898725fe9d..e163287ac6c1 100644 --- a/include/linux/sort.h +++ b/include/linux/sort.h @@ -6,7 +6,7 @@ void sort_r(void *base, size_t num, size_t size, cmp_r_func_t cmp_func, - swap_func_t swap_func, + swap_r_func_t swap_func, const void *priv); void sort(void *base, size_t num, size_t size, diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index dcea51fb60e2..8f0e9e7cb493 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -15,6 +15,7 @@ struct array_buffer; struct tracer; struct dentry; struct bpf_prog; +union bpf_attr; const char *trace_print_flags_seq(struct trace_seq *p, const char *delim, unsigned long flags, @@ -738,6 +739,7 @@ void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp); int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, u32 *fd_type, const char **buf, u64 *probe_offset, u64 *probe_addr); +int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); #else static inline unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx) { @@ -779,6 +781,11 @@ static inline int bpf_get_perf_event_info(const struct perf_event *event, { return -EOPNOTSUPP; } +static inline int +bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + return -EOPNOTSUPP; +} #endif enum { diff --git a/include/linux/types.h b/include/linux/types.h index ac825ad90e44..ea8cf60a8a79 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -226,6 +226,7 @@ struct callback_head { typedef void (*rcu_callback_t)(struct rcu_head *head); typedef void (*call_rcu_func_t)(struct rcu_head *head, rcu_callback_t func); +typedef void (*swap_r_func_t)(void *a, void *b, int size, const void *priv); typedef void (*swap_func_t)(void *a, void *b, int size); typedef int (*cmp_r_func_t)(const void *a, const void *b, const void *priv); diff --git a/include/net/xdp.h b/include/net/xdp.h index b7721c3e4d1f..04c852c7a77f 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -343,6 +343,20 @@ out: __xdp_release_frame(xdpf->data, mem); } +static __always_inline unsigned int xdp_get_frame_len(struct xdp_frame *xdpf) +{ + struct skb_shared_info *sinfo; + unsigned int len = xdpf->len; + + if (likely(!xdp_frame_has_frags(xdpf))) + goto out; + + sinfo = xdp_get_shared_info_from_frame(xdpf); + len += sinfo->xdp_frags_size; +out: + return len; +} + 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); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 4eebea830613..d14b10b85e51 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -997,6 +997,7 @@ enum bpf_attach_type { BPF_SK_REUSEPORT_SELECT, BPF_SK_REUSEPORT_SELECT_OR_MIGRATE, BPF_PERF_EVENT, + BPF_TRACE_KPROBE_MULTI, __MAX_BPF_ATTACH_TYPE }; @@ -1011,6 +1012,7 @@ enum bpf_link_type { BPF_LINK_TYPE_NETNS = 5, BPF_LINK_TYPE_XDP = 6, BPF_LINK_TYPE_PERF_EVENT = 7, + BPF_LINK_TYPE_KPROBE_MULTI = 8, MAX_BPF_LINK_TYPE, }; @@ -1118,6 +1120,11 @@ enum bpf_link_type { */ #define BPF_F_XDP_HAS_FRAGS (1U << 5) +/* link_create.kprobe_multi.flags used in LINK_CREATE command for + * BPF_TRACE_KPROBE_MULTI attach type to create return probe. + */ +#define BPF_F_KPROBE_MULTI_RETURN (1U << 0) + /* When BPF ldimm64's insn[0].src_reg != 0 then this can have * the following extensions: * @@ -1232,6 +1239,8 @@ enum { /* If set, run the test on the cpu specified by bpf_attr.test.cpu */ #define BPF_F_TEST_RUN_ON_CPU (1U << 0) +/* If set, XDP frames will be transmitted after processing */ +#define BPF_F_TEST_XDP_LIVE_FRAMES (1U << 1) /* type for BPF_ENABLE_STATS */ enum bpf_stats_type { @@ -1393,6 +1402,7 @@ union bpf_attr { __aligned_u64 ctx_out; __u32 flags; __u32 cpu; + __u32 batch_size; } test; struct { /* anonymous struct used by BPF_*_GET_*_ID */ @@ -1472,6 +1482,13 @@ union bpf_attr { */ __u64 bpf_cookie; } perf_event; + struct { + __u32 flags; + __u32 cnt; + __aligned_u64 syms; + __aligned_u64 addrs; + __aligned_u64 cookies; + } kprobe_multi; }; } link_create; @@ -2299,8 +2316,8 @@ union bpf_attr { * Return * The return value depends on the result of the test, and can be: * - * * 0, if current task belongs to the cgroup2. - * * 1, if current task does not belong to the cgroup2. + * * 1, if current task belongs to the cgroup2. + * * 0, if current task does not belong to the cgroup2. * * A negative error code, if an error occurred. * * long bpf_skb_change_tail(struct sk_buff *skb, u32 len, u64 flags) @@ -2992,8 +3009,8 @@ union bpf_attr { * * # sysctl kernel.perf_event_max_stack=<new value> * Return - * A non-negative value equal to or less than *size* on success, - * or a negative error in case of failure. + * The non-negative copied *buf* length equal to or less than + * *size* on success, or a negative error in case of failure. * * long bpf_skb_load_bytes_relative(const void *skb, u32 offset, void *to, u32 len, u32 start_header) * Description @@ -4299,8 +4316,8 @@ union bpf_attr { * * # sysctl kernel.perf_event_max_stack=<new value> * Return - * A non-negative value equal to or less than *size* on success, - * or a negative error in case of failure. + * The non-negative copied *buf* length equal to or less than + * *size* on success, or a negative error in case of failure. * * long bpf_load_hdr_opt(struct bpf_sock_ops *skops, void *searchby_res, u32 len, u64 flags) * Description @@ -5087,23 +5104,22 @@ union bpf_attr { * 0 on success, or a negative error in case of failure. On error * *dst* buffer is zeroed out. * - * long bpf_skb_set_delivery_time(struct sk_buff *skb, u64 dtime, u32 dtime_type) + * long bpf_skb_set_tstamp(struct sk_buff *skb, u64 tstamp, u32 tstamp_type) * Description - * Set a *dtime* (delivery time) to the __sk_buff->tstamp and also - * change the __sk_buff->delivery_time_type to *dtime_type*. - * - * When setting a delivery time (non zero *dtime*) to - * __sk_buff->tstamp, only BPF_SKB_DELIVERY_TIME_MONO *dtime_type* - * is supported. It is the only delivery_time_type that will be - * kept after bpf_redirect_*(). + * Change the __sk_buff->tstamp_type to *tstamp_type* + * and set *tstamp* to the __sk_buff->tstamp together. * - * If there is no need to change the __sk_buff->delivery_time_type, - * the delivery time can be directly written to __sk_buff->tstamp + * If there is no need to change the __sk_buff->tstamp_type, + * the tstamp value can be directly written to __sk_buff->tstamp * instead. * - * *dtime* 0 and *dtime_type* BPF_SKB_DELIVERY_TIME_NONE - * can be used to clear any delivery time stored in - * __sk_buff->tstamp. + * BPF_SKB_TSTAMP_DELIVERY_MONO is the only tstamp that + * will be kept during bpf_redirect_*(). A non zero + * *tstamp* must be used with the BPF_SKB_TSTAMP_DELIVERY_MONO + * *tstamp_type*. + * + * A BPF_SKB_TSTAMP_UNSPEC *tstamp_type* can only be used + * with a zero *tstamp*. * * Only IPv4 and IPv6 skb->protocol are supported. * @@ -5116,7 +5132,17 @@ union bpf_attr { * Return * 0 on success. * **-EINVAL** for invalid input - * **-EOPNOTSUPP** for unsupported delivery_time_type and protocol + * **-EOPNOTSUPP** for unsupported protocol + * + * long bpf_ima_file_hash(struct file *file, void *dst, u32 size) + * Description + * Returns a calculated IMA hash of the *file*. + * If the hash is larger than *size*, then only *size* + * bytes will be copied to *dst* + * Return + * The **hash_algo** is returned on success, + * **-EOPNOTSUP** if the hash calculation failed or **-EINVAL** if + * invalid arguments are passed. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5311,7 +5337,8 @@ union bpf_attr { FN(xdp_load_bytes), \ FN(xdp_store_bytes), \ FN(copy_from_user_task), \ - FN(skb_set_delivery_time), \ + FN(skb_set_tstamp), \ + FN(ima_file_hash), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -5502,9 +5529,12 @@ union { \ } __attribute__((aligned(8))) enum { - BPF_SKB_DELIVERY_TIME_NONE, - BPF_SKB_DELIVERY_TIME_UNSPEC, - BPF_SKB_DELIVERY_TIME_MONO, + BPF_SKB_TSTAMP_UNSPEC, + BPF_SKB_TSTAMP_DELIVERY_MONO, /* tstamp has mono delivery time */ + /* For any BPF_SKB_TSTAMP_* that the bpf prog cannot handle, + * the bpf prog should handle it like BPF_SKB_TSTAMP_UNSPEC + * and try to deduce it by ingress, egress or skb->sk->sk_clockid. + */ }; /* user accessible mirror of in-kernel sk_buff. @@ -5547,7 +5577,7 @@ struct __sk_buff { __u32 gso_segs; __bpf_md_ptr(struct bpf_sock *, sk); __u32 gso_size; - __u8 delivery_time_type; + __u8 tstamp_type; __u32 :24; /* Padding, future use. */ __u64 hwtstamp; }; |