Something went wrong. Try again.
(I'm so sorry!) Linux kernel mirror (for testing) git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
Something went wrong. Try again.
C
12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130113111321133113411351136113711381139114011411142114311441145114611471148114911501151115211531154115511561157115811591160116111621163116411651166116711681169117011711172117311741175117611771178117911801181118211831184118511861187118811891190119111921193119411951196119711981199120012011202120312041205120612071208120912101211121212131214121512161217121812191220122112221223122412251226122712281229123012311232123312341235123612371238123912401241124212431244124512461247124812491250125112521253125412551256125712581259126012611262126312641265126612671268126912701271127212731274127512761277127812791280128112821283128412851286128712881289129012911292129312941295129612971298129913001301130213031304130513061307130813091310131113121313131413151316131713181319132013211322132313241325132613271328132913301331133213331334133513361337133813391340134113421343134413451346134713481349135013511352135313541355135613571358135913601361136213631364136513661367136813691370137113721373137413751376137713781379138013811382138313841385138613871388138913901391139213931394139513961397139813991400140114021403140414051406140714081409141014111412141314141415141614171418141914201421142214231424142514261427142814291430143114321433143414351436143714381439144014411442144314441445144614471448144914501451145214531454145514561457145814591460146114621463146414651466146714681469147014711472147314741475147614771478147914801481148214831484148514861487148814891490149114921493149414951496149714981499150015011502150315041505150615071508150915101511151215131514151515161517151815191520152115221523152415251526152715281529153015311532153315341535153615371538153915401541154215431544154515461547154815491550155115521553155415551556155715581559156015611562156315641565156615671568156915701571157215731574157515761577157815791580158115821583158415851586158715881589159015911592159315941595159615971598159916001601160216031604160516061607160816091610161116121613161416151616161716181619162016211622162316241625162616271628162916301631163216331634163516361637163816391640164116421643164416451646164716481649165016511652165316541655165616571658165916601661166216631664166516661667166816691670167116721673167416751676167716781679168016811682168316841685168616871688168916901691169216931694169516961697169816991700170117021703170417051706170717081709171017111712171317141715171617171718171917201721172217231724172517261727172817291730173117321733173417351736173717381739174017411742174317441745174617471748174917501751175217531754175517561757175817591760176117621763176417651766176717681769177017711772177317741775177617771778177917801781178217831784178517861787178817891790179117921793179417951796179717981799180018011802180318041805180618071808180918101811181218131814181518161817181818191820182118221823182418251826182718281829183018311832183318341835183618371838183918401841184218431844184518461847184818491850185118521853185418551856185718581859186018611862186318641865186618671868186918701871187218731874187518761877187818791880188118821883188418851886188718881889189018911892189318941895189618971898189919001901190219031904190519061907190819091910191119121913191419151916191719181919192019211922192319241925192619271928192919301931193219331934193519361937193819391940194119421943194419451946194719481949195019511952195319541955195619571958195919601961/* SPDX-License-Identifier: GPL-2.0 *//* * Linux Socket Filter Data Structures */#ifndef __LINUX_FILTER_H__#define __LINUX_FILTER_H__
#include <linux/atomic.h>#include <linux/bpf.h>#include <linux/refcount.h>#include <linux/compat.h>#include <linux/skbuff.h>#include <linux/linkage.h>#include <linux/printk.h>#include <linux/workqueue.h>#include <linux/sched.h>#include <linux/sched/clock.h>#include <linux/capability.h>#include <linux/set_memory.h>#include <linux/kallsyms.h>#include <linux/if_vlan.h>#include <linux/vmalloc.h>#include <linux/sockptr.h>#include <linux/static_call.h>#include <linux/u64_stats_sync.h>
#include <net/sch_generic.h>
#include <asm/byteorder.h>#include <uapi/linux/filter.h>
struct sk_buff;struct sock;struct seccomp_data;struct bpf_prog_aux;struct xdp_rxq_info;struct xdp_buff;struct sock_reuseport;struct ctl_table;struct ctl_table_header;
/* ArgX, context and stack frame pointer register positions. Note, * Arg1, Arg2, Arg3, etc are used as argument mappings of function * calls in BPF_CALL instruction. */#define BPF_REG_ARG1 BPF_REG_1#define BPF_REG_ARG2 BPF_REG_2#define BPF_REG_ARG3 BPF_REG_3#define BPF_REG_ARG4 BPF_REG_4#define BPF_REG_ARG5 BPF_REG_5#define BPF_REG_CTX BPF_REG_6#define BPF_REG_FP BPF_REG_10
/* Additional register mappings for converted user programs. */#define BPF_REG_A BPF_REG_0#define BPF_REG_X BPF_REG_7#define BPF_REG_TMP BPF_REG_2 /* scratch reg */#define BPF_REG_D BPF_REG_8 /* data, callee-saved */#define BPF_REG_H BPF_REG_9 /* hlen, callee-saved */
/* Kernel hidden auxiliary/helper register. */#define BPF_REG_PARAMS MAX_BPF_REG#define BPF_REG_AX (MAX_BPF_REG + 1)#define MAX_BPF_EXT_REG (MAX_BPF_REG + 2)#define MAX_BPF_JIT_REG MAX_BPF_EXT_REG
/* unused opcode to mark special call to bpf_tail_call() helper */#define BPF_TAIL_CALL 0xf0
/* unused opcode to mark special load instruction. Same as BPF_ABS */#define BPF_PROBE_MEM 0x20
/* unused opcode to mark special ldsx instruction. Same as BPF_IND */#define BPF_PROBE_MEMSX 0x40
/* unused opcode to mark special load instruction. Same as BPF_MSH */#define BPF_PROBE_MEM32 0xa0
/* unused opcode to mark special atomic instruction */#define BPF_PROBE_ATOMIC 0xe0
/* unused opcode to mark special ldsx instruction. Same as BPF_NOSPEC */#define BPF_PROBE_MEM32SX 0xc0
/* unused opcode to mark call to interpreter with arguments */#define BPF_CALL_ARGS 0xe0
/* unused opcode to mark speculation barrier for mitigating * Spectre v1 and v4 */#define BPF_NOSPEC 0xc0
/* As per nm, we expose JITed images as text (code) section for * kallsyms. That way, tools like perf can find it to match * addresses. */#define BPF_SYM_ELF_TYPE 't'
/* BPF program can access up to 512 bytes of stack space. */#define MAX_BPF_STACK 512
/* Helper macros for filter block array initializers. */
/* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */
#define BPF_ALU64_REG_OFF(OP, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_OP(OP) | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 })
#define BPF_ALU64_REG(OP, DST, SRC) \ BPF_ALU64_REG_OFF(OP, DST, SRC, 0)
#define BPF_ALU32_REG_OFF(OP, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_OP(OP) | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 })
#define BPF_ALU32_REG(OP, DST, SRC) \ BPF_ALU32_REG_OFF(OP, DST, SRC, 0)
/* ALU ops on immediates, bpf_add|sub|...: dst_reg += imm32 */
#define BPF_ALU64_IMM_OFF(OP, DST, IMM, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_OP(OP) | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = OFF, \ .imm = IMM })#define BPF_ALU64_IMM(OP, DST, IMM) \ BPF_ALU64_IMM_OFF(OP, DST, IMM, 0)
#define BPF_ALU32_IMM_OFF(OP, DST, IMM, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_OP(OP) | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = OFF, \ .imm = IMM })#define BPF_ALU32_IMM(OP, DST, IMM) \ BPF_ALU32_IMM_OFF(OP, DST, IMM, 0)
/* Endianess conversion, cpu_to_{l,b}e(), {l,b}e_to_cpu() */
#define BPF_ENDIAN(TYPE, DST, LEN) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_END | BPF_SRC(TYPE), \ .dst_reg = DST, \ .src_reg = 0, \ .off = 0, \ .imm = LEN })
/* Byte Swap, bswap16/32/64 */
#define BPF_BSWAP(DST, LEN) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_END | BPF_SRC(BPF_TO_LE), \ .dst_reg = DST, \ .src_reg = 0, \ .off = 0, \ .imm = LEN })
/* Short form of mov, dst_reg = src_reg */
#define BPF_MOV64_REG(DST, SRC) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_MOV | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = 0 })
#define BPF_MOV32_REG(DST, SRC) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_MOV | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = 0 })
/* Special (internal-only) form of mov, used to resolve per-CPU addrs: * dst_reg = src_reg + <percpu_base_off> * BPF_ADDR_PERCPU is used as a special insn->off value. */#define BPF_ADDR_PERCPU (-1)
#define BPF_MOV64_PERCPU_REG(DST, SRC) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_MOV | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = BPF_ADDR_PERCPU, \ .imm = 0 })
static inline bool insn_is_mov_percpu_addr(const struct bpf_insn *insn){ return insn->code == (BPF_ALU64 | BPF_MOV | BPF_X) && insn->off == BPF_ADDR_PERCPU;}
/* Short form of mov, dst_reg = imm32 */
#define BPF_MOV64_IMM(DST, IMM) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_MOV | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = 0, \ .imm = IMM })
#define BPF_MOV32_IMM(DST, IMM) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_MOV | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = 0, \ .imm = IMM })
/* Short form of movsx, dst_reg = (s8,s16,s32)src_reg */
#define BPF_MOVSX64_REG(DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_MOV | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 })
#define BPF_MOVSX32_REG(DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_MOV | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 })
/* Special form of mov32, used for doing explicit zero extension on dst. */#define BPF_ZEXT_REG(DST) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_MOV | BPF_X, \ .dst_reg = DST, \ .src_reg = DST, \ .off = 0, \ .imm = 1 })
static inline bool insn_is_zext(const struct bpf_insn *insn){ return insn->code == (BPF_ALU | BPF_MOV | BPF_X) && insn->imm == 1;}
/* addr_space_cast from as(0) to as(1) is for converting bpf arena pointers * to pointers in user vma. */static inline bool insn_is_cast_user(const struct bpf_insn *insn){ return insn->code == (BPF_ALU64 | BPF_MOV | BPF_X) && insn->off == BPF_ADDR_SPACE_CAST && insn->imm == 1U << 16;}
/* BPF_LD_IMM64 macro encodes single 'load 64-bit immediate' insn */#define BPF_LD_IMM64(DST, IMM) \ BPF_LD_IMM64_RAW(DST, 0, IMM)
#define BPF_LD_IMM64_RAW(DST, SRC, IMM) \ ((struct bpf_insn) { \ .code = BPF_LD | BPF_DW | BPF_IMM, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = (__u32) (IMM) }), \ ((struct bpf_insn) { \ .code = 0, /* zero is reserved opcode */ \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = ((__u64) (IMM)) >> 32 })
/* pseudo BPF_LD_IMM64 insn used to refer to process-local map_fd */#define BPF_LD_MAP_FD(DST, MAP_FD) \ BPF_LD_IMM64_RAW(DST, BPF_PSEUDO_MAP_FD, MAP_FD)
/* Short form of mov based on type, BPF_X: dst_reg = src_reg, BPF_K: dst_reg = imm32 */
#define BPF_MOV64_RAW(TYPE, DST, SRC, IMM) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_MOV | BPF_SRC(TYPE), \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = IMM })
#define BPF_MOV32_RAW(TYPE, DST, SRC, IMM) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_MOV | BPF_SRC(TYPE), \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = IMM })
/* Direct packet access, R0 = *(uint *) (skb->data + imm32) */
#define BPF_LD_ABS(SIZE, IMM) \ ((struct bpf_insn) { \ .code = BPF_LD | BPF_SIZE(SIZE) | BPF_ABS, \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = IMM })
/* Indirect packet access, R0 = *(uint *) (skb->data + src_reg + imm32) */
#define BPF_LD_IND(SIZE, SRC, IMM) \ ((struct bpf_insn) { \ .code = BPF_LD | BPF_SIZE(SIZE) | BPF_IND, \ .dst_reg = 0, \ .src_reg = SRC, \ .off = 0, \ .imm = IMM })
/* Memory load, dst_reg = *(uint *) (src_reg + off16) */
#define BPF_LDX_MEM(SIZE, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_LDX | BPF_SIZE(SIZE) | BPF_MEM, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 })
/* Memory load, dst_reg = *(signed size *) (src_reg + off16) */
#define BPF_LDX_MEMSX(SIZE, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_LDX | BPF_SIZE(SIZE) | BPF_MEMSX, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 })
/* Memory store, *(uint *) (dst_reg + off16) = src_reg */
#define BPF_STX_MEM(SIZE, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_STX | BPF_SIZE(SIZE) | BPF_MEM, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 })
/* * Atomic operations: * * BPF_ADD *(uint *) (dst_reg + off16) += src_reg * BPF_AND *(uint *) (dst_reg + off16) &= src_reg * BPF_OR *(uint *) (dst_reg + off16) |= src_reg * BPF_XOR *(uint *) (dst_reg + off16) ^= src_reg * BPF_ADD | BPF_FETCH src_reg = atomic_fetch_add(dst_reg + off16, src_reg); * BPF_AND | BPF_FETCH src_reg = atomic_fetch_and(dst_reg + off16, src_reg); * BPF_OR | BPF_FETCH src_reg = atomic_fetch_or(dst_reg + off16, src_reg); * BPF_XOR | BPF_FETCH src_reg = atomic_fetch_xor(dst_reg + off16, src_reg); * BPF_XCHG src_reg = atomic_xchg(dst_reg + off16, src_reg) * BPF_CMPXCHG r0 = atomic_cmpxchg(dst_reg + off16, r0, src_reg) * BPF_LOAD_ACQ dst_reg = smp_load_acquire(src_reg + off16) * BPF_STORE_REL smp_store_release(dst_reg + off16, src_reg) */
#define BPF_ATOMIC_OP(SIZE, OP, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_STX | BPF_SIZE(SIZE) | BPF_ATOMIC, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = OP })
/* Legacy alias */#define BPF_STX_XADD(SIZE, DST, SRC, OFF) BPF_ATOMIC_OP(SIZE, BPF_ADD, DST, SRC, OFF)
/* * Given a BPF_ATOMIC instruction @atomic_insn, return true if it is an * atomic load or store, and false if it is a read-modify-write instruction. */static inline boolbpf_atomic_is_load_store(const struct bpf_insn *atomic_insn){ switch (atomic_insn->imm) { case BPF_LOAD_ACQ: case BPF_STORE_REL: return true; default: return false; }}
/* * A load-acquire is the only BPF_STX class instruction that reads into * dst_reg from src_reg + off16, i.e. it has the operand roles of a BPF_LDX. * Unlike bpf_atomic_is_load_store(), @insn is not assumed to be a BPF_ATOMIC * instruction here, so that callers which walk all instruction classes can * use this directly. */static inline bool bpf_atomic_is_load_acq(const struct bpf_insn *insn){ return BPF_CLASS(insn->code) == BPF_STX && (BPF_MODE(insn->code) == BPF_ATOMIC || BPF_MODE(insn->code) == BPF_PROBE_ATOMIC) && insn->imm == BPF_LOAD_ACQ;}
/* * Given an instruction @insn, return the number of the BPF register that a * BPF_ATOMIC reads the value at its memory operand into, or -1 if there is * no such register. That is the register a BPF_PROBE_ATOMIC has to clear when * the access faults. Like bpf_atomic_is_load_acq(), @insn is not assumed to * be a BPF_ATOMIC here. */static inline int bpf_atomic_load_reg(const struct bpf_insn *insn){ if (BPF_CLASS(insn->code) != BPF_STX || (BPF_MODE(insn->code) != BPF_ATOMIC && BPF_MODE(insn->code) != BPF_PROBE_ATOMIC)) return -1;
switch (insn->imm) { case BPF_LOAD_ACQ: return insn->dst_reg; case BPF_CMPXCHG: return BPF_REG_0; default: return (insn->imm & BPF_FETCH) ? insn->src_reg : -1; }}
/* Memory store, *(uint *) (dst_reg + off16) = imm32 */
#define BPF_ST_MEM(SIZE, DST, OFF, IMM) \ ((struct bpf_insn) { \ .code = BPF_ST | BPF_SIZE(SIZE) | BPF_MEM, \ .dst_reg = DST, \ .src_reg = 0, \ .off = OFF, \ .imm = IMM })
/* Conditional jumps against registers, if (dst_reg 'op' src_reg) goto pc + off16 */
#define BPF_JMP_REG(OP, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_OP(OP) | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 })
/* Conditional jumps against immediates, if (dst_reg 'op' imm32) goto pc + off16 */
#define BPF_JMP_IMM(OP, DST, IMM, OFF) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_OP(OP) | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = OFF, \ .imm = IMM })
/* Like BPF_JMP_REG, but with 32-bit wide operands for comparison. */
#define BPF_JMP32_REG(OP, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_JMP32 | BPF_OP(OP) | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 })
/* Like BPF_JMP_IMM, but with 32-bit wide operands for comparison. */
#define BPF_JMP32_IMM(OP, DST, IMM, OFF) \ ((struct bpf_insn) { \ .code = BPF_JMP32 | BPF_OP(OP) | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = OFF, \ .imm = IMM })
/* Unconditional jumps, goto pc + off16 */
#define BPF_JMP_A(OFF) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_JA, \ .dst_reg = 0, \ .src_reg = 0, \ .off = OFF, \ .imm = 0 })
/* Unconditional jumps, gotol pc + imm32 */
#define BPF_JMP32_A(IMM) \ ((struct bpf_insn) { \ .code = BPF_JMP32 | BPF_JA, \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = IMM })
/* Relative call */
#define BPF_CALL_REL(TGT) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_CALL, \ .dst_reg = 0, \ .src_reg = BPF_PSEUDO_CALL, \ .off = 0, \ .imm = TGT })
/* Convert function address to BPF immediate */
#define BPF_CALL_IMM(x) ((void *)(x) - (void *)__bpf_call_base)
#define BPF_EMIT_CALL(FUNC) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_CALL, \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = BPF_CALL_IMM(FUNC) })
/* Kfunc call */
#define BPF_CALL_KFUNC(OFF, IMM) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_CALL, \ .dst_reg = 0, \ .src_reg = BPF_PSEUDO_KFUNC_CALL, \ .off = OFF, \ .imm = IMM })
/* Raw code statement block */
#define BPF_RAW_INSN(CODE, DST, SRC, OFF, IMM) \ ((struct bpf_insn) { \ .code = CODE, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = IMM })
/* Program exit */
#define BPF_EXIT_INSN() \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_EXIT, \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = 0 })
/* Speculation barrier */
#define BPF_ST_NOSPEC() \ ((struct bpf_insn) { \ .code = BPF_ST | BPF_NOSPEC, \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = 0 })
/* Internal classic blocks for direct assignment */
#define __BPF_STMT(CODE, K) \ ((struct sock_filter) BPF_STMT(CODE, K))
#define __BPF_JUMP(CODE, K, JT, JF) \ ((struct sock_filter) BPF_JUMP(CODE, K, JT, JF))
#define bytes_to_bpf_size(bytes) \({ \ int bpf_size = -EINVAL; \ \ if (bytes == sizeof(u8)) \ bpf_size = BPF_B; \ else if (bytes == sizeof(u16)) \ bpf_size = BPF_H; \ else if (bytes == sizeof(u32)) \ bpf_size = BPF_W; \ else if (bytes == sizeof(u64)) \ bpf_size = BPF_DW; \ \ bpf_size; \})
#define bpf_size_to_bytes(bpf_size) \({ \ int bytes = -EINVAL; \ \ if (bpf_size == BPF_B) \ bytes = sizeof(u8); \ else if (bpf_size == BPF_H) \ bytes = sizeof(u16); \ else if (bpf_size == BPF_W) \ bytes = sizeof(u32); \ else if (bpf_size == BPF_DW) \ bytes = sizeof(u64); \ \ bytes; \})
#define BPF_SIZEOF(type) \ ({ \ const int __size = bytes_to_bpf_size(sizeof(type)); \ BUILD_BUG_ON(__size < 0); \ __size; \ })
#define BPF_FIELD_SIZEOF(type, field) \ ({ \ const int __size = bytes_to_bpf_size(sizeof_field(type, field)); \ BUILD_BUG_ON(__size < 0); \ __size; \ })
#define BPF_LDST_BYTES(insn) \ ({ \ const int __size = bpf_size_to_bytes(BPF_SIZE((insn)->code)); \ WARN_ON(__size < 0); \ __size; \ })
#define __BPF_MAP_0(m, v, ...) v#define __BPF_MAP_1(m, v, t, a, ...) m(t, a)#define __BPF_MAP_2(m, v, t, a, ...) m(t, a), __BPF_MAP_1(m, v, __VA_ARGS__)#define __BPF_MAP_3(m, v, t, a, ...) m(t, a), __BPF_MAP_2(m, v, __VA_ARGS__)#define __BPF_MAP_4(m, v, t, a, ...) m(t, a), __BPF_MAP_3(m, v, __VA_ARGS__)#define __BPF_MAP_5(m, v, t, a, ...) m(t, a), __BPF_MAP_4(m, v, __VA_ARGS__)
#define __BPF_REG_0(...) __BPF_PAD(5)#define __BPF_REG_1(...) __BPF_MAP(1, __VA_ARGS__), __BPF_PAD(4)#define __BPF_REG_2(...) __BPF_MAP(2, __VA_ARGS__), __BPF_PAD(3)#define __BPF_REG_3(...) __BPF_MAP(3, __VA_ARGS__), __BPF_PAD(2)#define __BPF_REG_4(...) __BPF_MAP(4, __VA_ARGS__), __BPF_PAD(1)#define __BPF_REG_5(...) __BPF_MAP(5, __VA_ARGS__)
#define __BPF_MAP(n, ...) __BPF_MAP_##n(__VA_ARGS__)#define __BPF_REG(n, ...) __BPF_REG_##n(__VA_ARGS__)
#define __BPF_CAST(t, a) \ (__force t) \ (__force \ typeof(__builtin_choose_expr(sizeof(t) == sizeof(unsigned long), \ (unsigned long)0, (t)0))) a#define __BPF_V void#define __BPF_N
#define __BPF_DECL_ARGS(t, a) t a#define __BPF_DECL_REGS(t, a) u64 a
#define __BPF_PAD(n) \ __BPF_MAP(n, __BPF_DECL_ARGS, __BPF_N, u64, __ur_1, u64, __ur_2, \ u64, __ur_3, u64, __ur_4, u64, __ur_5)
#define BPF_CALL_x(x, attr, name, ...) \ static __always_inline \ u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \ typedef u64 (*btf_##name)(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \ attr u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)); \ attr u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)) \ { \ return ((btf_##name)____##name)(__BPF_MAP(x,__BPF_CAST,__BPF_N,__VA_ARGS__));\ } \ static __always_inline \ u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__))
#define __NOATTR#define BPF_CALL_0(name, ...) BPF_CALL_x(0, __NOATTR, name, __VA_ARGS__)#define BPF_CALL_1(name, ...) BPF_CALL_x(1, __NOATTR, name, __VA_ARGS__)#define BPF_CALL_2(name, ...) BPF_CALL_x(2, __NOATTR, name, __VA_ARGS__)#define BPF_CALL_3(name, ...) BPF_CALL_x(3, __NOATTR, name, __VA_ARGS__)#define BPF_CALL_4(name, ...) BPF_CALL_x(4, __NOATTR, name, __VA_ARGS__)#define BPF_CALL_5(name, ...) BPF_CALL_x(5, __NOATTR, name, __VA_ARGS__)
#define NOTRACE_BPF_CALL_1(name, ...) BPF_CALL_x(1, notrace, name, __VA_ARGS__)
#define bpf_ctx_range(TYPE, MEMBER) \ offsetof(TYPE, MEMBER) ... offsetofend(TYPE, MEMBER) - 1#define bpf_ctx_range_till(TYPE, MEMBER1, MEMBER2) \ offsetof(TYPE, MEMBER1) ... offsetofend(TYPE, MEMBER2) - 1#if BITS_PER_LONG == 64# define bpf_ctx_range_ptr(TYPE, MEMBER) \ offsetof(TYPE, MEMBER) ... offsetofend(TYPE, MEMBER) - 1#else# define bpf_ctx_range_ptr(TYPE, MEMBER) \ offsetof(TYPE, MEMBER) ... offsetof(TYPE, MEMBER) + 8 - 1#endif /* BITS_PER_LONG == 64 */
#define bpf_target_off(TYPE, MEMBER, SIZE, PTR_SIZE) \ ({ \ BUILD_BUG_ON(sizeof_field(TYPE, MEMBER) != (SIZE)); \ *(PTR_SIZE) = (SIZE); \ offsetof(TYPE, MEMBER); \ })
/* A struct sock_filter is architecture independent. */struct compat_sock_fprog { u16 len; compat_uptr_t filter; /* struct sock_filter * */};
struct sock_fprog_kern { u16 len; struct sock_filter *filter;};
/* Some arches need doubleword alignment for their instructions and/or data */#define BPF_IMAGE_ALIGNMENT 8
struct bpf_binary_header { u32 size; u8 image[] __aligned(BPF_IMAGE_ALIGNMENT);};
struct bpf_prog_stats { u64_stats_t cnt; u64_stats_t nsecs; u64_stats_t misses; struct u64_stats_sync syncp;} __aligned(2 * sizeof(u64));
struct bpf_timed_may_goto { u64 count; u64 timestamp;};
struct sk_filter { refcount_t refcnt; struct rcu_head rcu; struct bpf_prog *prog;};
DECLARE_STATIC_KEY_FALSE(bpf_stats_enabled_key);
extern struct mutex nf_conn_btf_access_lock;extern int (*nfct_btf_struct_access)(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size);
typedef unsigned int (*bpf_dispatcher_fn)(const void *ctx, const struct bpf_insn *insnsi, unsigned int (*bpf_func)(const void *, const struct bpf_insn *));
static __always_inline u32 __bpf_prog_run(const struct bpf_prog *prog, const void *ctx, bpf_dispatcher_fn dfunc){ u32 ret;
cant_migrate(); if (static_branch_unlikely(&bpf_stats_enabled_key)) { struct bpf_prog_stats *stats; u64 duration, start = sched_clock(); unsigned long flags;
ret = dfunc(ctx, prog->insnsi, prog->bpf_func);
duration = sched_clock() - start; if (likely(prog->stats)) { stats = this_cpu_ptr(prog->stats); flags = u64_stats_update_begin_irqsave(&stats->syncp); u64_stats_inc(&stats->cnt); u64_stats_add(&stats->nsecs, duration); u64_stats_update_end_irqrestore(&stats->syncp, flags); } } else { ret = dfunc(ctx, prog->insnsi, prog->bpf_func); } return ret;}
static __always_inline u32 bpf_prog_run(const struct bpf_prog *prog, const void *ctx){ return __bpf_prog_run(prog, ctx, bpf_dispatcher_nop_func);}
/* * Use in preemptible and therefore migratable context to make sure that * the execution of the BPF program runs on one CPU. * * This uses migrate_disable/enable() explicitly to document that the * invocation of a BPF program does not require reentrancy protection * against a BPF program which is invoked from a preempting task. */static inline u32 bpf_prog_run_pin_on_cpu(const struct bpf_prog *prog, const void *ctx){ u32 ret;
migrate_disable(); ret = bpf_prog_run(prog, ctx); migrate_enable(); return ret;}
static inline bool is_stack_arg_ldx(const struct bpf_insn *insn){ return insn->code == (BPF_LDX | BPF_MEM | BPF_DW) && insn->src_reg == BPF_REG_PARAMS && insn->off > 0 && insn->off % 8 == 0;}
static inline bool is_stack_arg_st(const struct bpf_insn *insn){ return insn->code == (BPF_ST | BPF_MEM | BPF_DW) && insn->dst_reg == BPF_REG_PARAMS && insn->off < 0 && insn->off % 8 == 0;}
static inline bool is_stack_arg_stx(const struct bpf_insn *insn){ return insn->code == (BPF_STX | BPF_MEM | BPF_DW) && insn->dst_reg == BPF_REG_PARAMS && insn->off < 0 && insn->off % 8 == 0;}
#define BPF_SKB_CB_LEN QDISC_CB_PRIV_LEN
struct bpf_skb_data_end { struct qdisc_skb_cb qdisc_cb; void *data_meta; void *data_end;};
struct bpf_nh_params { u32 nh_family; union { u32 ipv4_nh; struct in6_addr ipv6_nh; };};
/* flags for bpf_redirect_info kern_flags */#define BPF_RI_F_RF_NO_DIRECT BIT(0) /* no napi_direct on return_frame */#define BPF_RI_F_RI_INIT BIT(1)#define BPF_RI_F_CPU_MAP_INIT BIT(2)#define BPF_RI_F_DEV_MAP_INIT BIT(3)#define BPF_RI_F_XSK_MAP_INIT BIT(4)
struct bpf_redirect_info { u64 tgt_index; void *tgt_value; struct bpf_map *map; u32 flags; u32 map_id; enum bpf_map_type map_type; struct bpf_nh_params nh; u32 kern_flags;};
struct bpf_net_context { struct bpf_redirect_info ri; struct list_head cpu_map_flush_list; struct list_head dev_map_flush_list; struct list_head xskmap_map_flush_list;};
static inline struct bpf_net_context *bpf_net_ctx_set(struct bpf_net_context *bpf_net_ctx){ struct task_struct *tsk = current;
if (tsk->bpf_net_context != NULL) return NULL; bpf_net_ctx->ri.kern_flags = 0;
tsk->bpf_net_context = bpf_net_ctx; return bpf_net_ctx;}
static inline void bpf_net_ctx_clear(struct bpf_net_context *bpf_net_ctx){ if (bpf_net_ctx) current->bpf_net_context = NULL;}
static inline struct bpf_net_context *bpf_net_ctx_get(void){ return current->bpf_net_context;}
static inline struct bpf_redirect_info *bpf_net_ctx_get_ri(void){ struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get();
if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_RI_INIT)) { memset(&bpf_net_ctx->ri, 0, offsetof(struct bpf_net_context, ri.nh)); bpf_net_ctx->ri.kern_flags |= BPF_RI_F_RI_INIT; }
return &bpf_net_ctx->ri;}
static inline struct list_head *bpf_net_ctx_get_cpu_map_flush_list(void){ struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get();
if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_CPU_MAP_INIT)) { INIT_LIST_HEAD(&bpf_net_ctx->cpu_map_flush_list); bpf_net_ctx->ri.kern_flags |= BPF_RI_F_CPU_MAP_INIT; }
return &bpf_net_ctx->cpu_map_flush_list;}
static inline struct list_head *bpf_net_ctx_get_dev_flush_list(void){ struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get();
if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_DEV_MAP_INIT)) { INIT_LIST_HEAD(&bpf_net_ctx->dev_map_flush_list); bpf_net_ctx->ri.kern_flags |= BPF_RI_F_DEV_MAP_INIT; }
return &bpf_net_ctx->dev_map_flush_list;}
static inline struct list_head *bpf_net_ctx_get_xskmap_flush_list(void){ struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get();
if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_XSK_MAP_INIT)) { INIT_LIST_HEAD(&bpf_net_ctx->xskmap_map_flush_list); bpf_net_ctx->ri.kern_flags |= BPF_RI_F_XSK_MAP_INIT; }
return &bpf_net_ctx->xskmap_map_flush_list;}
static inline void bpf_net_ctx_get_all_used_flush_lists(struct list_head **lh_map, struct list_head **lh_dev, struct list_head **lh_xsk){ struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get(); u32 kern_flags = bpf_net_ctx->ri.kern_flags; struct list_head *lh;
*lh_map = *lh_dev = *lh_xsk = NULL;
if (!IS_ENABLED(CONFIG_BPF_SYSCALL)) return;
lh = &bpf_net_ctx->dev_map_flush_list; if (kern_flags & BPF_RI_F_DEV_MAP_INIT && !list_empty(lh)) *lh_dev = lh;
lh = &bpf_net_ctx->cpu_map_flush_list; if (kern_flags & BPF_RI_F_CPU_MAP_INIT && !list_empty(lh)) *lh_map = lh;
lh = &bpf_net_ctx->xskmap_map_flush_list; if (IS_ENABLED(CONFIG_XDP_SOCKETS) && kern_flags & BPF_RI_F_XSK_MAP_INIT && !list_empty(lh)) *lh_xsk = lh;}
/* Compute the linear packet data range [data, data_end) which * will be accessed by various program types (cls_bpf, act_bpf, * lwt, ...). Subsystems allowing direct data access must (!) * ensure that cb[] area can be written to when BPF program is * invoked (otherwise cb[] save/restore is necessary). */static inline void bpf_compute_data_pointers(struct sk_buff *skb){ struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb;
BUILD_BUG_ON(sizeof(*cb) > sizeof_field(struct sk_buff, cb)); cb->data_meta = skb->data - skb_metadata_len(skb); cb->data_end = skb->data + skb_headlen(skb);}
static inline int bpf_prog_run_data_pointers( const struct bpf_prog *prog, struct sk_buff *skb){ struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb; void *save_data_meta, *save_data_end; int res;
save_data_meta = cb->data_meta; save_data_end = cb->data_end;
bpf_compute_data_pointers(skb); res = bpf_prog_run(prog, skb);
cb->data_meta = save_data_meta; cb->data_end = save_data_end;
return res;}
/* Similar to bpf_compute_data_pointers(), except that save orginal * data in cb->data and cb->meta_data for restore. */static inline void bpf_compute_and_save_data_end( struct sk_buff *skb, void **saved_data_end){ struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb;
*saved_data_end = cb->data_end; cb->data_end = skb->data + skb_headlen(skb);}
/* Restore data saved by bpf_compute_and_save_data_end(). */static inline void bpf_restore_data_end( struct sk_buff *skb, void *saved_data_end){ struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb;
cb->data_end = saved_data_end;}
static inline u8 *bpf_skb_cb(const struct sk_buff *skb){ /* eBPF programs may read/write skb->cb[] area to transfer meta * data between tail calls. Since this also needs to work with * tc, that scratch memory is mapped to qdisc_skb_cb's data area. * * In some socket filter cases, the cb unfortunately needs to be * saved/restored so that protocol specific skb->cb[] data won't * be lost. In any case, due to unpriviledged eBPF programs * attached to sockets, we need to clear the bpf_skb_cb() area * to not leak previous contents to user space. */ BUILD_BUG_ON(sizeof_field(struct __sk_buff, cb) != BPF_SKB_CB_LEN); BUILD_BUG_ON(sizeof_field(struct __sk_buff, cb) != sizeof_field(struct qdisc_skb_cb, data));
return qdisc_skb_cb(skb)->data;}
/* Must be invoked with migration disabled */static inline u32 __bpf_prog_run_save_cb(const struct bpf_prog *prog, const void *ctx){ const struct sk_buff *skb = ctx; u8 *cb_data = bpf_skb_cb(skb); u8 cb_saved[BPF_SKB_CB_LEN]; u32 res;
if (unlikely(prog->cb_access)) { memcpy(cb_saved, cb_data, sizeof(cb_saved)); memset(cb_data, 0, sizeof(cb_saved)); }
res = bpf_prog_run(prog, skb);
if (unlikely(prog->cb_access)) memcpy(cb_data, cb_saved, sizeof(cb_saved));
return res;}
static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog, struct sk_buff *skb){ u32 res;
migrate_disable(); res = __bpf_prog_run_save_cb(prog, skb); migrate_enable(); return res;}
static inline u32 bpf_prog_run_clear_cb(const struct bpf_prog *prog, struct sk_buff *skb){ u8 *cb_data = bpf_skb_cb(skb); u32 res;
if (unlikely(prog->cb_access)) memset(cb_data, 0, BPF_SKB_CB_LEN);
res = bpf_prog_run_pin_on_cpu(prog, skb); return res;}
DECLARE_BPF_DISPATCHER(xdp)
DECLARE_STATIC_KEY_FALSE(bpf_master_redirect_enabled_key);
u32 xdp_master_redirect(struct xdp_buff *xdp);
void bpf_prog_change_xdp(struct bpf_prog *prev_prog, struct bpf_prog *prog);
static inline u32 bpf_prog_insn_size(const struct bpf_prog *prog){ return prog->len * sizeof(struct bpf_insn);}
static inline unsigned int bpf_prog_size(unsigned int proglen){ return max(sizeof(struct bpf_prog), offsetof(struct bpf_prog, insns[proglen]));}
static inline bool bpf_prog_was_classic(const struct bpf_prog *prog){ /* When classic BPF programs have been loaded and the arch * does not have a classic BPF JIT (anymore), they have been * converted via bpf_migrate_filter() to eBPF and thus always * have an unspec program type. */ return prog->type == BPF_PROG_TYPE_UNSPEC;}
static inline u32 bpf_ctx_off_adjust_machine(u32 size){ const u32 size_machine = sizeof(unsigned long);
if (size > size_machine && size % size_machine == 0) size = size_machine;
return size;}
static inline boolbpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default){ return size <= size_default && (size & (size - 1)) == 0;}
static inline u8bpf_ctx_narrow_access_offset(u32 off, u32 size, u32 size_default){ u8 access_off = off & (size_default - 1);
#ifdef __LITTLE_ENDIAN return access_off;#else return size_default - (access_off + size);#endif}
#define bpf_ctx_wide_access_ok(off, size, type, field) \ (size == sizeof(__u64) && \ off >= offsetof(type, field) && \ off + sizeof(__u64) <= offsetofend(type, field) && \ off % sizeof(__u64) == 0)
#define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0]))
static inline int __must_check bpf_prog_lock_ro(struct bpf_prog *fp){#ifndef CONFIG_BPF_JIT_ALWAYS_ON if (!fp->jited) { set_vm_flush_reset_perms(fp); return set_memory_ro((unsigned long)fp, fp->pages); }#endif return 0;}
static inline int __must_checkbpf_jit_binary_lock_ro(struct bpf_binary_header *hdr){ set_vm_flush_reset_perms(hdr); return set_memory_rox((unsigned long)hdr, hdr->size >> PAGE_SHIFT);}
enum skb_drop_reasonsk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap);
static inline int sk_filter(struct sock *sk, struct sk_buff *skb){ enum skb_drop_reason drop_reason;
drop_reason = sk_filter_trim_cap(sk, skb, 1); return drop_reason ? -EPERM : 0;}
static inline enum skb_drop_reasonsk_filter_reason(struct sock *sk, struct sk_buff *skb){ return sk_filter_trim_cap(sk, skb, 1);}
struct bpf_prog *__bpf_prog_select_runtime(struct bpf_verifier_env *env, struct bpf_prog *fp, int *err);struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err);void bpf_prog_free(struct bpf_prog *fp);
bool bpf_opcode_in_insntable(u8 code);
void bpf_prog_fill_jited_linfo(struct bpf_prog *prog, const u32 *insn_to_jit_off);int bpf_prog_alloc_jited_linfo(struct bpf_prog *prog);void bpf_prog_jit_attempt_done(struct bpf_prog *prog);
struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags);struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flags);struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, gfp_t gfp_extra_flags);void __bpf_prog_free(struct bpf_prog *fp);
static inline void bpf_prog_unlock_free(struct bpf_prog *fp){ __bpf_prog_free(fp);}
typedef int (*bpf_aux_classic_check_t)(struct sock_filter *filter, unsigned int flen);
int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog);int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog, bpf_aux_classic_check_t trans, bool save_orig);void bpf_prog_destroy(struct bpf_prog *fp);
int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk);int sk_attach_bpf(u32 ufd, struct sock *sk);int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk);int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk);void sk_reuseport_prog_free(struct bpf_prog *prog);int sk_detach_filter(struct sock *sk);int sk_get_filter(struct sock *sk, sockptr_t optval, unsigned int len);
bool sk_filter_charge(struct sock *sk, struct sk_filter *fp);void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp);
u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_prog *prog);void bpf_jit_compile(struct bpf_prog *prog);bool bpf_jit_needs_zext(void);bool bpf_jit_inlines_helper_call(s32 imm);bool bpf_jit_supports_subprog_tailcalls(void);bool bpf_jit_supports_percpu_insn(void);bool bpf_jit_supports_kfunc_call(void);bool bpf_jit_supports_stack_args(void);bool bpf_jit_supports_arena_args(void);bool bpf_jit_supports_far_kfunc_call(void);bool bpf_jit_supports_exceptions(void);bool bpf_jit_supports_ptr_xchg(void);bool bpf_jit_supports_arena(void);bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena);bool bpf_jit_supports_private_stack(void);bool bpf_jit_supports_timed_may_goto(void);bool bpf_jit_supports_fsession(void);u64 bpf_arch_uaddress_limit(void);void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie);u64 arch_bpf_timed_may_goto(void);u64 bpf_check_timed_may_goto(struct bpf_timed_may_goto *);bool bpf_helper_changes_pkt_data(enum bpf_func_id func_id);
static inline bool bpf_dump_raw_ok(const struct cred *cred){ /* Reconstruction of call-sites is dependent on kallsyms, * thus make dump the same restriction. */ return kallsyms_show_value(cred);}
struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len);
#ifdef CONFIG_BPF_SYSCALLstruct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 off, const struct bpf_insn *patch, u32 len);#elsestatic inline struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 off, const struct bpf_insn *patch, u32 len){ return ERR_PTR(-ENOTSUPP);}#endif /* CONFIG_BPF_SYSCALL */
int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt);
static inline bool xdp_return_frame_no_direct(void){ struct bpf_redirect_info *ri = bpf_net_ctx_get_ri();
return ri->kern_flags & BPF_RI_F_RF_NO_DIRECT;}
static inline void xdp_set_return_frame_no_direct(void){ struct bpf_redirect_info *ri = bpf_net_ctx_get_ri();
ri->kern_flags |= BPF_RI_F_RF_NO_DIRECT;}
static inline void xdp_clear_return_frame_no_direct(void){ struct bpf_redirect_info *ri = bpf_net_ctx_get_ri();
ri->kern_flags &= ~BPF_RI_F_RF_NO_DIRECT;}
static inline int xdp_ok_fwd_dev(const struct net_device *fwd, unsigned int pktlen){ unsigned int len;
if (unlikely(!(fwd->flags & IFF_UP))) return -ENETDOWN;
len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN; if (pktlen > len) return -EMSGSIZE;
return 0;}
/* The pair of xdp_do_redirect and xdp_do_flush MUST be called in the * same cpu context. Further for best results no more than a single map * for the do_redirect/do_flush pair should be used. This limitation is * because we only track one map and force a flush when the map changes. * This does not appear to be a real limitation for existing software. */int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, struct xdp_buff *xdp, const struct bpf_prog *prog);int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, const struct bpf_prog *prog);int xdp_do_redirect_frame(struct net_device *dev, struct xdp_buff *xdp, struct xdp_frame *xdpf, const struct bpf_prog *prog);void xdp_do_flush(void);
void bpf_warn_invalid_xdp_action(const struct net_device *dev, const struct bpf_prog *prog, u32 act);
#ifdef CONFIG_INETstruct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, struct bpf_prog *prog, struct sk_buff *skb, struct sock *migrating_sk, u32 hash);#elsestatic inline struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, struct bpf_prog *prog, struct sk_buff *skb, struct sock *migrating_sk, u32 hash){ return NULL;}#endif
#ifdef CONFIG_BPF_JITextern int bpf_jit_enable;extern int bpf_jit_harden;extern int bpf_jit_kallsyms;extern long bpf_jit_limit;extern long bpf_jit_limit_max;
typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size);
/* * Flush the indirect branch predictors before reusing JIT memory, so that * indirect jumps into a newly written program don't reuse predictions left * behind by an old program that occupied the same space. */void bpf_arch_pred_flush(void);DECLARE_STATIC_CALL(bpf_arch_pred_flush, bpf_arch_pred_flush);DECLARE_STATIC_KEY_FALSE(bpf_pred_flush_enabled);
void bpf_jit_fill_hole_with_zero(void *area, unsigned int size);
struct bpf_binary_header *bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, unsigned int alignment, bpf_jit_fill_hole_t bpf_fill_ill_insns);void bpf_jit_binary_free(struct bpf_binary_header *hdr);u64 bpf_jit_alloc_exec_limit(void);void *bpf_jit_alloc_exec(unsigned long size);void bpf_jit_free_exec(void *addr);void bpf_jit_free(struct bpf_prog *fp);struct bpf_binary_header *bpf_jit_binary_pack_hdr(const struct bpf_prog *fp);
void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns, bool was_classic);void bpf_prog_pack_free(void *ptr, u32 size);
static inline bool bpf_prog_kallsyms_verify_off(const struct bpf_prog *fp){ return list_empty(&fp->aux->ksym.lnode) || fp->aux->ksym.lnode.prev == LIST_POISON2;}
struct bpf_binary_header *bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **ro_image, unsigned int alignment, struct bpf_binary_header **rw_hdr, u8 **rw_image, bpf_jit_fill_hole_t bpf_fill_ill_insns, bool was_classic);int bpf_jit_binary_pack_finalize(struct bpf_binary_header *ro_header, struct bpf_binary_header *rw_header);void bpf_jit_binary_pack_free(struct bpf_binary_header *ro_header, struct bpf_binary_header *rw_header);
int bpf_jit_add_poke_descriptor(struct bpf_prog *prog, struct bpf_jit_poke_descriptor *poke);
int bpf_jit_get_func_addr(const struct bpf_prog *prog, const struct bpf_insn *insn, bool extra_pass, u64 *func_addr, bool *func_addr_fixed);
const char *bpf_jit_get_prog_name(struct bpf_prog *prog);
struct bpf_prog *bpf_jit_blind_constants(struct bpf_verifier_env *env, struct bpf_prog *prog);void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other);
static inline bool bpf_prog_need_blind(const struct bpf_prog *prog){ return prog->blinding_requested && !prog->blinded;}
static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen, u32 pass, void *image){ pr_err("flen=%u proglen=%u pass=%u image=%p from=%s pid=%d\n", flen, proglen, pass, image, current->comm, task_pid_nr(current));
if (image) print_hex_dump(KERN_ERR, "JIT code: ", DUMP_PREFIX_OFFSET, 16, 1, image, proglen, false);}
static inline bool bpf_jit_is_ebpf(void){# ifdef CONFIG_HAVE_EBPF_JIT return true;# else return false;# endif}
static inline bool ebpf_jit_enabled(void){ return bpf_jit_enable && bpf_jit_is_ebpf();}
static inline bool bpf_prog_ebpf_jited(const struct bpf_prog *fp){ return fp->jited && bpf_jit_is_ebpf();}
static inline bool bpf_jit_blinding_enabled(struct bpf_prog *prog){ /* These are the prerequisites, should someone ever have the * idea to call blinding outside of them, we make sure to * bail out. */ if (!bpf_jit_is_ebpf()) return false; if (!prog->jit_requested) return false; if (!bpf_jit_harden) return false; if (bpf_jit_harden == 1 && bpf_token_capable(prog->aux->token, CAP_BPF)) return false;
return true;}
static inline bool bpf_jit_kallsyms_enabled(void){ /* There are a couple of corner cases where kallsyms should * not be enabled f.e. on hardening. */ if (bpf_jit_harden) return false; if (!bpf_jit_kallsyms) return false; if (bpf_jit_kallsyms == 1) return true;
return false;}
int bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char *sym);bool is_bpf_text_address(unsigned long addr);int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym);struct bpf_prog *bpf_prog_ksym_find(unsigned long addr);
void bpf_prog_kallsyms_add(struct bpf_prog *fp);void bpf_prog_kallsyms_del(struct bpf_prog *fp);
#else /* CONFIG_BPF_JIT */
static inline bool ebpf_jit_enabled(void){ return false;}
static inline bool bpf_jit_blinding_enabled(struct bpf_prog *prog){ return false;}
static inline bool bpf_prog_ebpf_jited(const struct bpf_prog *fp){ return false;}
static inline intbpf_jit_add_poke_descriptor(struct bpf_prog *prog, struct bpf_jit_poke_descriptor *poke){ return -ENOTSUPP;}
static inline void bpf_jit_free(struct bpf_prog *fp){ bpf_prog_unlock_free(fp);}
static inline bool bpf_jit_kallsyms_enabled(void){ return false;}
static inline intbpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char *sym){ return 0;}
static inline bool is_bpf_text_address(unsigned long addr){ return false;}
static inline int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym){ return -ERANGE;}
static inline struct bpf_prog *bpf_prog_ksym_find(unsigned long addr){ return NULL;}
static inline void bpf_prog_kallsyms_add(struct bpf_prog *fp){}
static inline void bpf_prog_kallsyms_del(struct bpf_prog *fp){}
static inline bool bpf_prog_need_blind(const struct bpf_prog *prog){ return false;}
static inlinestruct bpf_prog *bpf_jit_blind_constants(struct bpf_verifier_env *env, struct bpf_prog *prog){ return prog;}
static inline void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other){}#endif /* CONFIG_BPF_JIT */
void bpf_prog_kallsyms_del_all(struct bpf_prog *fp);
#define BPF_ANC BIT(15)
static inline bool bpf_needs_clear_a(const struct sock_filter *first){ switch (first->code) { case BPF_RET | BPF_K: case BPF_LD | BPF_W | BPF_LEN: return false;
case BPF_LD | BPF_W | BPF_ABS: case BPF_LD | BPF_H | BPF_ABS: case BPF_LD | BPF_B | BPF_ABS: if (first->k == SKF_AD_OFF + SKF_AD_ALU_XOR_X) return true; return false;
default: return true; }}
static inline u16 bpf_anc_helper(const struct sock_filter *ftest){ BUG_ON(ftest->code & BPF_ANC);
switch (ftest->code) { case BPF_LD | BPF_W | BPF_ABS: case BPF_LD | BPF_H | BPF_ABS: case BPF_LD | BPF_B | BPF_ABS:#define BPF_ANCILLARY(CODE) case SKF_AD_OFF + SKF_AD_##CODE: \ return BPF_ANC | SKF_AD_##CODE switch (ftest->k) { BPF_ANCILLARY(PROTOCOL); BPF_ANCILLARY(PKTTYPE); BPF_ANCILLARY(IFINDEX); BPF_ANCILLARY(NLATTR); BPF_ANCILLARY(NLATTR_NEST); BPF_ANCILLARY(MARK); BPF_ANCILLARY(QUEUE); BPF_ANCILLARY(HATYPE); BPF_ANCILLARY(RXHASH); BPF_ANCILLARY(CPU); BPF_ANCILLARY(ALU_XOR_X); BPF_ANCILLARY(VLAN_TAG); BPF_ANCILLARY(VLAN_TAG_PRESENT); BPF_ANCILLARY(PAY_OFFSET); BPF_ANCILLARY(RANDOM); BPF_ANCILLARY(VLAN_TPID); } fallthrough; default: return ftest->code; }}
void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, unsigned int size);
static inline int bpf_tell_extensions(void){ return SKF_AD_MAX;}
struct bpf_sock_addr_kern { struct sock *sk; struct sockaddr_unsized *uaddr; /* Temporary "register" to make indirect stores to nested structures * defined above. We need three registers to make such a store, but * only two (src and dst) are available at convert_ctx_access time */ u64 tmp_reg; void *t_ctx; /* Attach type specific context. */ u32 uaddrlen;};
struct bpf_sock_ops_kern { struct sock *sk; union { u32 args[4]; u32 reply; u32 replylong[4]; }; struct sk_buff *syn_skb; struct sk_buff *skb; void *skb_data_end; u8 op; u8 is_fullsock; u8 is_locked_tcp_sock; u8 remaining_opt_len; u64 temp; /* temp and everything after is not * initialized to 0 before calling * the BPF program. New fields that * should be initialized to 0 should * be inserted before temp. * temp is scratch storage used by * sock_ops_convert_ctx_access * as temporary storage of a register. */};
struct bpf_sysctl_kern { struct ctl_table_header *head; const struct ctl_table *table; void *cur_val; size_t cur_len; void *new_val; size_t new_len; int new_updated; int write; loff_t *ppos; /* Temporary "register" for indirect stores to ppos. */ u64 tmp_reg;};
#define BPF_SOCKOPT_KERN_BUF_SIZE 32struct bpf_sockopt_buf { u8 data[BPF_SOCKOPT_KERN_BUF_SIZE];};
struct bpf_sockopt_kern { struct sock *sk; u8 *optval; u8 *optval_end; s32 level; s32 optname; s32 optlen; /* for retval in struct bpf_cg_run_ctx */ struct task_struct *current_task; /* Temporary "register" for indirect stores to ppos. */ u64 tmp_reg;};
int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len);
struct bpf_sk_lookup_kern { u16 family; u16 protocol; __be16 sport; u16 dport; struct { __be32 saddr; __be32 daddr; } v4; struct { const struct in6_addr *saddr; const struct in6_addr *daddr; } v6; struct sock *selected_sk; u32 ingress_ifindex; bool no_reuseport;};
extern struct static_key_false bpf_sk_lookup_enabled;
/* Runners for BPF_SK_LOOKUP programs to invoke on socket lookup. * * Allowed return values for a BPF SK_LOOKUP program are SK_PASS and * SK_DROP. Their meaning is as follows: * * SK_PASS && ctx.selected_sk != NULL: use selected_sk as lookup result * SK_PASS && ctx.selected_sk == NULL: continue to htable-based socket lookup * SK_DROP : terminate lookup with -ECONNREFUSED * * This macro aggregates return values and selected sockets from * multiple BPF programs according to following rules in order: * * 1. If any program returned SK_PASS and a non-NULL ctx.selected_sk, * macro result is SK_PASS and last ctx.selected_sk is used. * 2. If any program returned SK_DROP return value, * macro result is SK_DROP. * 3. Otherwise result is SK_PASS and ctx.selected_sk is NULL. * * Caller must ensure that the prog array is non-NULL, and that the * array as well as the programs it contains remain valid. */#define BPF_PROG_SK_LOOKUP_RUN_ARRAY(array, ctx, func) \ ({ \ struct bpf_sk_lookup_kern *_ctx = &(ctx); \ struct bpf_prog_array_item *_item; \ struct sock *_selected_sk = NULL; \ bool _no_reuseport = false; \ struct bpf_prog *_prog; \ bool _all_pass = true; \ u32 _ret; \ \ migrate_disable(); \ _item = &(array)->items[0]; \ while ((_prog = READ_ONCE(_item->prog))) { \ /* restore most recent selection */ \ _ctx->selected_sk = _selected_sk; \ _ctx->no_reuseport = _no_reuseport; \ \ _ret = func(_prog, _ctx); \ if (_ret == SK_PASS && _ctx->selected_sk) { \ /* remember last non-NULL socket */ \ _selected_sk = _ctx->selected_sk; \ _no_reuseport = _ctx->no_reuseport; \ } else if (_ret == SK_DROP && _all_pass) { \ _all_pass = false; \ } \ _item++; \ } \ _ctx->selected_sk = _selected_sk; \ _ctx->no_reuseport = _no_reuseport; \ migrate_enable(); \ _all_pass || _selected_sk ? SK_PASS : SK_DROP; \ })
static inline bool bpf_sk_lookup_run_v4(const struct net *net, int protocol, const __be32 saddr, const __be16 sport, const __be32 daddr, const u16 dport, const int ifindex, struct sock **psk){ struct bpf_prog_array *run_array; struct sock *selected_sk = NULL; bool no_reuseport = false;
rcu_read_lock(); run_array = rcu_dereference(net->bpf.run_array[NETNS_BPF_SK_LOOKUP]); if (run_array) { struct bpf_sk_lookup_kern ctx = { .family = AF_INET, .protocol = protocol, .v4.saddr = saddr, .v4.daddr = daddr, .sport = sport, .dport = dport, .ingress_ifindex = ifindex, }; u32 act;
act = BPF_PROG_SK_LOOKUP_RUN_ARRAY(run_array, ctx, bpf_prog_run); if (act == SK_PASS) { selected_sk = ctx.selected_sk; no_reuseport = ctx.no_reuseport; } else { selected_sk = ERR_PTR(-ECONNREFUSED); } } rcu_read_unlock(); *psk = selected_sk; return no_reuseport;}
#if IS_ENABLED(CONFIG_IPV6)static inline bool bpf_sk_lookup_run_v6(const struct net *net, int protocol, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const u16 dport, const int ifindex, struct sock **psk){ struct bpf_prog_array *run_array; struct sock *selected_sk = NULL; bool no_reuseport = false;
rcu_read_lock(); run_array = rcu_dereference(net->bpf.run_array[NETNS_BPF_SK_LOOKUP]); if (run_array) { struct bpf_sk_lookup_kern ctx = { .family = AF_INET6, .protocol = protocol, .v6.saddr = saddr, .v6.daddr = daddr, .sport = sport, .dport = dport, .ingress_ifindex = ifindex, }; u32 act;
act = BPF_PROG_SK_LOOKUP_RUN_ARRAY(run_array, ctx, bpf_prog_run); if (act == SK_PASS) { selected_sk = ctx.selected_sk; no_reuseport = ctx.no_reuseport; } else { selected_sk = ERR_PTR(-ECONNREFUSED); } } rcu_read_unlock(); *psk = selected_sk; return no_reuseport;}#endif /* IS_ENABLED(CONFIG_IPV6) */
static __always_inline long __bpf_xdp_redirect_map(struct bpf_map *map, u64 index, u64 flags, const u64 flag_mask, void *lookup_elem(struct bpf_map *map, u32 key)){ struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); const u64 action_mask = XDP_ABORTED | XDP_DROP | XDP_PASS | XDP_TX;
/* Lower bits of the flags are used as return code on lookup failure */ if (unlikely(flags & ~(action_mask | flag_mask))) return XDP_ABORTED;
ri->tgt_value = lookup_elem(map, index); if (unlikely(!ri->tgt_value) && !(flags & BPF_F_BROADCAST)) { /* If the lookup fails we want to clear out the state in the * redirect_info struct completely, so that if an eBPF program * performs multiple lookups, the last one always takes * precedence. */ ri->map_id = INT_MAX; /* Valid map id idr range: [1,INT_MAX[ */ ri->map_type = BPF_MAP_TYPE_UNSPEC; return flags & action_mask; }
ri->tgt_index = index; ri->map_id = map->id; ri->map_type = map->map_type;
if (flags & BPF_F_BROADCAST) { WRITE_ONCE(ri->map, map); ri->flags = flags; } else { WRITE_ONCE(ri->map, NULL); ri->flags = 0; }
return XDP_REDIRECT;}
#ifdef CONFIG_NETint __bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, void *to, u32 len);int __bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags);int __bpf_xdp_load_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len);int __bpf_xdp_store_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len);void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len);void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, void *buf, unsigned long len, bool flush);int __bpf_skb_meta_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags);void *bpf_skb_meta_pointer(struct sk_buff *skb, u32 offset);#else /* CONFIG_NET */static inline int __bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, void *to, u32 len){ return -EOPNOTSUPP;}
static inline int __bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags){ return -EOPNOTSUPP;}
static inline int __bpf_xdp_load_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len){ return -EOPNOTSUPP;}
static inline int __bpf_xdp_store_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len){ return -EOPNOTSUPP;}
static inline void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len){ return NULL;}
static inline void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, void *buf, unsigned long len, bool flush){}
static inline int __bpf_skb_meta_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags){ return -EOPNOTSUPP;}
static inline void *bpf_skb_meta_pointer(struct sk_buff *skb, u32 offset){ return ERR_PTR(-EOPNOTSUPP);}#endif /* CONFIG_NET */
#endif /* __LINUX_FILTER_H__ */