diff options
177 files changed, 8407 insertions, 1798 deletions
diff --git a/Documentation/bpf/cpumasks.rst b/Documentation/bpf/cpumasks.rst index a22b6ad105fb..b5d47a04da5d 100644 --- a/Documentation/bpf/cpumasks.rst +++ b/Documentation/bpf/cpumasks.rst @@ -352,7 +352,7 @@ can be used to query the contents of cpumasks. .. kernel-doc:: kernel/bpf/cpumask.c :identifiers: bpf_cpumask_first bpf_cpumask_first_zero bpf_cpumask_first_and - bpf_cpumask_test_cpu + bpf_cpumask_test_cpu bpf_cpumask_weight .. kernel-doc:: kernel/bpf/cpumask.c :identifiers: bpf_cpumask_equal bpf_cpumask_intersects bpf_cpumask_subset diff --git a/Documentation/bpf/fs_kfuncs.rst b/Documentation/bpf/fs_kfuncs.rst new file mode 100644 index 000000000000..8762c3233a3d --- /dev/null +++ b/Documentation/bpf/fs_kfuncs.rst @@ -0,0 +1,21 @@ +.. SPDX-License-Identifier: GPL-2.0 + +.. _fs_kfuncs-header-label: + +===================== +BPF filesystem kfuncs +===================== + +BPF LSM programs need to access filesystem data from LSM hooks. The following +BPF kfuncs can be used to get these data. + + * ``bpf_get_file_xattr()`` + + * ``bpf_get_fsverity_digest()`` + +To avoid recursions, these kfuncs follow the following rules: + +1. These kfuncs are only permitted from BPF LSM function. +2. These kfuncs should not call into other LSM hooks, i.e. security_*(). For + example, ``bpf_get_file_xattr()`` does not use ``vfs_getxattr()``, because + the latter calls LSM hook ``security_inode_getxattr``. diff --git a/Documentation/bpf/index.rst b/Documentation/bpf/index.rst index aeaeb35e6d4a..0bb5cb8157f1 100644 --- a/Documentation/bpf/index.rst +++ b/Documentation/bpf/index.rst @@ -21,6 +21,7 @@ that goes into great technical depth about the BPF Architecture. helpers kfuncs cpumasks + fs_kfuncs programs maps bpf_prog_run diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index f2c76d103bd8..3addac970680 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -54,6 +54,10 @@ definitions: name: hash doc: Device is capable of exposing receive packet hash via bpf_xdp_metadata_rx_hash(). + - + name: vlan-tag + doc: + Device is capable of exposing receive packet VLAN tag via bpf_xdp_metadata_rx_vlan_tag(). - type: flags name: xsk-flags diff --git a/Documentation/networking/xdp-rx-metadata.rst b/Documentation/networking/xdp-rx-metadata.rst index e3e9420fd817..a6e0ece18be5 100644 --- a/Documentation/networking/xdp-rx-metadata.rst +++ b/Documentation/networking/xdp-rx-metadata.rst @@ -20,7 +20,13 @@ Currently, the following kfuncs are supported. In the future, as more metadata is supported, this set will grow: .. kernel-doc:: net/core/xdp.c - :identifiers: bpf_xdp_metadata_rx_timestamp bpf_xdp_metadata_rx_hash + :identifiers: bpf_xdp_metadata_rx_timestamp + +.. kernel-doc:: net/core/xdp.c + :identifiers: bpf_xdp_metadata_rx_hash + +.. kernel-doc:: net/core/xdp.c + :identifiers: bpf_xdp_metadata_rx_vlan_tag An XDP program can use these kfuncs to read the metadata into stack variables for its own consumption. Or, to pass the metadata on to other diff --git a/Documentation/networking/xsk-tx-metadata.rst b/Documentation/networking/xsk-tx-metadata.rst index 97ecfa480d00..bd033fe95cca 100644 --- a/Documentation/networking/xsk-tx-metadata.rst +++ b/Documentation/networking/xsk-tx-metadata.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: GPL-2.0 + ================== AF_XDP TX Metadata ================== diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 7d4af64e3982..8955da5c47cf 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -1828,7 +1828,7 @@ static void restore_args(struct jit_ctx *ctx, int args_off, int nregs) * */ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, - struct bpf_tramp_links *tlinks, void *orig_call, + struct bpf_tramp_links *tlinks, void *func_addr, int nregs, u32 flags) { int i; @@ -1926,7 +1926,7 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, if (flags & BPF_TRAMP_F_IP_ARG) { /* save ip address of the traced function */ - emit_addr_mov_i64(A64_R(10), (const u64)orig_call, ctx); + emit_addr_mov_i64(A64_R(10), (const u64)func_addr, ctx); emit(A64_STR64I(A64_R(10), A64_SP, ip_off), ctx); } @@ -2026,18 +2026,10 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, return ctx->idx; } -int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, - void *image_end, const struct btf_func_model *m, - u32 flags, struct bpf_tramp_links *tlinks, - void *orig_call) +static int btf_func_model_nregs(const struct btf_func_model *m) { - int i, ret; int nregs = m->nr_args; - int max_insns = ((long)image_end - (long)image) / AARCH64_INSN_SIZE; - struct jit_ctx ctx = { - .image = NULL, - .idx = 0, - }; + int i; /* extra registers needed for struct argument */ for (i = 0; i < MAX_BPF_FUNC_ARGS; i++) { @@ -2046,22 +2038,49 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, nregs += (m->arg_size[i] + 7) / 8 - 1; } + return nregs; +} + +int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, + struct bpf_tramp_links *tlinks, void *func_addr) +{ + struct jit_ctx ctx = { + .image = NULL, + .idx = 0, + }; + struct bpf_tramp_image im; + int nregs, ret; + + nregs = btf_func_model_nregs(m); /* the first 8 registers are used for arguments */ if (nregs > 8) return -ENOTSUPP; - ret = prepare_trampoline(&ctx, im, tlinks, orig_call, nregs, flags); + ret = prepare_trampoline(&ctx, &im, tlinks, func_addr, nregs, flags); if (ret < 0) return ret; - if (ret > max_insns) - return -EFBIG; + return ret < 0 ? ret : ret * AARCH64_INSN_SIZE; +} - ctx.image = image; - ctx.idx = 0; +int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, + void *image_end, const struct btf_func_model *m, + u32 flags, struct bpf_tramp_links *tlinks, + void *func_addr) +{ + int ret, nregs; + struct jit_ctx ctx = { + .image = image, + .idx = 0, + }; + + nregs = btf_func_model_nregs(m); + /* the first 8 registers are used for arguments */ + if (nregs > 8) + return -ENOTSUPP; jit_fill_hole(image, (unsigned int)(image_end - image)); - ret = prepare_trampoline(&ctx, im, tlinks, orig_call, nregs, flags); + ret = prepare_trampoline(&ctx, im, tlinks, func_addr, nregs, flags); if (ret > 0 && validate_code(&ctx) < 0) ret = -EINVAL; diff --git a/arch/riscv/include/asm/cfi.h b/arch/riscv/include/asm/cfi.h index 56bf9d69d5e3..8f7a62257044 100644 --- a/arch/riscv/include/asm/cfi.h +++ b/arch/riscv/include/asm/cfi.h @@ -7,8 +7,9 @@ * * Copyright (C) 2023 Google LLC */ +#include <linux/bug.h> -#include <linux/cfi.h> +struct pt_regs; #ifdef CONFIG_CFI_CLANG enum bug_trap_type handle_cfi_failure(struct pt_regs *regs); diff --git a/arch/riscv/kernel/cfi.c b/arch/riscv/kernel/cfi.c index 820158d7a291..6ec9dbd7292e 100644 --- a/arch/riscv/kernel/cfi.c +++ b/arch/riscv/kernel/cfi.c @@ -4,7 +4,7 @@ * * Copyright (C) 2023 Google LLC */ -#include <asm/cfi.h> +#include <linux/cfi.h> #include <asm/insn.h> /* diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index 8581693e62d3..58dc64dd94a8 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -1029,23 +1029,28 @@ out: return ret; } -int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, - void *image_end, const struct btf_func_model *m, - u32 flags, struct bpf_tramp_links *tlinks, - void *func_addr) +int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, + struct bpf_tramp_links *tlinks, void *func_addr) { - int ret; + struct bpf_tramp_image im; struct rv_jit_context ctx; + int ret; ctx.ninsns = 0; ctx.insns = NULL; ctx.ro_insns = NULL; - ret = __arch_prepare_bpf_trampoline(im, m, tlinks, func_addr, flags, &ctx); - if (ret < 0) - return ret; + ret = __arch_prepare_bpf_trampoline(&im, m, tlinks, func_addr, flags, &ctx); - if (ninsns_rvoff(ret) > (long)image_end - (long)image) - return -EFBIG; + return ret < 0 ? ret : ninsns_rvoff(ctx.ninsns); +} + +int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, + void *image_end, const struct btf_func_model *m, + u32 flags, struct bpf_tramp_links *tlinks, + void *func_addr) +{ + int ret; + struct rv_jit_context ctx; ctx.ninsns = 0; /* diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index bf06b7283f0c..7f0a7b97ef4c 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -2362,7 +2362,8 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, return -ENOTSUPP; /* Return to %r14, since func_addr and %r0 are not available. */ - if (!func_addr && !(flags & BPF_TRAMP_F_ORIG_STACK)) + if ((!func_addr && !(flags & BPF_TRAMP_F_ORIG_STACK)) || + (flags & BPF_TRAMP_F_INDIRECT)) flags |= BPF_TRAMP_F_SKIP_FRAME; /* @@ -2637,6 +2638,21 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, return 0; } +int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, + struct bpf_tramp_links *tlinks, void *orig_call) +{ + struct bpf_tramp_image im; + struct bpf_tramp_jit tjit; + int ret; + + memset(&tjit, 0, sizeof(tjit)); + + ret = __arch_prepare_bpf_trampoline(&im, &tjit, m, flags, + tlinks, orig_call); + + return ret < 0 ? ret : tjit.common.prg; +} + int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end, const struct btf_func_model *m, u32 flags, struct bpf_tramp_links *tlinks, @@ -2644,30 +2660,27 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, { struct bpf_tramp_jit tjit; int ret; - int i; - for (i = 0; i < 2; i++) { - if (i == 0) { - /* Compute offsets, check whether the code fits. */ - memset(&tjit, 0, sizeof(tjit)); - } else { - /* Generate the code. */ - tjit.common.prg = 0; - tjit.common.prg_buf = image; - } - ret = __arch_prepare_bpf_trampoline(im, &tjit, m, flags, - tlinks, func_addr); - if (ret < 0) - return ret; - if (tjit.common.prg > (char *)image_end - (char *)image) - /* - * Use the same error code as for exceeding - * BPF_MAX_TRAMP_LINKS. - */ - return -E2BIG; - } + /* Compute offsets, check whether the code fits. */ + memset(&tjit, 0, sizeof(tjit)); + ret = __arch_prepare_bpf_trampoline(im, &tjit, m, flags, + tlinks, func_addr); + + if (ret < 0) + return ret; + if (tjit.common.prg > (char *)image_end - (char *)image) + /* + * Use the same error code as for exceeding + * BPF_MAX_TRAMP_LINKS. + */ + return -E2BIG; + + tjit.common.prg = 0; + tjit.common.prg_buf = image; + ret = __arch_prepare_bpf_trampoline(im, &tjit, m, flags, + tlinks, func_addr); - return tjit.common.prg; + return ret < 0 ? ret : tjit.common.prg; } bool bpf_jit_supports_subprog_tailcalls(void) diff --git a/arch/x86/include/asm/cfi.h b/arch/x86/include/asm/cfi.h index 58dacd90daef..7cd752557905 100644 --- a/arch/x86/include/asm/cfi.h +++ b/arch/x86/include/asm/cfi.h @@ -7,16 +7,140 @@ * * Copyright (C) 2022 Google LLC */ +#include <linux/bug.h> +#include <asm/ibt.h> -#include <linux/cfi.h> +/* + * An overview of the various calling conventions... + * + * Traditional: + * + * foo: + * ... code here ... + * ret + * + * direct caller: + * call foo + * + * indirect caller: + * lea foo(%rip), %r11 + * ... + * call *%r11 + * + * + * IBT: + * + * foo: + * endbr64 + * ... code here ... + * ret + * + * direct caller: + * call foo / call foo+4 + * + * indirect caller: + * lea foo(%rip), %r11 + * ... + * call *%r11 + * + * + * kCFI: + * + * __cfi_foo: + * movl $0x12345678, %eax + * # 11 nops when CONFIG_CALL_PADDING + * foo: + * endbr64 # when IBT + * ... code here ... + * ret + * + * direct call: + * call foo # / call foo+4 when IBT + * + * indirect call: + * lea foo(%rip), %r11 + * ... + * movl $(-0x12345678), %r10d + * addl -4(%r11), %r10d # -15 when CONFIG_CALL_PADDING + * jz 1f + * ud2 + * 1:call *%r11 + * + * + * FineIBT (builds as kCFI + CALL_PADDING + IBT + RETPOLINE and runtime patches into): + * + * __cfi_foo: + * endbr64 + * subl 0x12345678, %r10d + * jz foo + * ud2 + * nop + * foo: + * osp nop3 # was endbr64 + * ... code here ... + * ret + * + * direct caller: + * call foo / call foo+4 + * + * indirect caller: + * lea foo(%rip), %r11 + * ... + * movl $0x12345678, %r10d + * subl $16, %r11 + * nop4 + * call *%r11 + * + */ +enum cfi_mode { + CFI_DEFAULT, /* FineIBT if hardware has IBT, otherwise kCFI */ + CFI_OFF, /* Taditional / IBT depending on .config */ + CFI_KCFI, /* Optionally CALL_PADDING, IBT, RETPOLINE */ + CFI_FINEIBT, /* see arch/x86/kernel/alternative.c */ +}; + +extern enum cfi_mode cfi_mode; + +struct pt_regs; #ifdef CONFIG_CFI_CLANG enum bug_trap_type handle_cfi_failure(struct pt_regs *regs); +#define __bpfcall +extern u32 cfi_bpf_hash; +extern u32 cfi_bpf_subprog_hash; + +static inline int cfi_get_offset(void) +{ + switch (cfi_mode) { + case CFI_FINEIBT: + return 16; + case CFI_KCFI: + if (IS_ENABLED(CONFIG_CALL_PADDING)) + return 16; + return 5; + default: + return 0; + } +} +#define cfi_get_offset cfi_get_offset + +extern u32 cfi_get_func_hash(void *func); + #else static inline enum bug_trap_type handle_cfi_failure(struct pt_regs *regs) { return BUG_TRAP_TYPE_NONE; } +#define cfi_bpf_hash 0U +#define cfi_bpf_subprog_hash 0U +static inline u32 cfi_get_func_hash(void *func) +{ + return 0; +} #endif /* CONFIG_CFI_CLANG */ +#if HAS_KERNEL_IBT == 1 +#define CFI_NOSEAL(x) asm(IBT_NOSEAL(__stringify(x))) +#endif + #endif /* _ASM_X86_CFI_H */ diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 73be3931e4f0..49c2a62ba5e4 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -30,6 +30,7 @@ #include <asm/fixmap.h> #include <asm/paravirt.h> #include <asm/asm-prototypes.h> +#include <asm/cfi.h> int __read_mostly alternatives_patched; @@ -832,15 +833,82 @@ void __init_or_module apply_seal_endbr(s32 *start, s32 *end) { } #endif /* CONFIG_X86_KERNEL_IBT */ #ifdef CONFIG_FINEIBT +#define __CFI_DEFAULT CFI_DEFAULT +#elif defined(CONFIG_CFI_CLANG) +#define __CFI_DEFAULT CFI_KCFI +#else +#define __CFI_DEFAULT CFI_OFF +#endif -enum cfi_mode { - CFI_DEFAULT, - CFI_OFF, - CFI_KCFI, - CFI_FINEIBT, -}; +enum cfi_mode cfi_mode __ro_after_init = __CFI_DEFAULT; + +#ifdef CONFIG_CFI_CLANG +struct bpf_insn; + +/* Must match bpf_func_t / DEFINE_BPF_PROG_RUN() */ +extern unsigned int __bpf_prog_runX(const void *ctx, + const struct bpf_insn *insn); + +/* + * Force a reference to the external symbol so the compiler generates + * __kcfi_typid. + */ +__ADDRESSABLE(__bpf_prog_runX); + +/* u32 __ro_after_init cfi_bpf_hash = __kcfi_typeid___bpf_prog_runX; */ +asm ( +" .pushsection .data..ro_after_init,\"aw\",@progbits \n" +" .type cfi_bpf_hash,@object \n" +" .globl cfi_bpf_hash \n" +" .p2align 2, 0x0 \n" +"cfi_bpf_hash: \n" +" .long __kcfi_typeid___bpf_prog_runX \n" +" .size cfi_bpf_hash, 4 \n" +" .popsection \n" +); + +/* Must match bpf_callback_t */ +extern u64 __bpf_callback_fn(u64, u64, u64, u64, u64); + +__ADDRESSABLE(__bpf_callback_fn); + +/* u32 __ro_after_init cfi_bpf_subprog_hash = __kcfi_typeid___bpf_callback_fn; */ +asm ( +" .pushsection .data..ro_after_init,\"aw\",@progbits \n" +" .type cfi_bpf_subprog_hash,@object \n" +" .globl cfi_bpf_subprog_hash \n" +" .p2align 2, 0x0 \n" +"cfi_bpf_subprog_hash: \n" +" .long __kcfi_typeid___bpf_callback_fn \n" +" .size cfi_bpf_subprog_hash, 4 \n" +" .popsection \n" +); + +u32 cfi_get_func_hash(void *func) +{ + u32 hash; + + func -= cfi_get_offset(); + switch (cfi_mode) { + case CFI_FINEIBT: + func += 7; + break; + case CFI_KCFI: + func += 1; + break; + default: + return 0; + } + + if (get_kernel_nofault(hash, func)) + return 0; + + return hash; +} +#endif + +#ifdef CONFIG_FINEIBT -static enum cfi_mode cfi_mode __ro_after_init = CFI_DEFAULT; static bool cfi_rand __ro_after_init = true; static u32 cfi_seed __ro_after_init; @@ -1149,8 +1217,11 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline, goto err; if (cfi_rand) { - if (builtin) + if (builtin) { cfi_seed = get_random_u32(); + cfi_bpf_hash = cfi_rehash(cfi_bpf_hash); + cfi_bpf_subprog_hash = cfi_rehash(cfi_bpf_subprog_hash); + } ret = cfi_rand_preamble(start_cfi, end_cfi); if (ret) diff --git a/arch/x86/kernel/cfi.c b/arch/x86/kernel/cfi.c index 8674a5c0c031..e6bf78fac146 100644 --- a/arch/x86/kernel/cfi.c +++ b/arch/x86/kernel/cfi.c @@ -4,10 +4,10 @@ * * Copyright (C) 2022 Google LLC */ -#include <asm/cfi.h> +#include <linux/string.h> +#include <linux/cfi.h> #include <asm/insn.h> #include <asm/insn-eval.h> -#include <linux/string.h> /* * Returns the target address and the expected type when regs->ip points diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index e89e415aa743..bdacbb84456d 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -17,6 +17,7 @@ #include <asm/nospec-branch.h> #include <asm/text-patching.h> #include <asm/unwind.h> +#include <asm/cfi.h> static bool all_callee_regs_used[4] = {true, true, true, true}; @@ -51,9 +52,11 @@ static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len) do { EMIT4(b1, b2, b3, b4); EMIT(off, 4); } while (0) #ifdef CONFIG_X86_KERNEL_IBT -#define EMIT_ENDBR() EMIT(gen_endbr(), 4) +#define EMIT_ENDBR() EMIT(gen_endbr(), 4) +#define EMIT_ENDBR_POISON() EMIT(gen_endbr_poison(), 4) #else #define EMIT_ENDBR() +#define EMIT_ENDBR_POISON() #endif static bool is_imm8(int value) @@ -305,6 +308,69 @@ static void pop_callee_regs(u8 **pprog, bool *callee_regs_used) } /* + * Emit the various CFI preambles, see asm/cfi.h and the comments about FineIBT + * in arch/x86/kernel/alternative.c + */ + +static void emit_fineibt(u8 **pprog, u32 hash) +{ + u8 *prog = *pprog; + + EMIT_ENDBR(); + EMIT3_off32(0x41, 0x81, 0xea, hash); /* subl $hash, %r10d */ + EMIT2(0x74, 0x07); /* jz.d8 +7 */ + EMIT2(0x0f, 0x0b); /* ud2 */ + EMIT1(0x90); /* nop */ + EMIT_ENDBR_POISON(); + + *pprog = prog; +} + +static void emit_kcfi(u8 **pprog, u32 hash) +{ + u8 *prog = *pprog; + + EMIT1_off32(0xb8, hash); /* movl $hash, %eax */ +#ifdef CONFIG_CALL_PADDING + EMIT1(0x90); + EMIT1(0x90); + EMIT1(0x90); + EMIT1(0x90); + EMIT1(0x90); + EMIT1(0x90); + EMIT1(0x90); + EMIT1(0x90); + EMIT1(0x90); + EMIT1(0x90); + EMIT1(0x90); +#endif + EMIT_ENDBR(); + + *pprog = prog; +} + +static void emit_cfi(u8 **pprog, u32 hash) +{ + u8 *prog = *pprog; + + switch (cfi_mode) { + case CFI_FINEIBT: + emit_fineibt(&prog, hash); + break; + + case CFI_KCFI: + emit_kcfi(&prog, hash); + break; + + default: + EMIT_ENDBR(); + break; + } + + *pprog = prog; +} + +/* * Emit x86-64 prologue code for BPF program. * bpf_tail_call helper will skip the first X86_TAIL_CALL_OFFSET bytes * while jumping to another program @@ -315,10 +381,10 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf, { u8 *prog = *pprog; + emit_cfi(&prog, is_subprog ? cfi_bpf_subprog_hash : cfi_bpf_hash); /* BPF trampoline can be made to work without these nops, * but let's waste 5 bytes for now and optimize later */ - EMIT_ENDBR(); memcpy(prog, x86_nops[5], X86_PATCH_SIZE); prog += X86_PATCH_SIZE; if (!ebpf_from_cbpf) { @@ -2198,7 +2264,8 @@ static void restore_regs(const struct btf_func_model *m, u8 **prog, static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, struct bpf_tramp_link *l, int stack_size, - int run_ctx_off, bool save_ret) + int run_ctx_off, bool save_ret, + void *image, void *rw_image) { u8 *prog = *pprog; u8 *jmp_insn; @@ -2226,7 +2293,7 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, else EMIT4(0x48, 0x8D, 0x75, -run_ctx_off); - if (emit_rsb_call(&prog, bpf_trampoline_enter(p), prog)) + if (emit_rsb_call(&prog, bpf_trampoline_enter(p), image + (prog - (u8 *)rw_image))) return -EINVAL; /* remember prog start time returned by __bpf_prog_enter */ emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0); @@ -2250,7 +2317,7 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, (long) p->insnsi >> 32, (u32) (long) p->insnsi); /* call JITed bpf program or interpreter */ - if (emit_rsb_call(&prog, p->bpf_func, prog)) + if (emit_rsb_call(&prog, p->bpf_func, image + (prog - (u8 *)rw_image))) return -EINVAL; /* @@ -2277,7 +2344,7 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, EMIT3_off32(0x48, 0x8D, 0x95, -run_ctx_off); else EMIT4(0x48, 0x8D, 0x55, -run_ctx_off); - if (emit_rsb_call(&prog, bpf_trampoline_exit(p), prog)) + if (emit_rsb_call(&prog, bpf_trampoline_exit(p), image + (prog - (u8 *)rw_image))) return -EINVAL; *pprog = prog; @@ -2312,14 +2379,15 @@ static int emit_cond_near_jump(u8 **pprog, void *func, void *ip, u8 jmp_cond) static int invoke_bpf(const struct btf_func_model *m, u8 **pprog, struct bpf_tramp_links *tl, int stack_size, - int run_ctx_off, bool save_ret) + int run_ctx_off, bool save_ret, + void *image, void *rw_image) { int i; u8 *prog = *pprog; for (i = 0; i < tl->nr_links; i++) { if (invoke_bpf_prog(m, &prog, tl->links[i], stack_size, - run_ctx_off, save_ret)) + run_ctx_off, save_ret, image, rw_image)) return -EINVAL; } *pprog = prog; @@ -2328,7 +2396,8 @@ static int invoke_bpf(const struct btf_func_model *m, u8 **pprog, static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog, struct bpf_tramp_links *tl, int stack_size, - int run_ctx_off, u8 **branches) + int run_ctx_off, u8 **branches, + void *image, void *rw_image) { u8 *prog = *pprog; int i; @@ -2339,7 +2408,8 @@ static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog, emit_mov_imm32(&prog, false, BPF_REG_0, 0); emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8); for (i = 0; i < tl->nr_links; i++) { - if (invoke_bpf_prog(m, &prog, tl->links[i], stack_size, run_ctx_off, true)) + if (invoke_bpf_prog(m, &prog, tl->links[i], stack_size, run_ctx_off, true, + image, rw_image)) return -EINVAL; /* mod_ret prog stored return value into [rbp - 8]. Emit: @@ -2422,10 +2492,11 @@ static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog, * add rsp, 8 // skip eth_type_trans's frame * ret // return to its caller */ -int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end, - const struct btf_func_model *m, u32 flags, - struct bpf_tramp_links *tlinks, - void *func_addr) +static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_image, + void *rw_image_end, void *image, + const struct btf_func_model *m, u32 flags, + struct bpf_tramp_links *tlinks, + void *func_addr) { int i, ret, nr_regs = m->nr_args, stack_size = 0; int regs_off, nregs_off, ip_off, run_ctx_off, arg_stack_off, rbx_off; @@ -2437,10 +2508,19 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i u8 *prog; bool save_ret; + /* + * F_INDIRECT is only compatible with F_RET_FENTRY_RET, it is + * explicitly incompatible with F_CALL_ORIG | F_SKIP_FRAME | F_IP_ARG + * because @func_addr. + */ + WARN_ON_ONCE((flags & BPF_TRAMP_F_INDIRECT) && + (flags & ~(BPF_TRAMP_F_INDIRECT | BPF_TRAMP_F_RET_FENTRY_RET))); + /* extra registers for struct arguments */ - for (i = 0; i < m->nr_args; i++) + for (i = 0; i < m->nr_args; i++) { if (m->arg_flags[i] & BTF_FMODEL_STRUCT_ARG) nr_regs += (m->arg_size[i] + 7) / 8 - 1; + } /* x86-64 supports up to MAX_BPF_FUNC_ARGS arguments. 1-6 * are passed through regs, the remains are through stack. @@ -2521,22 +2601,29 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i orig_call += X86_PATCH_SIZE; } - prog = image; + prog = rw_image; - EMIT_ENDBR(); - /* - * This is the direct-call trampoline, as such it needs accounting - * for the __fentry__ call. - */ - x86_call_depth_emit_accounting(&prog, NULL); + if (flags & BPF_TRAMP_F_INDIRECT) { + /* + * Indirect call for bpf_struct_ops + */ + emit_cfi(&prog, cfi_get_func_hash(func_addr)); + } else { + /* + * Direct-call fentry stub, as such it needs accounting for the + * __fentry__ call. + */ + x86_call_depth_emit_accounting(&prog, NULL); + } EMIT1(0x55); /* push rbp */ EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */ - if (!is_imm8(stack_size)) + if (!is_imm8(stack_size)) { /* sub rsp, stack_size */ EMIT3_off32(0x48, 0x81, 0xEC, stack_size); - else + } else { /* sub rsp, stack_size */ EMIT4(0x48, 0x83, 0xEC, stack_size); + } if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) EMIT1(0x50); /* push rax */ /* mov QWORD PTR [rbp - rbx_off], rbx */ @@ -2563,16 +2650,18 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i if (flags & BPF_TRAMP_F_CALL_ORIG) { /* arg1: mov rdi, im */ emit_mov_imm64(&prog, BPF_REG_1, (long) im >> 32, (u32) (long) im); - if (emit_rsb_call(&prog, __bpf_tramp_enter, prog)) { + if (emit_rsb_call(&prog, __bpf_tramp_enter, + image + (prog - (u8 *)rw_image))) { ret = -EINVAL; goto cleanup; } } - if (fentry->nr_links) + if (fentry->nr_links) { if (invoke_bpf(m, &prog, fentry, regs_off, run_ctx_off, - flags & BPF_TRAMP_F_RET_FENTRY_RET)) + flags & BPF_TRAMP_F_RET_FENTRY_RET, image, rw_image)) return -EINVAL; + } if (fmod_ret->nr_links) { branches = kcalloc(fmod_ret->nr_links, sizeof(u8 *), @@ -2581,7 +2670,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i return -ENOMEM; if (invoke_bpf_mod_ret(m, &prog, fmod_ret, regs_off, - run_ctx_off, branches)) { + run_ctx_off, branches, image, rw_image)) { ret = -EINVAL; goto cleanup; } @@ -2591,25 +2680,26 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i restore_regs(m, &prog, regs_off); save_args(m, &prog, arg_stack_off, true); - if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) + if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) { /* Before calling the original function, restore the * tail_call_cnt from stack to rax. */ RESTORE_TAIL_CALL_CNT(stack_size); + } if (flags & BPF_TRAMP_F_ORIG_STACK) { emit_ldx(&prog, BPF_DW, BPF_REG_6, BPF_REG_FP, 8); EMIT2(0xff, 0xd3); /* call *rbx */ } else { /* call original function */ - if (emit_rsb_call(&prog, orig_call, prog)) { + if (emit_rsb_call(&prog, orig_call, image + (prog - (u8 *)rw_image))) { ret = -EINVAL; goto cleanup; } } /* remember return value in a stack for bpf prog to access */ emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8); - im->ip_after_call = prog; + im->ip_after_call = image + (prog - (u8 *)rw_image); memcpy(prog, x86_nops[5], X86_PATCH_SIZE); prog += X86_PATCH_SIZE; } @@ -2624,16 +2714,19 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i /* Update the branches saved in invoke_bpf_mod_ret with the * aligned address of do_fexit. */ - for (i = 0; i < fmod_ret->nr_links; i++) - emit_cond_near_jump(&branches[i], prog, branches[i], - X86_JNE); + for (i = 0; i < fmod_ret->nr_links; i++) { + emit_cond_near_jump(&branches[i], image + (prog - (u8 *)rw_image), + image + (branches[i] - (u8 *)rw_image), X86_JNE); + } } - if (fexit->nr_links) - if (invoke_bpf(m, &prog, fexit, regs_off, run_ctx_off, false)) { + if (fexit->nr_links) { + if (invoke_bpf(m, &prog, fexit, regs_off, run_ctx_off, + false, image, rw_image)) { ret = -EINVAL; goto cleanup; } + } if (flags & BPF_TRAMP_F_RESTORE_REGS) restore_regs(m, &prog, regs_off); @@ -2643,18 +2736,19 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i * restored to R0. */ if (flags & BPF_TRAMP_F_CALL_ORIG) { - im->ip_epilogue = prog; + im->ip_epilogue = image + (prog - (u8 *)rw_image); /* arg1: mov rdi, im */ emit_mov_imm64(&prog, BPF_REG_1, (long) im >> 32, (u32) (long) im); - if (emit_rsb_call(&prog, __bpf_tramp_exit, prog)) { + if (emit_rsb_call(&prog, __bpf_tramp_exit, image + (prog - (u8 *)rw_image))) { ret = -EINVAL; goto cleanup; } - } else if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) + } else if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) { /* Before running the original function, restore the * tail_call_cnt from stack to rax. */ RESTORE_TAIL_CALL_CNT(stack_size); + } /* restore return value of orig_call or fentry prog back into RAX */ if (save_ret) @@ -2662,22 +2756,94 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i emit_ldx(&prog, BPF_DW, BPF_REG_6, BPF_REG_FP, -rbx_off); EMIT1(0xC9); /* leave */ - if (flags & BPF_TRAMP_F_SKIP_FRAME) + if (flags & BPF_TRAMP_F_SKIP_FRAME) { /* skip our return address and return to parent */ EMIT4(0x48, 0x83, 0xC4, 8); /* add rsp, 8 */ - emit_return(&prog, prog); + } + emit_return(&prog, image + (prog - (u8 *)rw_image)); /* Make sure the trampoline generation logic doesn't overflow */ - if (WARN_ON_ONCE(prog > (u8 *)image_end - BPF_INSN_SAFETY)) { + if (WARN_ON_ONCE(prog > (u8 *)rw_image_end - BPF_INSN_SAFETY)) { ret = -EFAULT; goto cleanup; } - ret = prog - (u8 *)image; + ret = prog - (u8 *)rw_image + BPF_INSN_SAFETY; cleanup: kfree(branches); return ret; } +void *arch_alloc_bpf_trampoline(unsigned int size) +{ + return bpf_prog_pack_alloc(size, jit_fill_hole); +} + +void arch_free_bpf_trampoline(void *image, unsigned int size) +{ + bpf_prog_pack_free(image, size); +} + +void arch_protect_bpf_trampoline(void *image, unsigned int size) +{ +} + +void arch_unprotect_bpf_trampoline(void *image, unsigned int size) +{ +} + +int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end, + const struct btf_func_model *m, u32 flags, + struct bpf_tramp_links *tlinks, + void *func_addr) +{ + void *rw_image, *tmp; + int ret; + u32 size = image_end - image; + + /* rw_image doesn't need to be in module memory range, so we can + * use kvmalloc. + */ + rw_image = kvmalloc(size, GFP_KERNEL); + if (!rw_image) + return -ENOMEM; + + ret = __arch_prepare_bpf_trampoline(im, rw_image, rw_image + size, image, m, + flags, tlinks, func_addr); + if (ret < 0) + goto out; + + tmp = bpf_arch_text_copy(image, rw_image, size); + if (IS_ERR(tmp)) + ret = PTR_ERR(tmp); +out: + kvfree(rw_image); + return ret; +} + +int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, + struct bpf_tramp_links *tlinks, void *func_addr) +{ + struct bpf_tramp_image im; + void *image; + int ret; + + /* Allocate a temporary buffer for __arch_prepare_bpf_trampoline(). + * This will NOT cause fragmentation in direct map, as we do not + * call set_memory_*() on this buffer. + * + * We cannot use kvmalloc here, because we need image to be in + * module memory range. + */ + image = bpf_jit_alloc_exec(PAGE_SIZE); + if (!image) + return -ENOMEM; + + ret = __arch_prepare_bpf_trampoline(&im, image, image + PAGE_SIZE, image, + m, flags, tlinks, func_addr); + bpf_jit_free_exec(image); + return ret; +} + static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs, u8 *image, u8 *buf) { u8 *jg_reloc, *prog = *pprog; @@ -2935,9 +3101,16 @@ out_image: jit_data->header = header; jit_data->rw_header = rw_header; } - prog->bpf_func = (void *)image; + /* + * ctx.prog_offset is used when CFI preambles put code *before* + * the function. See emit_cfi(). For FineIBT specifically this code + * can also be executed and bpf_prog_kallsyms_add() will + * generate an additional symbol to cover this, hence also + * decrement proglen. + */ + prog->bpf_func = (void *)image + cfi_get_offset(); prog->jited = 1; - prog->jited_len = proglen; + prog->jited_len = proglen - cfi_get_offset(); } else { prog = orig_prog; } @@ -2992,6 +3165,7 @@ void bpf_jit_free(struct bpf_prog *prog) kvfree(jit_data->addrs); kfree(jit_data); } + prog->bpf_func = (void *)prog->bpf_func - cfi_get_offset(); hdr = bpf_jit_binary_pack_hdr(prog); bpf_jit_binary_pack_free(hdr, NULL); WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(prog)); diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c index fe17c7f98e81..6d07693c6b9f 100644 --- a/drivers/media/rc/bpf-lirc.c +++ b/drivers/media/rc/bpf-lirc.c @@ -110,7 +110,7 @@ lirc_mode2_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_get_prandom_u32: return &bpf_get_prandom_u32_proto; case BPF_FUNC_trace_printk: - if (perfmon_capable()) + if (bpf_token_capable(prog->aux->token, CAP_PERFMON)) return bpf_get_trace_printk_proto(); fallthrough; default: diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 50304e4a4fb0..2defac6d9168 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -1008,4 +1008,6 @@ static inline void ice_clear_rdma_cap(struct ice_pf *pf) set_bit(ICE_FLAG_UNPLUG_AUX_DEV, pf->flags); clear_bit(ICE_FLAG_RDMA_ENA, pf->flags); } + +extern const struct xdp_metadata_ops ice_xdp_md_ops; #endif /* _ICE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index edad5f9ab16c..b25b7f415965 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -527,6 +527,19 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring) return 0; } +static void ice_xsk_pool_fill_cb(struct ice_rx_ring *ring) +{ + void *ctx_ptr = &ring->pkt_ctx; + struct xsk_cb_desc desc = {}; + + XSK_CHECK_PRIV_TYPE(struct ice_xdp_buff); + desc.src = &ctx_ptr; + desc.off = offsetof(struct ice_xdp_buff, pkt_ctx) - + sizeof(struct xdp_buff); + desc.bytes = sizeof(ctx_ptr); + xsk_pool_fill_cb(ring->xsk_pool, &desc); +} + /** * ice_vsi_cfg_rxq - Configure an Rx queue * @ring: the ring being configured @@ -561,6 +574,7 @@ int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) if (err) return err; xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq); + ice_xsk_pool_fill_cb(ring); dev_info(dev, "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n", ring->q_index); @@ -583,6 +597,7 @@ int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) xdp_init_buff(&ring->xdp, ice_rx_pg_size(ring) / 2, &ring->xdp_rxq); ring->xdp.data = NULL; + ring->xdp_ext.pkt_ctx = &ring->pkt_ctx; err = ice_setup_rx_ctx(ring); if (err) { dev_err(dev, "ice_setup_rx_ctx failed for RxQ %d, err %d\n", diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h index 89f986a75cc8..d384ddfcb83e 100644 --- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h +++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h @@ -673,6 +673,212 @@ struct ice_tlan_ctx { * Use the enum ice_rx_l2_ptype to decode the packet type * ENDIF */ +#define ICE_PTYPES \ + /* L2 Packet types */ \ + ICE_PTT_UNUSED_ENTRY(0), \ + ICE_PTT(1, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), \ + ICE_PTT_UNUSED_ENTRY(2), \ + ICE_PTT_UNUSED_ENTRY(3), \ + ICE_PTT_UNUSED_ENTRY(4), \ + ICE_PTT_UNUSED_ENTRY(5), \ + ICE_PTT(6, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE), \ + ICE_PTT(7, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE), \ + ICE_PTT_UNUSED_ENTRY(8), \ + ICE_PTT_UNUSED_ENTRY(9), \ + ICE_PTT(10, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE), \ + ICE_PTT(11, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE), \ + ICE_PTT_UNUSED_ENTRY(12), \ + ICE_PTT_UNUSED_ENTRY(13), \ + ICE_PTT_UNUSED_ENTRY(14), \ + ICE_PTT_UNUSED_ENTRY(15), \ + ICE_PTT_UNUSED_ENTRY(16), \ + ICE_PTT_UNUSED_ENTRY(17), \ + ICE_PTT_UNUSED_ENTRY(18), \ + ICE_PTT_UNUSED_ENTRY(19), \ + ICE_PTT_UNUSED_ENTRY(20), \ + ICE_PTT_UNUSED_ENTRY(21), \ + \ + /* Non Tunneled IPv4 */ \ + ICE_PTT(22, IP, IPV4, FRG, NONE, NONE, NOF, NONE, PAY3), \ + ICE_PTT(23, IP, IPV4, NOF, NONE, NONE, NOF, NONE, PAY3), \ + ICE_PTT(24, IP, IPV4, NOF, NONE, NONE, NOF, UDP, PAY4), \ + ICE_PTT_UNUSED_ENTRY(25), \ + ICE_PTT(26, IP, IPV4, NOF, NONE, NONE, NOF, TCP, PAY4), \ + ICE_PTT(27, IP, IPV4, NOF, NONE, NONE, NOF, SCTP, PAY4), \ + ICE_PTT(28, IP, IPV4, NOF, NONE, NONE, NOF, ICMP, PAY4), \ + \ + /* IPv4 --> IPv4 */ \ + ICE_PTT(29, IP, IPV4, NOF, IP_IP, IPV4, FRG, NONE, PAY3), \ + ICE_PTT(30, IP, IPV4, NOF, IP_IP, IPV4, NOF, NONE, PAY3), \ + ICE_PTT(31, IP, IPV4, NOF, IP_IP, IPV4, NOF, UDP, PAY4), \ + ICE_PTT_UNUSED_ENTRY(32), \ + ICE_PTT(33, IP, IPV4, NOF, IP_IP, IPV4, NOF, TCP, PAY4), \ + ICE_PTT(34, IP, IPV4, NOF, IP_IP, IPV4, NOF, SCTP, PAY4), \ + ICE_PTT(35, IP, IPV4, NOF, IP_IP, IPV4, NOF, ICMP, PAY4), \ + \ + /* IPv4 --> IPv6 */ \ + ICE_PTT(36, IP, IPV4, NOF, IP_IP, IPV6, FRG, NONE, PAY3), \ + ICE_PTT(37, IP, IPV4, NOF, IP_IP, IPV6, NOF, NONE, PAY3), \ + ICE_PTT(38, IP, IPV4, NOF, IP_IP, IPV6, NOF, UDP, PAY4), \ + ICE_PTT_UNUSED_ENTRY(39), \ + ICE_PTT(40, IP, IPV4, NOF, IP_IP, IPV6, NOF, TCP, PAY4), \ + ICE_PTT(41, IP, IPV4, NOF, IP_IP, IPV6, NOF, SCTP, PAY4), \ + ICE_PTT(42, IP, IPV4, NOF, IP_IP, IPV6, NOF, ICMP, PAY4), \ + \ + /* IPv4 --> GRE/NAT */ \ + ICE_PTT(43, IP, IPV4, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3), \ + \ + /* IPv4 --> GRE/NAT --> IPv4 */ \ + ICE_PTT(44, IP, IPV4, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3), \ + ICE_PTT(45, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3), \ + ICE_PTT(46, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4), \ + ICE_PTT_UNUSED_ENTRY(47), \ + ICE_PTT(48, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4), \ + ICE_PTT(49, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4), \ + ICE_PTT(50, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4), \ + \ + /* IPv4 --> GRE/NAT --> IPv6 */ \ + ICE_PTT(51, IP, IPV4, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3), \ + ICE_PTT(52, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3), \ + ICE_PTT(53, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4), \ + ICE_PTT_UNUSED_ENTRY(54), \ + ICE_PTT(55, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4), \ + ICE_PTT(56, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4), \ + ICE_PTT(57, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4), \ + \ + /* IPv4 --> GRE/NAT --> MAC */ \ + ICE_PTT(58, IP, IPV4, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3), \ + \ + /* IPv4 --> GRE/NAT --> MAC --> IPv4 */ \ + ICE_PTT(59, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3), \ + ICE_PTT(60, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3), \ + ICE_PTT(61, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4), \ + ICE_PTT_UNUSED_ENTRY(62), \ + ICE_PTT(63, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4), \ + ICE_PTT(64, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4), \ + ICE_PTT(65, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4), \ + \ + /* IPv4 --> GRE/NAT -> MAC --> IPv6 */ \ + ICE_PTT(66, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3), \ + ICE_PTT(67, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3), \ + ICE_PTT(68, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4), \ + ICE_PTT_UNUSED_ENTRY(69), \ + ICE_PTT(70, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4), \ + ICE_PTT(71, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4), \ + ICE_PTT(72, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4), \ + \ + /* IPv4 --> GRE/NAT --> MAC/VLAN */ \ + ICE_PTT(73, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3), \ + \ + /* IPv4 ---> GRE/NAT -> MAC/VLAN --> IPv4 */ \ + ICE_PTT(74, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3), \ + ICE_PTT(75, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3), \ + ICE_PTT(76, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4), \ + ICE_PTT_UNUSED_ENTRY(77), \ + ICE_PTT(78, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4), \ + ICE_PTT(79, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4), \ + ICE_PTT(80, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4), \ + \ + /* IPv4 -> GRE/NAT -> MAC/VLAN --> IPv6 */ \ + ICE_PTT(81, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3), \ + ICE_PTT(82, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3), \ + ICE_PTT(83, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4), \ + ICE_PTT_UNUSED_ENTRY(84), \ + ICE_PTT(85, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4), \ + ICE_PTT(86, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4), \ + ICE_PTT(87, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4), \ + \ + /* Non Tunneled IPv6 */ \ + ICE_PTT(88, IP, IPV6, FRG, NONE, NONE, NOF, NONE, PAY3), \ + ICE_PTT(89, IP, IPV6, NOF, NONE, NONE, NOF, NONE, PAY3), \ + ICE_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP, PAY4), \ + ICE_PTT_UNUSED_ENTRY(91), \ + ICE_PTT(92, IP, IPV6, NOF, NONE, NONE, NOF, TCP, PAY4), \ + ICE_PTT(93, IP, IPV6, NOF, NONE, NONE, NOF, SCTP, PAY4), \ + ICE_PTT(94, IP, IPV6, NOF, NONE, NONE, NOF, ICMP, PAY4), \ + \ + /* IPv6 --> IPv4 */ \ + ICE_PTT(95, IP, IPV6, NOF, IP_IP, IPV4, FRG, NONE, PAY3), \ + ICE_PTT(96, IP, IPV6, NOF, IP_IP, IPV4, NOF, NONE, PAY3), \ + ICE_PTT(97, IP, IPV6, NOF, IP_IP, IPV4, NOF, UDP, PAY4), \ + ICE_PTT_UNUSED_ENTRY(98), \ + ICE_PTT(99, IP, IPV6, NOF, IP_IP, IPV4, NOF, TCP, PAY4), \ + ICE_PTT(100, IP, IPV6, NOF, IP_IP, IPV4, NOF, SCTP, PAY4), \ + ICE_PTT(101, IP, IPV6, NOF, IP_IP, IPV4, NOF, ICMP, PAY4), \ + \ + /* IPv6 --> IPv6 */ \ + ICE_PTT(102, IP, IPV6, NOF, IP_IP, IPV6, FRG, NONE, PAY3), \ + ICE_PTT(103, IP, IPV6, NOF, IP_IP, IPV6, NOF, NONE, PAY3), \ + ICE_PTT(104, IP, IPV6, NOF, IP_IP, IPV6, NOF, UDP, PAY4), \ + ICE_PTT_UNUSED_ENTRY(105), \ + ICE_PTT(106, IP, IPV6, NOF, IP_IP, IPV6, NOF, TCP, PAY4), \ + ICE_PTT(107, IP, IPV6, NOF, IP_IP, IPV6, NOF, SCTP, PAY4), \ + ICE_PTT(108, IP, IPV6, NOF, IP_IP, IPV6, NOF, ICMP, PAY4), \ + \ + /* IPv6 --> GRE/NAT */ \ + ICE_PTT(109, IP, IPV6, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3), \ + \ + /* IPv6 --> GRE/NAT -> IPv4 */ \ + ICE_PTT(110, IP, IPV6, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3), \ + ICE_PTT(111, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3), \ + ICE_PTT(112, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4), \ + ICE_PTT_UNUSED_ENTRY(113), \ + ICE_PTT(114, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4), \ + ICE_PTT(115, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4), \ + ICE_PTT(116, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4), \ + \ + /* IPv6 --> GRE/NAT -> IPv6 */ \ + ICE_PTT(117, IP, IPV6, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3), \ + ICE_PTT(118, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3), \ + ICE_PTT(119, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4), \ + ICE_PTT_UNUSED_ENTRY(120), \ + ICE_PTT(121, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4), \ + ICE_PTT(122, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4), \ + ICE_PTT(123, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4), \ + \ + /* IPv6 --> GRE/NAT -> MAC */ \ + ICE_PTT(124, IP, IPV6, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3), \ + \ + /* IPv6 --> GRE/NAT -> MAC -> IPv4 */ \ + ICE_PTT(125, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3), \ + ICE_PTT(126, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3), \ + ICE_PTT(127, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4), \ + ICE_PTT_UNUSED_ENTRY(128), \ + ICE_PTT(129, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4), \ + ICE_PTT(130, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4), \ + ICE_PTT(131, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4), \ + \ + /* IPv6 --> GRE/NAT -> MAC -> IPv6 */ \ + ICE_PTT(132, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3), \ + ICE_PTT(133, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3), \ + ICE_PTT(134, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4), \ + ICE_PTT_UNUSED_ENTRY(135), \ + ICE_PTT(136, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4), \ + ICE_PTT(137, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4), \ + ICE_PTT(138, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4), \ + \ + /* IPv6 --> GRE/NAT -> MAC/VLAN */ \ + ICE_PTT(139, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3), \ + \ + /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv4 */ \ + ICE_PTT(140, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3), \ + ICE_PTT(141, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3), \ + ICE_PTT(142, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4), \ + ICE_PTT_UNUSED_ENTRY(143), \ + ICE_PTT(144, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4), \ + ICE_PTT(145, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4), \ + ICE_PTT(146, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4), \ + \ + /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv6 */ \ + ICE_PTT(147, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3), \ + ICE_PTT(148, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3), \ + ICE_PTT(149, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4), \ + ICE_PTT_UNUSED_ENTRY(150), \ + ICE_PTT(151, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4), \ + ICE_PTT(152, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4), \ + ICE_PTT(153, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4), + +#define ICE_NUM_DEFINED_PTYPES 154 /* macro to make the table lines short, use explicit indexing with [PTYPE] */ #define ICE_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\ @@ -695,212 +901,10 @@ struct ice_tlan_ctx { /* Lookup table mapping in the 10-bit HW PTYPE to the bit field for decoding */ static const struct ice_rx_ptype_decoded ice_ptype_lkup[BIT(10)] = { - /* L2 Packet types */ - ICE_PTT_UNUSED_ENTRY(0), - ICE_PTT(1, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), - ICE_PTT_UNUSED_ENTRY(2), - ICE_PTT_UNUSED_ENTRY(3), - ICE_PTT_UNUSED_ENTRY(4), - ICE_PTT_UNUSED_ENTRY(5), - ICE_PTT(6, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE), - ICE_PTT(7, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE), - ICE_PTT_UNUSED_ENTRY(8), - ICE_PTT_UNUSED_ENTRY(9), - ICE_PTT(10, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE), - ICE_PTT(11, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE), - ICE_PTT_UNUSED_ENTRY(12), - ICE_PTT_UNUSED_ENTRY(13), - ICE_PTT_UNUSED_ENTRY(14), - ICE_PTT_UNUSED_ENTRY(15), - ICE_PTT_UNUSED_ENTRY(16), - ICE_PTT_UNUSED_ENTRY(17), - ICE_PTT_UNUSED_ENTRY(18), - ICE_PTT_UNUSED_ENTRY(19), - ICE_PTT_UNUSED_ENTRY(20), - ICE_PTT_UNUSED_ENTRY(21), - - /* Non Tunneled IPv4 */ - ICE_PTT(22, IP, IPV4, FRG, NONE, NONE, NOF, NONE, PAY3), - ICE_PTT(23, IP, IPV4, NOF, NONE, NONE, NOF, NONE, PAY3), - ICE_PTT(24, IP, IPV4, NOF, NONE, NONE, NOF, UDP, PAY4), - ICE_PTT_UNUSED_ENTRY(25), - ICE_PTT(26, IP, IPV4, NOF, NONE, NONE, NOF, TCP, PAY4), - ICE_PTT(27, IP, IPV4, NOF, NONE, NONE, NOF, SCTP, PAY4), - ICE_PTT(28, IP, IPV4, NOF, NONE, NONE, NOF, ICMP, PAY4), - - /* IPv4 --> IPv4 */ - ICE_PTT(29, IP, IPV4, NOF, IP_IP, IPV4, FRG, NONE, PAY3), - ICE_PTT(30, IP, IPV4, NOF, IP_IP, IPV4, NOF, NONE, PAY3), - ICE_PTT(31, IP, IPV4, NOF, IP_IP, IPV4, NOF, UDP, PAY4), - ICE_PTT_UNUSED_ENTRY(32), - ICE_PTT(33, IP, IPV4, NOF, IP_IP, IPV4, NOF, TCP, PAY4), - ICE_PTT(34, IP, IPV4, NOF, IP_IP, IPV4, NOF, SCTP, PAY4), - ICE_PTT(35, IP, IPV4, NOF, IP_IP, IPV4, NOF, ICMP, PAY4), - - /* IPv4 --> IPv6 */ - ICE_PTT(36, IP, IPV4, NOF, IP_IP, IPV6, FRG, NONE, PAY3), - ICE_PTT(37, IP, IPV4, NOF, IP_IP, IPV6, NOF, NONE, PAY3), - ICE_PTT(38, IP, IPV4, NOF, IP_IP, IPV6, NOF, UDP, PAY4), - ICE_PTT_UNUSED_ENTRY(39), - ICE_PTT(40, IP, IPV4, NOF, IP_IP, IPV6, NOF, TCP, PAY4), - ICE_PTT(41, IP, IPV4, NOF, IP_IP, IPV6, NOF, SCTP, PAY4), - ICE_PTT(42, IP, IPV4, NOF, IP_IP, IPV6, NOF, ICMP, PAY4), - - /* IPv4 --> GRE/NAT */ - ICE_PTT(43, IP, IPV4, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3), - - /* IPv4 --> GRE/NAT --> IPv4 */ - ICE_PTT(44, IP, IPV4, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3), - ICE_PTT(45, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3), - ICE_PTT(46, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4), - ICE_PTT_UNUSED_ENTRY(47), - ICE_PTT(48, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4), - ICE_PTT(49, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4), - ICE_PTT(50, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4), - - /* IPv4 --> GRE/NAT --> IPv6 */ - ICE_PTT(51, IP, IPV4, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3), - ICE_PTT(52, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3), - ICE_PTT(53, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4), - ICE_PTT_UNUSED_ENTRY(54), - ICE_PTT(55, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4), - ICE_PTT(56, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4), - ICE_PTT(57, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4), - - /* IPv4 --> GRE/NAT --> MAC */ - ICE_PTT(58, IP, IPV4, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3), - - /* IPv4 --> GRE/NAT --> MAC --> IPv4 */ - ICE_PTT(59, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3), - ICE_PTT(60, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3), - ICE_PTT(61, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4), - ICE_PTT_UNUSED_ENTRY(62), - ICE_PTT(63, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4), - ICE_PTT(64, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4), - ICE_PTT(65, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4), - - /* IPv4 --> GRE/NAT -> MAC --> IPv6 */ - ICE_PTT(66, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3), - ICE_PTT(67, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3), - ICE_PTT(68, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4), - ICE_PTT_UNUSED_ENTRY(69), - ICE_PTT(70, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4), - ICE_PTT(71, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4), - ICE_PTT(72, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4), - - /* IPv4 --> GRE/NAT --> MAC/VLAN */ - ICE_PTT(73, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3), - - /* IPv4 ---> GRE/NAT -> MAC/VLAN --> IPv4 */ - ICE_PTT(74, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3), - ICE_PTT(75, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3), - ICE_PTT(76, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4), - ICE_PTT_UNUSED_ENTRY(77), - ICE_PTT(78, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4), - ICE_PTT(79, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4), - ICE_PTT(80, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4), - - /* IPv4 -> GRE/NAT -> MAC/VLAN --> IPv6 */ - ICE_PTT(81, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3), - ICE_PTT(82, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3), - ICE_PTT(83, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4), - ICE_PTT_UNUSED_ENTRY(84), - ICE_PTT(85, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4), - ICE_PTT(86, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4), - ICE_PTT(87, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4), - - /* Non Tunneled IPv6 */ - ICE_PTT(88, IP, IPV6, FRG, NONE, NONE, NOF, NONE, PAY3), - ICE_PTT(89, IP, IPV6, NOF, NONE, NONE, NOF, NONE, PAY3), - ICE_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP, PAY4), - ICE_PTT_UNUSED_ENTRY(91), - ICE_PTT(92, IP, IPV6, NOF, NONE, NONE, NOF, TCP, PAY4), - ICE_PTT(93, IP, IPV6, NOF, NONE, NONE, NOF, SCTP, PAY4), - ICE_PTT(94, IP, IPV6, NOF, NONE, NONE, NOF, ICMP, PAY4), - - /* IPv6 --> IPv4 */ - ICE_PTT(95, IP, IPV6, NOF, IP_IP, IPV4, FRG, NONE, PAY3), - ICE_PTT(96, IP, IPV6, NOF, IP_IP, IPV4, NOF, NONE, PAY3), - ICE_PTT(97, IP, IPV6, NOF, IP_IP, IPV4, NOF, UDP, PAY4), - ICE_PTT_UNUSED_ENTRY(98), - ICE_PTT(99, IP, IPV6, NOF, IP_IP, IPV4, NOF, TCP, PAY4), - ICE_PTT(100, IP, IPV6, NOF, IP_IP, IPV4, NOF, SCTP, PAY4), - ICE_PTT(101, IP, IPV6, NOF, IP_IP, IPV4, NOF, ICMP, PAY4), - - /* IPv6 --> IPv6 */ - ICE_PTT(102, IP, IPV6, NOF, IP_IP, IPV6, FRG, NONE, PAY3), - ICE_PTT(103, IP, IPV6, NOF, IP_IP, IPV6, NOF, NONE, PAY3), - ICE_PTT(104, IP, IPV6, NOF, IP_IP, IPV6, NOF, UDP, PAY4), - ICE_PTT_UNUSED_ENTRY(105), - ICE_PTT(106, IP, IPV6, NOF, IP_IP, IPV6, NOF, TCP, PAY4), - ICE_PTT(107, IP, IPV6, NOF, IP_IP, IPV6, NOF, SCTP, PAY4), - ICE_PTT(108, IP, IPV6, NOF, IP_IP, IPV6, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT */ - ICE_PTT(109, IP, IPV6, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3), - - /* IPv6 --> GRE/NAT -> IPv4 */ - ICE_PTT(110, IP, IPV6, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3), - ICE_PTT(111, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3), - ICE_PTT(112, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4), - ICE_PTT_UNUSED_ENTRY(113), - ICE_PTT(114, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4), - ICE_PTT(115, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4), - ICE_PTT(116, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT -> IPv6 */ - ICE_PTT(117, IP, IPV6, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3), - ICE_PTT(118, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3), - ICE_PTT(119, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4), - ICE_PTT_UNUSED_ENTRY(120), - ICE_PTT(121, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4), - ICE_PTT(122, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4), - ICE_PTT(123, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT -> MAC */ - ICE_PTT(124, IP, IPV6, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3), - - /* IPv6 --> GRE/NAT -> MAC -> IPv4 */ - ICE_PTT(125, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3), - ICE_PTT(126, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3), - ICE_PTT(127, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4), - ICE_PTT_UNUSED_ENTRY(128), - ICE_PTT(129, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4), - ICE_PTT(130, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4), - ICE_PTT(131, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT -> MAC -> IPv6 */ - ICE_PTT(132, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3), - ICE_PTT(133, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3), - ICE_PTT(134, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4), - ICE_PTT_UNUSED_ENTRY(135), - ICE_PTT(136, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4), - ICE_PTT(137, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4), - ICE_PTT(138, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT -> MAC/VLAN */ - ICE_PTT(139, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3), - - /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv4 */ - ICE_PTT(140, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3), - ICE_PTT(141, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3), - ICE_PTT(142, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4), - ICE_PTT_UNUSED_ENTRY(143), - ICE_PTT(144, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4), - ICE_PTT(145, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4), - ICE_PTT(146, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv6 */ - ICE_PTT(147, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3), - ICE_PTT(148, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3), - ICE_PTT(149, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4), - ICE_PTT_UNUSED_ENTRY(150), - ICE_PTT(151, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4), - ICE_PTT(152, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4), - ICE_PTT(153, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4), + ICE_PTYPES /* unused entries */ - [154 ... 1023] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 } + [ICE_NUM_DEFINED_PTYPES ... 1023] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 } }; static inline struct ice_rx_ptype_decoded ice_decode_rx_desc_ptype(u16 ptype) diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 9b0c04d595ce..b97d116650be 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -3426,6 +3426,7 @@ static void ice_set_ops(struct ice_vsi *vsi) netdev->netdev_ops = &ice_netdev_ops; netdev->udp_tunnel_nic_info = &pf->hw.udp_tunnel_nic; + netdev->xdp_metadata_ops = &ice_xdp_md_ops; ice_set_ethtool_ops(netdev); if (vsi->type != ICE_VSI_PF) @@ -6094,6 +6095,23 @@ ice_fix_features(struct net_device *netdev, netdev_features_t features) } /** + * ice_set_rx_rings_vlan_proto - update rings with new stripped VLAN proto + * @vsi: PF's VSI + * @vlan_ethertype: VLAN ethertype (802.1Q or 802.1ad) in network byte order + * + * Store current stripped VLAN proto in ring packet context, + * so it can be accessed more efficiently by packet processing code. + */ +static void +ice_set_rx_rings_vlan_proto(struct ice_vsi *vsi, __be16 vlan_ethertype) +{ + u16 i; + + ice_for_each_alloc_rxq(vsi, i) + vsi->rx_rings[i]->pkt_ctx.vlan_proto = vlan_ethertype; +} + +/** * ice_set_vlan_offload_features - set VLAN offload features for the PF VSI * @vsi: PF's VSI * @features: features used to determine VLAN offload settings @@ -6135,6 +6153,9 @@ ice_set_vlan_offload_features(struct ice_vsi *vsi, netdev_features_t features) if (strip_err || insert_err) return -EIO; + ice_set_rx_rings_vlan_proto(vsi, enable_stripping ? + htons(vlan_ethertype) : 0); + return 0; } diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index e9e59f4b5580..239cf8a2ee80 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -2129,30 +2129,26 @@ int ice_ptp_set_ts_config(struct ice_pf *pf, struct ifreq *ifr) } /** - * ice_ptp_rx_hwtstamp - Check for an Rx timestamp - * @rx_ring: Ring to get the VSI info + * ice_ptp_get_rx_hwts - Get packet Rx timestamp in ns * @rx_desc: Receive descriptor - * @skb: Particular skb to send timestamp with + * @pkt_ctx: Packet context to get the cached time * * The driver receives a notification in the receive descriptor with timestamp. - * The timestamp is in ns, so we must convert the result first. */ -void -ice_ptp_rx_hwtstamp(struct ice_rx_ring *rx_ring, - union ice_32b_rx_flex_desc *rx_desc, struct sk_buff *skb) +u64 ice_ptp_get_rx_hwts(const union ice_32b_rx_flex_desc *rx_desc, + const struct ice_pkt_ctx *pkt_ctx) { - struct skb_shared_hwtstamps *hwtstamps; u64 ts_ns, cached_time; u32 ts_high; if (!(rx_desc->wb.time_stamp_low & ICE_PTP_TS_VALID)) - return; + return 0; - cached_time = READ_ONCE(rx_ring->cached_phctime); + cached_time = READ_ONCE(pkt_ctx->cached_phctime); /* Do not report a timestamp if we don't have a cached PHC time */ if (!cached_time) - return; + return 0; /* Use ice_ptp_extend_32b_ts directly, using the ring-specific cached * PHC value, rather than accessing the PF. This also allows us to @@ -2163,9 +2159,7 @@ ice_ptp_rx_hwtstamp(struct ice_rx_ring *rx_ring, ts_high = le32_to_cpu(rx_desc->wb.flex_ts.ts_high); ts_ns = ice_ptp_extend_32b_ts(cached_time, ts_high); - hwtstamps = skb_hwtstamps(skb); - memset(hwtstamps, 0, sizeof(*hwtstamps)); - hwtstamps->hwtstamp = ns_to_ktime(ts_ns); + return ts_ns; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h index d79281061409..032653a7a133 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp.h @@ -298,9 +298,8 @@ void ice_ptp_extts_event(struct ice_pf *pf); s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb); enum ice_tx_tstamp_work ice_ptp_process_ts(struct ice_pf *pf); -void -ice_ptp_rx_hwtstamp(struct ice_rx_ring *rx_ring, - union ice_32b_rx_flex_desc *rx_desc, struct sk_buff *skb); +u64 ice_ptp_get_rx_hwts(const union ice_32b_rx_flex_desc *rx_desc, + const struct ice_pkt_ctx *pkt_ctx); void ice_ptp_reset(struct ice_pf *pf); void ice_ptp_prepare_for_reset(struct ice_pf *pf); void ice_ptp_init(struct ice_pf *pf); @@ -329,9 +328,14 @@ static inline bool ice_ptp_process_ts(struct ice_pf *pf) { return true; } -static inline void -ice_ptp_rx_hwtstamp(struct ice_rx_ring *rx_ring, - union ice_32b_rx_flex_desc *rx_desc, struct sk_buff *skb) { } + +static inline u64 +ice_ptp_get_rx_hwts(const union ice_32b_rx_flex_desc *rx_desc, + const struct ice_pkt_ctx *pkt_ctx) +{ + return 0; +} + static inline void ice_ptp_reset(struct ice_pf *pf) { } static inline void ice_ptp_prepare_for_reset(struct ice_pf *pf) { } static inline void ice_ptp_init(struct ice_pf *pf) { } diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 9e97ea863068..59617f055e35 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -557,13 +557,14 @@ ice_rx_frame_truesize(struct ice_rx_ring *rx_ring, const unsigned int size) * @xdp_prog: XDP program to run * @xdp_ring: ring to be used for XDP_TX action * @rx_buf: Rx buffer to store the XDP action + * @eop_desc: Last descriptor in packet to read metadata from * * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR} */ static void ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring, - struct ice_rx_buf *rx_buf) + struct ice_rx_buf *rx_buf, union ice_32b_rx_flex_desc *eop_desc) { unsigned int ret = ICE_XDP_PASS; u32 act; @@ -571,6 +572,8 @@ ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, if (!xdp_prog) goto exit; + ice_xdp_meta_set_desc(xdp, eop_desc); + act = bpf_prog_run_xdp(xdp_prog, xdp); switch (act) { case XDP_PASS: @@ -1180,8 +1183,7 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) struct sk_buff *skb; unsigned int size; u16 stat_err_bits; - u16 vlan_tag = 0; - u16 rx_ptype; + u16 vlan_tci; /* get the Rx desc from Rx ring based on 'next_to_clean' */ rx_desc = ICE_RX_DESC(rx_ring, ntc); @@ -1241,7 +1243,7 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) if (ice_is_non_eop(rx_ring, rx_desc)) continue; - ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_buf); + ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_buf, rx_desc); if (rx_buf->act == ICE_XDP_PASS) goto construct_skb; total_rx_bytes += xdp_get_buff_len(xdp); @@ -1276,7 +1278,7 @@ construct_skb: continue; } - vlan_tag = ice_get_vlan_tag_from_rx_desc(rx_desc); + vlan_tci = ice_get_vlan_tci(rx_desc); /* pad the skb if needed, to make a valid ethernet frame */ if (eth_skb_pad(skb)) @@ -1286,14 +1288,11 @@ construct_skb: total_rx_bytes += skb->len; /* populate checksum, VLAN, and protocol */ - rx_ptype = le16_to_cpu(rx_desc->wb.ptype_flex_flags0) & - ICE_RX_FLEX_DESC_PTYPE_M; - - ice_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype); + ice_process_skb_fields(rx_ring, rx_desc, skb); ice_trace(clean_rx_irq_indicate, rx_ring, rx_desc, skb); /* send completed skb up the stack */ - ice_receive_skb(rx_ring, skb, vlan_tag); + ice_receive_skb(rx_ring, skb, vlan_tci); /* update budget accounting */ total_rx_pkts++; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index daf7b9dbb143..b3379ff73674 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -257,6 +257,20 @@ enum ice_rx_dtype { ICE_RX_DTYPE_SPLIT_ALWAYS = 2, }; +struct ice_pkt_ctx { + u64 cached_phctime; + __be16 vlan_proto; +}; + +struct ice_xdp_buff { + struct xdp_buff xdp_buff; + const union ice_32b_rx_flex_desc *eop_desc; + const struct ice_pkt_ctx *pkt_ctx; +}; + +/* Required for compatibility with xdp_buffs from xsk_pool */ +static_assert(offsetof(struct ice_xdp_buff, xdp_buff) == 0); + /* indices into GLINT_ITR registers */ #define ICE_RX_ITR ICE_IDX_ITR0 #define ICE_TX_ITR ICE_IDX_ITR1 @@ -298,7 +312,6 @@ enum ice_dynamic_itr { /* descriptor ring, associated with a VSI */ struct ice_rx_ring { /* CL1 - 1st cacheline starts here */ - struct ice_rx_ring *next; /* pointer to next ring in q_vector */ void *desc; /* Descriptor ring memory */ struct device *dev; /* Used for DMA mapping */ struct net_device *netdev; /* netdev ring maps to */ @@ -310,13 +323,24 @@ struct ice_rx_ring { u16 count; /* Number of descriptors */ u16 reg_idx; /* HW register index of the ring */ u16 next_to_alloc; - /* CL2 - 2nd cacheline starts here */ + union { struct ice_rx_buf *rx_buf; struct xdp_buff **xdp_buf; }; - struct xdp_buff xdp; + /* CL2 - 2nd cacheline starts here */ + union { + struct ice_xdp_buff xdp_ext; + struct xdp_buff xdp; + }; /* CL3 - 3rd cacheline starts here */ + union { + struct ice_pkt_ctx pkt_ctx; + struct { + u64 cached_phctime; + __be16 vlan_proto; + }; + }; struct bpf_prog *xdp_prog; u16 rx_offset; @@ -332,9 +356,9 @@ struct ice_rx_ring { /* CL4 - 4th cacheline starts here */ struct ice_channel *ch; struct ice_tx_ring *xdp_ring; + struct ice_rx_ring *next; /* pointer to next ring in q_vector */ struct xsk_buff_pool *xsk_pool; dma_addr_t dma; /* physical address of ring */ - u64 cached_phctime; u16 rx_buf_len; u8 dcb_tc; /* Traffic class of ring */ u8 ptp_rx; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c index 7e06373e14d9..839e5da24ad5 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c @@ -63,28 +63,42 @@ static enum pkt_hash_types ice_ptype_to_htype(u16 ptype) } /** - * ice_rx_hash - set the hash value in the skb + * ice_get_rx_hash - get RX hash value from descriptor + * @rx_desc: specific descriptor + * + * Returns hash, if present, 0 otherwise. + */ +static u32 ice_get_rx_hash(const union ice_32b_rx_flex_desc *rx_desc) +{ + const struct ice_32b_rx_flex_desc_nic *nic_mdid; + + if (unlikely(rx_desc->wb.rxdid != ICE_RXDID_FLEX_NIC)) + return 0; + + nic_mdid = (struct ice_32b_rx_flex_desc_nic *)rx_desc; + return le32_to_cpu(nic_mdid->rss_hash); +} + +/** + * ice_rx_hash_to_skb - set the hash value in the skb * @rx_ring: descriptor ring * @rx_desc: specific descriptor * @skb: pointer to current skb * @rx_ptype: the ptype value from the descriptor */ static void -ice_rx_hash(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc, - struct sk_buff *skb, u16 rx_ptype) +ice_rx_hash_to_skb(const struct ice_rx_ring *rx_ring, + const union ice_32b_rx_flex_desc *rx_desc, + struct sk_buff *skb, u16 rx_ptype) { - struct ice_32b_rx_flex_desc_nic *nic_mdid; u32 hash; if (!(rx_ring->netdev->features & NETIF_F_RXHASH)) return; - if (rx_desc->wb.rxdid != ICE_RXDID_FLEX_NIC) - return; - - nic_mdid = (struct ice_32b_rx_flex_desc_nic *)rx_desc; - hash = le32_to_cpu(nic_mdid->rss_hash); - skb_set_hash(skb, hash, ice_ptype_to_htype(rx_ptype)); + hash = ice_get_rx_hash(rx_desc); + if (likely(hash)) + skb_set_hash(skb, hash, ice_ptype_to_htype(rx_ptype)); } /** @@ -171,11 +185,38 @@ checksum_fail: } /** + * ice_ptp_rx_hwts_to_skb - Put RX timestamp into skb + * @rx_ring: Ring to get the VSI info + * @rx_desc: Receive descriptor + * @skb: Particular skb to send timestamp with + * + * The timestamp is in ns, so we must convert the result first. + */ +static void +ice_ptp_rx_hwts_to_skb(struct ice_rx_ring *rx_ring, + const union ice_32b_rx_flex_desc *rx_desc, + struct sk_buff *skb) +{ + u64 ts_ns = ice_ptp_get_rx_hwts(rx_desc, &rx_ring->pkt_ctx); + + skb_hwtstamps(skb)->hwtstamp = ns_to_ktime(ts_ns); +} + +/** + * ice_get_ptype - Read HW packet type from the descriptor + * @rx_desc: RX descriptor + */ +static u16 ice_get_ptype(const union ice_32b_rx_flex_desc *rx_desc) +{ + return le16_to_cpu(rx_desc->wb.ptype_flex_flags0) & + ICE_RX_FLEX_DESC_PTYPE_M; +} + +/** * ice_process_skb_fields - Populate skb header fields from Rx descriptor * @rx_ring: Rx descriptor ring packet is being transacted on * @rx_desc: pointer to the EOP Rx descriptor * @skb: pointer to current skb being populated - * @ptype: the packet type decoded by hardware * * This function checks the ring, descriptor, and packet information in * order to populate the hash, checksum, VLAN, protocol, and @@ -184,9 +225,11 @@ checksum_fail: void ice_process_skb_fields(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc, - struct sk_buff *skb, u16 ptype) + struct sk_buff *skb) { - ice_rx_hash(rx_ring, rx_desc, skb, ptype); + u16 ptype = ice_get_ptype(rx_desc); + + ice_rx_hash_to_skb(rx_ring, rx_desc, skb, ptype); /* modifies the skb - consumes the enet header */ skb->protocol = eth_type_trans(skb, rx_ring->netdev); @@ -194,28 +237,24 @@ ice_process_skb_fields(struct ice_rx_ring *rx_ring, ice_rx_csum(rx_ring, skb, rx_desc, ptype); if (rx_ring->ptp_rx) - ice_ptp_rx_hwtstamp(rx_ring, rx_desc, skb); + ice_ptp_rx_hwts_to_skb(rx_ring, rx_desc, skb); } /** * ice_receive_skb - Send a completed packet up the stack * @rx_ring: Rx ring in play * @skb: packet to send up - * @vlan_tag: VLAN tag for packet + * @vlan_tci: VLAN TCI for packet * * This function sends the completed packet (via. skb) up the stack using * gro receive functions (with/without VLAN tag) */ void -ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag) +ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tci) { - netdev_features_t features = rx_ring->netdev->features; - bool non_zero_vlan = !!(vlan_tag & VLAN_VID_MASK); - - if ((features & NETIF_F_HW_VLAN_CTAG_RX) && non_zero_vlan) - __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tag); - else if ((features & NETIF_F_HW_VLAN_STAG_RX) && non_zero_vlan) - __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021AD), vlan_tag); + if ((vlan_tci & VLAN_VID_MASK) && rx_ring->vlan_proto) + __vlan_hwaccel_put_tag(skb, rx_ring->vlan_proto, + vlan_tci); napi_gro_receive(&rx_ring->q_vector->napi, skb); } @@ -464,3 +503,125 @@ void ice_finalize_xdp_rx(struct ice_tx_ring *xdp_ring, unsigned int xdp_res, spin_unlock(&xdp_ring->tx_lock); } } + +/** + * ice_xdp_rx_hw_ts - HW timestamp XDP hint handler + * @ctx: XDP buff pointer + * @ts_ns: destination address + * + * Copy HW timestamp (if available) to the destination address. + */ +static int ice_xdp_rx_hw_ts(const struct xdp_md *ctx, u64 *ts_ns) +{ + const struct ice_xdp_buff *xdp_ext = (void *)ctx; + + *ts_ns = ice_ptp_get_rx_hwts(xdp_ext->eop_desc, + xdp_ext->pkt_ctx); + if (!*ts_ns) + return -ENODATA; + + return 0; +} + +/* Define a ptype index -> XDP hash type lookup table. + * It uses the same ptype definitions as ice_decode_rx_desc_ptype[], + * avoiding possible copy-paste errors. + */ +#undef ICE_PTT +#undef ICE_PTT_UNUSED_ENTRY + +#define ICE_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\ + [PTYPE] = XDP_RSS_L3_##OUTER_IP_VER | XDP_RSS_L4_##I | XDP_RSS_TYPE_##PL + +#define ICE_PTT_UNUSED_ENTRY(PTYPE) [PTYPE] = 0 + +/* A few supplementary definitions for when XDP hash types do not coincide + * with what can be generated from ptype definitions + * by means of preprocessor concatenation. + */ +#define XDP_RSS_L3_NONE XDP_RSS_TYPE_NONE +#define XDP_RSS_L4_NONE XDP_RSS_TYPE_NONE +#define XDP_RSS_TYPE_PAY2 XDP_RSS_TYPE_L2 +#define XDP_RSS_TYPE_PAY3 XDP_RSS_TYPE_NONE +#define XDP_RSS_TYPE_PAY4 XDP_RSS_L4 + +static const enum xdp_rss_hash_type +ice_ptype_to_xdp_hash[ICE_NUM_DEFINED_PTYPES] = { + ICE_PTYPES +}; + +#undef XDP_RSS_L3_NONE +#undef XDP_RSS_L4_NONE +#undef XDP_RSS_TYPE_PAY2 +#undef XDP_RSS_TYPE_PAY3 +#undef XDP_RSS_TYPE_PAY4 + +#undef ICE_PTT +#undef ICE_PTT_UNUSED_ENTRY + +/** + * ice_xdp_rx_hash_type - Get XDP-specific hash type from the RX descriptor + * @eop_desc: End of Packet descriptor + */ +static enum xdp_rss_hash_type +ice_xdp_rx_hash_type(const union ice_32b_rx_flex_desc *eop_desc) +{ + u16 ptype = ice_get_ptype(eop_desc); + + if (unlikely(ptype >= ICE_NUM_DEFINED_PTYPES)) + return 0; + + return ice_ptype_to_xdp_hash[ptype]; +} + +/** + * ice_xdp_rx_hash - RX hash XDP hint handler + * @ctx: XDP buff pointer + * @hash: hash destination address + * @rss_type: XDP hash type destination address + * + * Copy RX hash (if available) and its type to the destination address. + */ +static int ice_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash, + enum xdp_rss_hash_type *rss_type) +{ + const struct ice_xdp_buff *xdp_ext = (void *)ctx; + + *hash = ice_get_rx_hash(xdp_ext->eop_desc); + *rss_type = ice_xdp_rx_hash_type(xdp_ext->eop_desc); + if (!likely(*hash)) + return -ENODATA; + + return 0; +} + +/** + * ice_xdp_rx_vlan_tag - VLAN tag XDP hint handler + * @ctx: XDP buff pointer + * @vlan_proto: destination address for VLAN protocol + * @vlan_tci: destination address for VLAN TCI + * + * Copy VLAN tag (if was stripped) and corresponding protocol + * to the destination address. + */ +static int ice_xdp_rx_vlan_tag(const struct xdp_md *ctx, __be16 *vlan_proto, + u16 *vlan_tci) +{ + const struct ice_xdp_buff *xdp_ext = (void *)ctx; + + *vlan_proto = xdp_ext->pkt_ctx->vlan_proto; + if (!*vlan_proto) + return -ENODATA; + + *vlan_tci = ice_get_vlan_tci(xdp_ext->eop_desc); + if (!*vlan_tci) + return -ENODATA; + + return 0; +} + +const struct xdp_metadata_ops ice_xdp_md_ops = { + .xmo_rx_timestamp = ice_xdp_rx_hw_ts, + .xmo_rx_hash = ice_xdp_rx_hash, + .xmo_rx_vlan_tag = ice_xdp_rx_vlan_tag, +}; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h index 115969ecdf7b..762047508619 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h @@ -84,7 +84,7 @@ ice_build_ctob(u64 td_cmd, u64 td_offset, unsigned int size, u64 td_tag) } /** - * ice_get_vlan_tag_from_rx_desc - get VLAN from Rx flex descriptor + * ice_get_vlan_tci - get VLAN TCI from Rx flex descriptor * @rx_desc: Rx 32b flex descriptor with RXDID=2 * * The OS and current PF implementation only support stripping a single VLAN tag @@ -92,7 +92,7 @@ ice_build_ctob(u64 td_cmd, u64 td_offset, unsigned int size, u64 td_tag) * one is found return the tag, else return 0 to mean no VLAN tag was found. */ static inline u16 -ice_get_vlan_tag_from_rx_desc(union ice_32b_rx_flex_desc *rx_desc) +ice_get_vlan_tci(const union ice_32b_rx_flex_desc *rx_desc) { u16 stat_err_bits; @@ -148,7 +148,17 @@ void ice_release_rx_desc(struct ice_rx_ring *rx_ring, u16 val); void ice_process_skb_fields(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc, - struct sk_buff *skb, u16 ptype); + struct sk_buff *skb); void -ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag); +ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tci); + +static inline void +ice_xdp_meta_set_desc(struct xdp_buff *xdp, + union ice_32b_rx_flex_desc *eop_desc) +{ + struct ice_xdp_buff *xdp_ext = container_of(xdp, struct ice_xdp_buff, + xdp_buff); + + xdp_ext->eop_desc = eop_desc; +} #endif /* !_ICE_TXRX_LIB_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 99954508184f..5d1ae8e4058a 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -458,6 +458,11 @@ static u16 ice_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp, rx_desc->read.pkt_addr = cpu_to_le64(dma); rx_desc->wb.status_error0 = 0; + /* Put private info that changes on a per-packet basis + * into xdp_buff_xsk->cb. + */ + ice_xdp_meta_set_desc(*xdp, rx_desc); + rx_desc++; xdp++; } @@ -863,8 +868,7 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget) struct xdp_buff *xdp; struct sk_buff *skb; u16 stat_err_bits; - u16 vlan_tag = 0; - u16 rx_ptype; + u16 vlan_tci; rx_desc = ICE_RX_DESC(rx_ring, ntc); @@ -942,13 +946,10 @@ construct_skb: total_rx_bytes += skb->len; total_rx_packets++; - vlan_tag = ice_get_vlan_tag_from_rx_desc(rx_desc); - - rx_ptype = le16_to_cpu(rx_desc->wb.ptype_flex_flags0) & - ICE_RX_FLEX_DESC_PTYPE_M; + vlan_tci = ice_get_vlan_tci(rx_desc); - ice_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype); - ice_receive_skb(rx_ring, skb, vlan_tag); + ice_process_skb_fields(rx_ring, rx_desc, skb); + ice_receive_skb(rx_ring, skb, vlan_tci); } rx_ring->next_to_clean = ntc; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index e2e7d82cfca4..9e695ed122ee 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -256,9 +256,24 @@ static int mlx5e_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash, return 0; } +static int mlx5e_xdp_rx_vlan_tag(const struct xdp_md *ctx, __be16 *vlan_proto, + u16 *vlan_tci) +{ + const struct mlx5e_xdp_buff *_ctx = (void *)ctx; + const struct mlx5_cqe64 *cqe = _ctx->cqe; + + if (!cqe_has_vlan(cqe)) + return -ENODATA; + + *vlan_proto = htons(ETH_P_8021Q); + *vlan_tci = be16_to_cpu(cqe->vlan_info); + return 0; +} + const struct xdp_metadata_ops mlx5e_xdp_metadata_ops = { .xmo_rx_timestamp = mlx5e_xdp_rx_timestamp, .xmo_rx_hash = mlx5e_xdp_rx_hash, + .xmo_rx_vlan_tag = mlx5e_xdp_rx_vlan_tag, }; struct mlx5e_xsk_tx_complete { diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 977861c46b1f..578e36ea1589 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -1723,6 +1723,24 @@ static int veth_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash, return 0; } +static int veth_xdp_rx_vlan_tag(const struct xdp_md *ctx, __be16 *vlan_proto, + u16 *vlan_tci) +{ + const struct veth_xdp_buff *_ctx = (void *)ctx; + const struct sk_buff *skb = _ctx->skb; + int err; + + if (!skb) + return -ENODATA; + + err = __vlan_hwaccel_get_tag(skb, vlan_tci); + if (err) + return err; + + *vlan_proto = skb->vlan_proto; + return err; +} + static const struct net_device_ops veth_netdev_ops = { .ndo_init = veth_dev_init, .ndo_open = veth_open, @@ -1747,6 +1765,7 @@ static const struct net_device_ops veth_netdev_ops = { static const struct xdp_metadata_ops veth_xdp_metadata_ops = { .xmo_rx_timestamp = veth_xdp_rx_timestamp, .xmo_rx_hash = veth_xdp_rx_hash, + .xmo_rx_vlan_tag = veth_xdp_rx_vlan_tag, }; #define VETH_FEATURES (NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HW_CSUM | \ diff --git a/fs/verity/fsverity_private.h b/fs/verity/fsverity_private.h index d071a6e32581..a6a6b2749241 100644 --- a/fs/verity/fsverity_private.h +++ b/fs/verity/fsverity_private.h @@ -100,6 +100,16 @@ fsverity_msg(const struct inode *inode, const char *level, #define fsverity_err(inode, fmt, ...) \ fsverity_msg((inode), KERN_ERR, fmt, ##__VA_ARGS__) +/* measure.c */ + +#ifdef CONFIG_BPF_SYSCALL +void __init fsverity_init_bpf(void); +#else +static inline void fsverity_init_bpf(void) +{ +} +#endif + /* open.c */ int fsverity_init_merkle_tree_params(struct merkle_tree_params *params, diff --git a/fs/verity/init.c b/fs/verity/init.c index a29f062f6047..1e207c0f71de 100644 --- a/fs/verity/init.c +++ b/fs/verity/init.c @@ -69,6 +69,7 @@ static int __init fsverity_init(void) fsverity_init_workqueue(); fsverity_init_sysctl(); fsverity_init_signature(); + fsverity_init_bpf(); return 0; } late_initcall(fsverity_init) diff --git a/fs/verity/measure.c b/fs/verity/measure.c index eec5956141da..bf7a5f4cccaf 100644 --- a/fs/verity/measure.c +++ b/fs/verity/measure.c @@ -7,6 +7,8 @@ #include "fsverity_private.h" +#include <linux/bpf.h> +#include <linux/btf.h> #include <linux/uaccess.h> /** @@ -100,3 +102,85 @@ int fsverity_get_digest(struct inode *inode, return hash_alg->digest_size; } EXPORT_SYMBOL_GPL(fsverity_get_digest); + +#ifdef CONFIG_BPF_SYSCALL + +/* bpf kfuncs */ +__bpf_kfunc_start_defs(); + +/** + * bpf_get_fsverity_digest: read fsverity digest of file + * @file: file to get digest from + * @digest_ptr: (out) dynptr for struct fsverity_digest + * + * Read fsverity_digest of *file* into *digest_ptr*. + * + * Return: 0 on success, a negative value on error. + */ +__bpf_kfunc int bpf_get_fsverity_digest(struct file *file, struct bpf_dynptr_kern *digest_ptr) +{ + const struct inode *inode = file_inode(file); + u32 dynptr_sz = __bpf_dynptr_size(digest_ptr); + struct fsverity_digest *arg; + const struct fsverity_info *vi; + const struct fsverity_hash_alg *hash_alg; + int out_digest_sz; + + if (dynptr_sz < sizeof(struct fsverity_digest)) + return -EINVAL; + + arg = __bpf_dynptr_data_rw(digest_ptr, dynptr_sz); + if (!arg) + return -EINVAL; + + if (!IS_ALIGNED((uintptr_t)arg, __alignof__(*arg))) + return -EINVAL; + + vi = fsverity_get_info(inode); + if (!vi) + return -ENODATA; /* not a verity file */ + + hash_alg = vi->tree_params.hash_alg; + + arg->digest_algorithm = hash_alg - fsverity_hash_algs; + arg->digest_size = hash_alg->digest_size; + + out_digest_sz = dynptr_sz - sizeof(struct fsverity_digest); + + /* copy digest */ + memcpy(arg->digest, vi->file_digest, min_t(int, hash_alg->digest_size, out_digest_sz)); + + /* fill the extra buffer with zeros */ + if (out_digest_sz > hash_alg->digest_size) + memset(arg->digest + arg->digest_size, 0, out_digest_sz - hash_alg->digest_size); + + return 0; +} + +__bpf_kfunc_end_defs(); + +BTF_SET8_START(fsverity_set_ids) +BTF_ID_FLAGS(func, bpf_get_fsverity_digest, KF_TRUSTED_ARGS) +BTF_SET8_END(fsverity_set_ids) + +static int bpf_get_fsverity_digest_filter(const struct bpf_prog *prog, u32 kfunc_id) +{ + if (!btf_id_set8_contains(&fsverity_set_ids, kfunc_id)) + return 0; + + /* Only allow to attach from LSM hooks, to avoid recursion */ + return prog->type != BPF_PROG_TYPE_LSM ? -EACCES : 0; +} + +static const struct btf_kfunc_id_set bpf_fsverity_set = { + .owner = THIS_MODULE, + .set = &fsverity_set_ids, + .filter = bpf_get_fsverity_digest_filter, +}; + +void __init fsverity_init_bpf(void) +{ + register_btf_kfunc_id_set(BPF_PROG_TYPE_LSM, &bpf_fsverity_set); +} + +#endif /* CONFIG_BPF_SYSCALL */ diff --git a/include/asm-generic/Kbuild b/include/asm-generic/Kbuild index def242528b1d..d436bee4d129 100644 --- a/include/asm-generic/Kbuild +++ b/include/asm-generic/Kbuild @@ -11,6 +11,7 @@ mandatory-y += bitops.h mandatory-y += bug.h mandatory-y += bugs.h mandatory-y += cacheflush.h +mandatory-y += cfi.h mandatory-y += checksum.h mandatory-y += compat.h mandatory-y += current.h diff --git a/include/asm-generic/cfi.h b/include/asm-generic/cfi.h new file mode 100644 index 000000000000..41fac3537bf9 --- /dev/null +++ b/include/asm-generic/cfi.h @@ -0,0 +1,5 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_GENERIC_CFI_H +#define __ASM_GENERIC_CFI_H + +#endif /* __ASM_GENERIC_CFI_H */ diff --git a/include/linux/bpf.h b/include/linux/bpf.h index d5d8e2083610..2f54cc0436c4 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -29,6 +29,7 @@ #include <linux/rcupdate_trace.h> #include <linux/static_call.h> #include <linux/memcontrol.h> +#include <linux/cfi.h> struct bpf_verifier_env; struct bpf_verifier_log; @@ -51,6 +52,10 @@ struct module; struct bpf_func_state; struct ftrace_ops; struct cgroup; +struct bpf_token; +struct user_namespace; +struct super_block; +struct inode; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; @@ -106,7 +111,11 @@ struct bpf_map_ops { /* funcs called by prog_array and perf_event_array map */ void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file, int fd); - void (*map_fd_put_ptr)(void *ptr); + /* If need_defer is true, the implementation should guarantee that + * the to-be-put element is still alive before the bpf program, which + * may manipulate it, exists. + */ + void (*map_fd_put_ptr)(struct bpf_map *map, void *ptr, bool need_defer); int (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf); u32 (*map_fd_sys_lookup_elem)(void *ptr); void (*map_seq_show_elem)(struct bpf_map *map, void *key, @@ -272,7 +281,11 @@ struct bpf_map { */ atomic64_t refcnt ____cacheline_aligned; atomic64_t usercnt; - struct work_struct work; + /* rcu is used before freeing and work is only used during freeing */ + union { + struct work_struct work; + struct rcu_head rcu; + }; struct mutex freeze_mutex; atomic64_t writecnt; /* 'Ownership' of program-containing map is claimed by the first program @@ -288,6 +301,9 @@ struct bpf_map { } owner; bool bypass_spec_v1; bool frozen; /* write-once; write-protected by freeze_mutex */ + bool free_after_mult_rcu_gp; + bool free_after_rcu_gp; + atomic64_t sleepable_refcnt; s64 __percpu *elem_count; }; @@ -1044,6 +1060,17 @@ struct btf_func_model { */ #define BPF_TRAMP_F_TAIL_CALL_CTX BIT(7) +/* + * Indicate the trampoline should be suitable to receive indirect calls; + * without this indirectly calling the generated code can result in #UD/#CP, + * depending on the CFI options. + * + * Used by bpf_struct_ops. + * + * Incompatible with FENTRY usage, overloads @func_addr argument. + */ +#define BPF_TRAMP_F_INDIRECT BIT(8) + /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 * bytes on x86. */ @@ -1083,10 +1110,17 @@ struct bpf_tramp_run_ctx; * fexit = a set of program to run after original function */ struct bpf_tramp_image; -int arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end, +int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end, const struct btf_func_model *m, u32 flags, struct bpf_tramp_links *tlinks, - void *orig_call); + void *func_addr); +void *arch_alloc_bpf_trampoline(unsigned int size); +void arch_free_bpf_trampoline(void *image, unsigned int size); +void arch_protect_bpf_trampoline(void *image, unsigned int size); +void arch_unprotect_bpf_trampoline(void *image, unsigned int size); +int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, + struct bpf_tramp_links *tlinks, void *func_addr); + u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx); void notrace __bpf_prog_exit_sleepable_recur(struct bpf_prog *prog, u64 start, @@ -1119,6 +1153,7 @@ enum bpf_tramp_prog_type { struct bpf_tramp_image { void *image; + int size; struct bpf_ksym ksym; struct percpu_ref pcref; void *ip_after_call; @@ -1188,7 +1223,11 @@ struct bpf_dispatcher { #endif }; -static __always_inline __nocfi unsigned int bpf_dispatcher_nop_func( +#ifndef __bpfcall +#define __bpfcall __nocfi +#endif + +static __always_inline __bpfcall unsigned int bpf_dispatcher_nop_func( const void *ctx, const struct bpf_insn *insnsi, bpf_func_t bpf_func) @@ -1280,7 +1319,7 @@ int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_func #define DEFINE_BPF_DISPATCHER(name) \ __BPF_DISPATCHER_SC(name); \ - noinline __nocfi unsigned int bpf_dispatcher_##name##_func( \ + noinline __bpfcall unsigned int bpf_dispatcher_##name##_func( \ const void *ctx, \ const struct bpf_insn *insnsi, \ bpf_func_t bpf_func) \ @@ -1303,7 +1342,7 @@ int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_func void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, struct bpf_prog *to); /* Called only from JIT-enabled code, so there's no need for stubs. */ -void bpf_image_ksym_add(void *data, struct bpf_ksym *ksym); +void bpf_image_ksym_add(void *data, unsigned int size, struct bpf_ksym *ksym); void bpf_image_ksym_del(struct bpf_ksym *ksym); void bpf_ksym_add(struct bpf_ksym *ksym); void bpf_ksym_del(struct bpf_ksym *ksym); @@ -1430,6 +1469,9 @@ struct bpf_prog_aux { struct bpf_kfunc_desc_tab *kfunc_tab; struct bpf_kfunc_btf_tab *kfunc_btf_tab; u32 size_poke_tab; +#ifdef CONFIG_FINEIBT + struct bpf_ksym ksym_prefix; +#endif struct bpf_ksym ksym; const struct bpf_prog_ops *ops; struct bpf_map **used_maps; @@ -1442,10 +1484,11 @@ struct bpf_prog_aux { int cgroup_atype; /* enum cgroup_bpf_attach_type */ struct bpf_map *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]; char name[BPF_OBJ_NAME_LEN]; - unsigned int (*bpf_exception_cb)(u64 cookie, u64 sp, u64 bp); + u64 (*bpf_exception_cb)(u64 cookie, u64 sp, u64 bp, u64, u64); #ifdef CONFIG_SECURITY void *security; #endif + struct bpf_token *token; struct bpf_prog_offload *offload; struct btf *btf; struct bpf_func_info *func_info; @@ -1570,6 +1613,31 @@ struct bpf_link_primer { u32 id; }; +struct bpf_mount_opts { + kuid_t uid; + kgid_t gid; + umode_t mode; + + /* BPF token-related delegation options */ + u64 delegate_cmds; + u64 delegate_maps; + u64 delegate_progs; + u64 delegate_attachs; +}; + +struct bpf_token { + struct work_struct work; + atomic64_t refcnt; + struct user_namespace *userns; + u64 allowed_cmds; + u64 allowed_maps; + u64 allowed_progs; + u64 allowed_attachs; +#ifdef CONFIG_SECURITY + void *security; +#endif +}; + struct bpf_struct_ops_value; struct btf_member; @@ -1640,6 +1708,7 @@ struct bpf_struct_ops { struct btf_func_model func_models[BPF_STRUCT_OPS_MAX_NR_MEMBERS]; u32 type_id; u32 value_id; + void *cfi_stubs; }; #if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL) @@ -1653,6 +1722,7 @@ int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks, struct bpf_tramp_link *link, const struct btf_func_model *model, + void *stub_func, void *image, void *image_end); static inline bool bpf_try_module_get(const void *data, struct module *owner) { @@ -2027,6 +2097,7 @@ static inline void bpf_enable_instrumentation(void) migrate_enable(); } +extern const struct super_operations bpf_super_ops; extern const struct file_operations bpf_map_fops; extern const struct file_operations bpf_prog_fops; extern const struct file_operations bpf_iter_fops; @@ -2161,24 +2232,26 @@ static inline void bpf_map_dec_elem_count(struct bpf_map *map) extern int sysctl_unprivileged_bpf_disabled; -static inline bool bpf_allow_ptr_leaks(void) +bool bpf_token_capable(const struct bpf_token *token, int cap); + +static inline bool bpf_allow_ptr_leaks(const struct bpf_token *token) { - return perfmon_capable(); + return bpf_token_capable(token, CAP_PERFMON); } -static inline bool bpf_allow_uninit_stack(void) +static inline bool bpf_allow_uninit_stack(const struct bpf_token *token) { - return perfmon_capable(); + return bpf_token_capable(token, CAP_PERFMON); } -static inline bool bpf_bypass_spec_v1(void) +static inline bool bpf_bypass_spec_v1(const struct bpf_token *token) { - return cpu_mitigations_off() || perfmon_capable(); + return cpu_mitigations_off() || bpf_token_capable(token, CAP_PERFMON); } -static inline bool bpf_bypass_spec_v4(void) +static inline bool bpf_bypass_spec_v4(const struct bpf_token *token) { - return cpu_mitigations_off() || perfmon_capable(); + return cpu_mitigations_off() || bpf_token_capable(token, CAP_PERFMON); } int bpf_map_new_fd(struct bpf_map *map, int flags); @@ -2195,8 +2268,21 @@ int bpf_link_new_fd(struct bpf_link *link); struct bpf_link *bpf_link_get_from_fd(u32 ufd); struct bpf_link *bpf_link_get_curr_or_next(u32 *id); +void bpf_token_inc(struct bpf_token *token); +void bpf_token_put(struct bpf_token *token); +int bpf_token_create(union bpf_attr *attr); +struct bpf_token *bpf_token_get_from_fd(u32 ufd); + +bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd); +bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type); +bool bpf_token_allow_prog_type(const struct bpf_token *token, + enum bpf_prog_type prog_type, + enum bpf_attach_type attach_type); + int bpf_obj_pin_user(u32 ufd, int path_fd, const char __user *pathname); int bpf_obj_get_user(int path_fd, const char __user *pathname, int flags); +struct inode *bpf_get_inode(struct super_block *sb, const struct inode *dir, + umode_t mode); #define BPF_ITER_FUNC_PREFIX "bpf_iter_" #define DEFINE_BPF_ITER_FUNC(target, args...) \ @@ -2431,7 +2517,7 @@ int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog, int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog, struct bpf_reg_state *regs); int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, - struct bpf_reg_state *reg, bool is_ex_cb); + struct bpf_reg_state *reg, u32 *nargs); int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog, struct btf *btf, const struct btf_type *t); const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type *pt, @@ -2440,7 +2526,8 @@ const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type struct bpf_prog *bpf_prog_by_id(u32 id); struct bpf_link *bpf_link_by_id(u32 id); -const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id); +const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id, + const struct bpf_prog *prog); void bpf_task_storage_free(struct task_struct *task); void bpf_cgrp_storage_free(struct cgroup *cgroup); bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog); @@ -2559,6 +2646,24 @@ static inline int bpf_obj_get_user(const char __user *pathname, int flags) return -EOPNOTSUPP; } +static inline bool bpf_token_capable(const struct bpf_token *token, int cap) +{ + return capable(cap) || (cap != CAP_SYS_ADMIN && capable(CAP_SYS_ADMIN)); +} + +static inline void bpf_token_inc(struct bpf_token *token) +{ +} + +static inline void bpf_token_put(struct bpf_token *token) +{ +} + +static inline struct bpf_token *bpf_token_get_from_fd(u32 ufd) +{ + return ERR_PTR(-EOPNOTSUPP); +} + static inline void __dev_flush(void) { } @@ -2682,7 +2787,7 @@ static inline int btf_struct_access(struct bpf_verifier_log *log, } static inline const struct bpf_func_proto * -bpf_base_func_proto(enum bpf_func_id func_id) +bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { return NULL; } diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index d99a636d36a7..c2819a6579a5 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -275,6 +275,11 @@ struct bpf_reference_state { int callback_ref; }; +struct bpf_retval_range { + s32 minval; + s32 maxval; +}; + /* state of the program: * type of all registers and stack info */ @@ -297,8 +302,8 @@ struct bpf_func_state { * void foo(void) { bpf_timer_set_callback(,foo); } */ u32 async_entry_cnt; + struct bpf_retval_range callback_ret_range; bool in_callback_fn; - struct tnum callback_ret_range; bool in_async_callback_fn; bool in_exception_callback_fn; /* For callback calling functions that limit number of possible @@ -316,16 +321,48 @@ struct bpf_func_state { /* The following fields should be last. See copy_func_state() */ int acquired_refs; struct bpf_reference_state *refs; - int allocated_stack; + /* The state of the stack. Each element of the array describes BPF_REG_SIZE + * (i.e. 8) bytes worth of stack memory. + * stack[0] represents bytes [*(r10-8)..*(r10-1)] + * stack[1] represents bytes [*(r10-16)..*(r10-9)] + * ... + * stack[allocated_stack/8 - 1] represents [*(r10-allocated_stack)..*(r10-allocated_stack+7)] + */ struct bpf_stack_state *stack; + /* Size of the current stack, in bytes. The stack state is tracked below, in + * `stack`. allocated_stack is always a multiple of BPF_REG_SIZE. + */ + int allocated_stack; +}; + +#define MAX_CALL_FRAMES 8 + +/* instruction history flags, used in bpf_jmp_history_entry.flags field */ +enum { + /* instruction references stack slot through PTR_TO_STACK register; + * we also store stack's frame number in lower 3 bits (MAX_CALL_FRAMES is 8) + * and accessed stack slot's index in next 6 bits (MAX_BPF_STACK is 512, + * 8 bytes per slot, so slot index (spi) is [0, 63]) + */ + INSN_F_FRAMENO_MASK = 0x7, /* 3 bits */ + + INSN_F_SPI_MASK = 0x3f, /* 6 bits */ + INSN_F_SPI_SHIFT = 3, /* shifted 3 bits to the left */ + + INSN_F_STACK_ACCESS = BIT(9), /* we need 10 bits total */ }; -struct bpf_idx_pair { - u32 prev_idx; +static_assert(INSN_F_FRAMENO_MASK + 1 >= MAX_CALL_FRAMES); +static_assert(INSN_F_SPI_MASK + 1 >= MAX_BPF_STACK / 8); + +struct bpf_jmp_history_entry { u32 idx; + /* insn idx can't be bigger than 1 million */ + u32 prev_idx : 22; + /* special flags, e.g., whether insn is doing register stack spill/load */ + u32 flags : 10; }; -#define MAX_CALL_FRAMES 8 /* Maximum number of register states that can exist at once */ #define BPF_ID_MAP_SIZE ((MAX_BPF_REG + MAX_BPF_STACK / BPF_REG_SIZE) * MAX_CALL_FRAMES) struct bpf_verifier_state { @@ -408,7 +445,7 @@ struct bpf_verifier_state { * For most states jmp_history_cnt is [0-3]. * For loops can go up to ~40. */ - struct bpf_idx_pair *jmp_history; + struct bpf_jmp_history_entry *jmp_history; u32 jmp_history_cnt; u32 dfs_depth; u32 callback_unroll_depth; @@ -574,12 +611,12 @@ struct bpf_subprog_info { u32 start; /* insn idx of function entry point */ u32 linfo_idx; /* The idx to the main_prog->aux->linfo */ u16 stack_depth; /* max. stack depth used by this function */ - bool has_tail_call; - bool tail_call_reachable; - bool has_ld_abs; - bool is_cb; - bool is_async_cb; - bool is_exception_cb; + bool has_tail_call: 1; + bool tail_call_reachable: 1; + bool has_ld_abs: 1; + bool is_cb: 1; + bool is_async_cb: 1; + bool is_exception_cb: 1; }; struct bpf_verifier_env; @@ -631,6 +668,10 @@ struct bpf_verifier_env { int exception_callback_subprog; bool explore_alu_limits; bool allow_ptr_leaks; + /* Allow access to uninitialized stack memory. Writes with fixed offset are + * always allowed, so this refers to reads (with fixed or variable offset), + * to writes with variable offset and to indirect (helper) accesses. + */ bool allow_uninit_stack; bool bpf_capable; bool bypass_spec_v1; @@ -651,6 +692,7 @@ struct bpf_verifier_env { int cur_stack; } cfg; struct backtrack_state bt; + struct bpf_jmp_history_entry *cur_hist_ent; u32 pass_cnt; /* number of times do_check() was called */ u32 subprog_cnt; /* number of instructions analyzed by the verifier */ diff --git a/include/linux/cfi.h b/include/linux/cfi.h index 3552ec82b725..f0df518e11dd 100644 --- a/include/linux/cfi.h +++ b/include/linux/cfi.h @@ -9,6 +9,14 @@ #include <linux/bug.h> #include <linux/module.h> +#include <asm/cfi.h> + +#ifndef cfi_get_offset +static inline int cfi_get_offset(void) +{ + return 0; +} +#endif #ifdef CONFIG_CFI_CLANG enum bug_trap_type report_cfi_failure(struct pt_regs *regs, unsigned long addr, @@ -38,4 +46,8 @@ static inline void module_cfi_finalize(const Elf_Ehdr *hdr, #endif /* CONFIG_ARCH_USES_CFI_TRAPS */ #endif /* CONFIG_MODULES */ +#ifndef CFI_NOSEAL +#define CFI_NOSEAL(x) +#endif + #endif /* _LINUX_CFI_H */ diff --git a/include/linux/filter.h b/include/linux/filter.h index a4953fafc8cb..12d907f17d36 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1067,7 +1067,7 @@ 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); -void bpf_prog_pack_free(struct bpf_binary_header *hdr); +void bpf_prog_pack_free(void *ptr, u32 size); static inline bool bpf_prog_kallsyms_verify_off(const struct bpf_prog *fp) { @@ -1139,7 +1139,7 @@ static inline bool bpf_jit_blinding_enabled(struct bpf_prog *prog) return false; if (!bpf_jit_harden) return false; - if (bpf_jit_harden == 1 && bpf_capable()) + if (bpf_jit_harden == 1 && bpf_token_capable(prog->aux->token, CAP_BPF)) return false; return true; diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 3028af87716e..c1645c86eed9 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -540,7 +540,7 @@ static inline int __vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) struct vlan_ethhdr *veth = skb_vlan_eth_hdr(skb); if (!eth_type_vlan(veth->h_vlan_proto)) - return -EINVAL; + return -ENODATA; *vlan_tci = ntohs(veth->h_vlan_TCI); return 0; @@ -561,7 +561,7 @@ static inline int __vlan_hwaccel_get_tag(const struct sk_buff *skb, return 0; } else { *vlan_tci = 0; - return -EINVAL; + return -ENODATA; } } diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index ff217a5ce552..3fdd00b452ac 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -398,10 +398,17 @@ LSM_HOOK(void, LSM_RET_VOID, audit_rule_free, void *lsmrule) LSM_HOOK(int, 0, bpf, int cmd, union bpf_attr *attr, unsigned int size) LSM_HOOK(int, 0, bpf_map, struct bpf_map *map, fmode_t fmode) LSM_HOOK(int, 0, bpf_prog, struct bpf_prog *prog) -LSM_HOOK(int, 0, bpf_map_alloc_security, struct bpf_map *map) -LSM_HOOK(void, LSM_RET_VOID, bpf_map_free_security, struct bpf_map *map) -LSM_HOOK(int, 0, bpf_prog_alloc_security, struct bpf_prog_aux *aux) -LSM_HOOK(void, LSM_RET_VOID, bpf_prog_free_security, struct bpf_prog_aux *aux) +LSM_HOOK(int, 0, bpf_map_create, struct bpf_map *map, union bpf_attr *attr, + struct bpf_token *token) +LSM_HOOK(void, LSM_RET_VOID, bpf_map_free, struct bpf_map *map) +LSM_HOOK(int, 0, bpf_prog_load, struct bpf_prog *prog, union bpf_attr *attr, + struct bpf_token *token) +LSM_HOOK(void, LSM_RET_VOID, bpf_prog_free, struct bpf_prog *prog) +LSM_HOOK(int, 0, bpf_token_create, struct bpf_token *token, union bpf_attr *attr, + struct path *path) +LSM_HOOK(void, LSM_RET_VOID, bpf_token_free, struct bpf_token *token) +LSM_HOOK(int, 0, bpf_token_cmd, const struct bpf_token *token, enum bpf_cmd cmd) +LSM_HOOK(int, 0, bpf_token_capable, const struct bpf_token *token, int cap) #endif /* CONFIG_BPF_SYSCALL */ LSM_HOOK(int, 0, locked_down, enum lockdown_reason what) diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 820bca965fb6..01275c6e8468 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -918,7 +918,7 @@ static inline u8 get_cqe_tls_offload(struct mlx5_cqe64 *cqe) return (cqe->tls_outer_l3_tunneled >> 3) & 0x3; } -static inline bool cqe_has_vlan(struct mlx5_cqe64 *cqe) +static inline bool cqe_has_vlan(const struct mlx5_cqe64 *cqe) { return cqe->l4_l3_hdr_type & 0x1; } diff --git a/include/linux/security.h b/include/linux/security.h index 1d1df326c881..00809d2d5c38 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -32,6 +32,7 @@ #include <linux/string.h> #include <linux/mm.h> #include <linux/sockptr.h> +#include <linux/bpf.h> struct linux_binprm; struct cred; @@ -2020,15 +2021,22 @@ static inline void securityfs_remove(struct dentry *dentry) union bpf_attr; struct bpf_map; struct bpf_prog; -struct bpf_prog_aux; +struct bpf_token; #ifdef CONFIG_SECURITY extern int security_bpf(int cmd, union bpf_attr *attr, unsigned int size); extern int security_bpf_map(struct bpf_map *map, fmode_t fmode); extern int security_bpf_prog(struct bpf_prog *prog); -extern int security_bpf_map_alloc(struct bpf_map *map); +extern int security_bpf_map_create(struct bpf_map *map, union bpf_attr *attr, + struct bpf_token *token); extern void security_bpf_map_free(struct bpf_map *map); -extern int security_bpf_prog_alloc(struct bpf_prog_aux *aux); -extern void security_bpf_prog_free(struct bpf_prog_aux *aux); +extern int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, + struct bpf_token *token); +extern void security_bpf_prog_free(struct bpf_prog *prog); +extern int security_bpf_token_create(struct bpf_token *token, union bpf_attr *attr, + struct path *path); +extern void security_bpf_token_free(struct bpf_token *token); +extern int security_bpf_token_cmd(const struct bpf_token *token, enum bpf_cmd cmd); +extern int security_bpf_token_capable(const struct bpf_token *token, int cap); #else static inline int security_bpf(int cmd, union bpf_attr *attr, unsigned int size) @@ -2046,7 +2054,8 @@ static inline int security_bpf_prog(struct bpf_prog *prog) return 0; } -static inline int security_bpf_map_alloc(struct bpf_map *map) +static inline int security_bpf_map_create(struct bpf_map *map, union bpf_attr *attr, + struct bpf_token *token) { return 0; } @@ -2054,13 +2063,33 @@ static inline int security_bpf_map_alloc(struct bpf_map *map) static inline void security_bpf_map_free(struct bpf_map *map) { } -static inline int security_bpf_prog_alloc(struct bpf_prog_aux *aux) +static inline int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, + struct bpf_token *token) { return 0; } -static inline void security_bpf_prog_free(struct bpf_prog_aux *aux) +static inline void security_bpf_prog_free(struct bpf_prog *prog) { } + +static inline int security_bpf_token_create(struct bpf_token *token, union bpf_attr *attr, + struct path *path) +{ + return 0; +} + +static inline void security_bpf_token_free(struct bpf_token *token) +{ } + +static inline int security_bpf_token_cmd(const struct bpf_token *token, enum bpf_cmd cmd) +{ + return 0; +} + +static inline int security_bpf_token_capable(const struct bpf_token *token, int cap) +{ + return 0; +} #endif /* CONFIG_SECURITY */ #endif /* CONFIG_BPF_SYSCALL */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 7ce38874dbd1..ea5c8ab3ed00 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4247,10 +4247,13 @@ static inline bool __skb_metadata_differs(const struct sk_buff *skb_a, { const void *a = skb_metadata_end(skb_a); const void *b = skb_metadata_end(skb_b); - /* Using more efficient variant than plain call to memcmp(). */ -#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 u64 diffs = 0; + if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) || + BITS_PER_LONG != 64) + goto slow; + + /* Using more efficient variant than plain call to memcmp(). */ switch (meta_len) { #define __it(x, op) (x -= sizeof(u##op)) #define __it_diff(a, b, op) (*(u##op *)__it(a, op)) ^ (*(u##op *)__it(b, op)) @@ -4270,11 +4273,11 @@ static inline bool __skb_metadata_differs(const struct sk_buff *skb_a, fallthrough; case 4: diffs |= __it_diff(a, b, 32); break; + default: +slow: + return memcmp(a - meta_len, b - meta_len, meta_len); } return diffs; -#else - return memcmp(a - meta_len, b - meta_len, meta_len); -#endif } static inline bool skb_metadata_differs(const struct sk_buff *skb_a, diff --git a/include/net/xdp.h b/include/net/xdp.h index 349c36fb5fd8..e6770dd40c91 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -16,7 +16,7 @@ * * The XDP RX-queue info (xdp_rxq_info) is associated with the driver * level RX-ring queues. It is information that is specific to how - * the driver have configured a given RX-ring queue. + * the driver has configured a given RX-ring queue. * * Each xdp_buff frame received in the driver carries a (pointer) * reference to this xdp_rxq_info structure. This provides the XDP @@ -32,7 +32,7 @@ * The struct is not directly tied to the XDP prog. A new XDP prog * can be attached as long as it doesn't change the underlying * RX-ring. If the RX-ring does change significantly, the NIC driver - * naturally need to stop the RX-ring before purging and reallocating + * naturally needs to stop the RX-ring before purging and reallocating * memory. In that process the driver MUST call unregister (which * also applies for driver shutdown and unload). The register API is * also mandatory during RX-ring setup. @@ -369,7 +369,12 @@ xdp_data_meta_unsupported(const struct xdp_buff *xdp) static inline bool xdp_metalen_invalid(unsigned long metalen) { - return (metalen & (sizeof(__u32) - 1)) || (metalen > 32); + unsigned long meta_max; + + meta_max = type_max(typeof_member(struct skb_shared_info, meta_len)); + BUILD_BUG_ON(!__builtin_constant_p(meta_max)); + + return !IS_ALIGNED(metalen, sizeof(u32)) || metalen > meta_max; } struct xdp_attachment_info { @@ -399,6 +404,10 @@ void xdp_attachment_setup(struct xdp_attachment_info *info, NETDEV_XDP_RX_METADATA_HASH, \ bpf_xdp_metadata_rx_hash, \ xmo_rx_hash) \ + XDP_METADATA_KFUNC(XDP_METADATA_KFUNC_RX_VLAN_TAG, \ + NETDEV_XDP_RX_METADATA_VLAN_TAG, \ + bpf_xdp_metadata_rx_vlan_tag, \ + xmo_rx_vlan_tag) \ enum xdp_rx_metadata { #define XDP_METADATA_KFUNC(name, _, __, ___) name, @@ -427,6 +436,7 @@ enum xdp_rss_hash_type { XDP_RSS_L4_UDP = BIT(5), XDP_RSS_L4_SCTP = BIT(6), XDP_RSS_L4_IPSEC = BIT(7), /* L4 based hash include IPSEC SPI */ + XDP_RSS_L4_ICMP = BIT(8), /* Second part: RSS hash type combinations used for driver HW mapping */ XDP_RSS_TYPE_NONE = 0, @@ -442,11 +452,13 @@ enum xdp_rss_hash_type { XDP_RSS_TYPE_L4_IPV4_UDP = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_UDP, XDP_RSS_TYPE_L4_IPV4_SCTP = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_SCTP, XDP_RSS_TYPE_L4_IPV4_IPSEC = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_IPSEC, + XDP_RSS_TYPE_L4_IPV4_ICMP = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_ICMP, XDP_RSS_TYPE_L4_IPV6_TCP = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_TCP, XDP_RSS_TYPE_L4_IPV6_UDP = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_UDP, XDP_RSS_TYPE_L4_IPV6_SCTP = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_SCTP, XDP_RSS_TYPE_L4_IPV6_IPSEC = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_IPSEC, + XDP_RSS_TYPE_L4_IPV6_ICMP = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_ICMP, XDP_RSS_TYPE_L4_IPV6_TCP_EX = XDP_RSS_TYPE_L4_IPV6_TCP | XDP_RSS_L3_DYNHDR, XDP_RSS_TYPE_L4_IPV6_UDP_EX = XDP_RSS_TYPE_L4_IPV6_UDP | XDP_RSS_L3_DYNHDR, @@ -457,6 +469,8 @@ struct xdp_metadata_ops { int (*xmo_rx_timestamp)(const struct xdp_md *ctx, u64 *timestamp); int (*xmo_rx_hash)(const struct xdp_md *ctx, u32 *hash, enum xdp_rss_hash_type *rss_type); + int (*xmo_rx_vlan_tag)(const struct xdp_md *ctx, __be16 *vlan_proto, + u16 *vlan_tci); }; #ifdef CONFIG_NET diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index 81e02de3f453..b62bb8525a5f 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -14,6 +14,12 @@ #ifdef CONFIG_XDP_SOCKETS +struct xsk_cb_desc { + void *src; + u8 off; + u8 bytes; +}; + void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries); bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc); u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, u32 max); @@ -47,6 +53,12 @@ static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool, xp_set_rxq_info(pool, rxq); } +static inline void xsk_pool_fill_cb(struct xsk_buff_pool *pool, + struct xsk_cb_desc *desc) +{ + xp_fill_cb(pool, desc); +} + static inline unsigned int xsk_pool_get_napi_id(struct xsk_buff_pool *pool) { #ifdef CONFIG_NET_RX_BUSY_POLL @@ -274,6 +286,11 @@ static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool, { } +static inline void xsk_pool_fill_cb(struct xsk_buff_pool *pool, + struct xsk_cb_desc *desc) +{ +} + static inline unsigned int xsk_pool_get_napi_id(struct xsk_buff_pool *pool) { return 0; diff --git a/include/net/xfrm.h b/include/net/xfrm.h index c9bb0f892f55..1d107241b901 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -2190,4 +2190,13 @@ static inline int register_xfrm_interface_bpf(void) #endif +#if IS_ENABLED(CONFIG_DEBUG_INFO_BTF) +int register_xfrm_state_bpf(void); +#else +static inline int register_xfrm_state_bpf(void) +{ + return 0; +} +#endif + #endif /* _NET_XFRM_H */ diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 8d48d37ab7c0..99dd7376df6a 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -12,6 +12,7 @@ struct xsk_buff_pool; struct xdp_rxq_info; +struct xsk_cb_desc; struct xsk_queue; struct xdp_desc; struct xdp_umem; @@ -135,6 +136,7 @@ static inline void xp_init_xskb_dma(struct xdp_buff_xsk *xskb, struct xsk_buff_p /* AF_XDP ZC drivers, via xdp_sock_buff.h */ void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq); +void xp_fill_cb(struct xsk_buff_pool *pool, struct xsk_cb_desc *desc); int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev, unsigned long attrs, struct page **pages, u32 nr_pages); void xp_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index b1e8c5bdfc82..42f4d3090efe 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -847,6 +847,36 @@ union bpf_iter_link_info { * Returns zero on success. On error, -1 is returned and *errno* * is set appropriately. * + * BPF_TOKEN_CREATE + * Description + * Create BPF token with embedded information about what + * BPF-related functionality it allows: + * - a set of allowed bpf() syscall commands; + * - a set of allowed BPF map types to be created with + * BPF_MAP_CREATE command, if BPF_MAP_CREATE itself is allowed; + * - a set of allowed BPF program types and BPF program attach + * types to be loaded with BPF_PROG_LOAD command, if + * BPF_PROG_LOAD itself is allowed. + * + * BPF token is created (derived) from an instance of BPF FS, + * assuming it has necessary delegation mount options specified. + * This BPF token can be passed as an extra parameter to various + * bpf() syscall commands to grant BPF subsystem functionality to + * unprivileged processes. + * + * When created, BPF token is "associated" with the owning + * user namespace of BPF FS instance (super block) that it was + * derived from, and subsequent BPF operations performed with + * BPF token would be performing capabilities checks (i.e., + * CAP_BPF, CAP_PERFMON, CAP_NET_ADMIN, CAP_SYS_ADMIN) within + * that user namespace. Without BPF token, such capabilities + * have to be granted in init user namespace, making bpf() + * syscall incompatible with user namespace, for the most part. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * * NOTES * eBPF objects (maps and programs) can be shared between processes. * @@ -901,6 +931,8 @@ enum bpf_cmd { BPF_ITER_CREATE, BPF_LINK_DETACH, BPF_PROG_BIND_MAP, + BPF_TOKEN_CREATE, + __MAX_BPF_CMD, }; enum bpf_map_type { @@ -951,6 +983,7 @@ enum bpf_map_type { BPF_MAP_TYPE_BLOOM_FILTER, BPF_MAP_TYPE_USER_RINGBUF, BPF_MAP_TYPE_CGRP_STORAGE, + __MAX_BPF_MAP_TYPE }; /* Note that tracing related programs such as @@ -995,6 +1028,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_SK_LOOKUP, BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */ BPF_PROG_TYPE_NETFILTER, + __MAX_BPF_PROG_TYPE }; enum bpf_attach_type { @@ -1074,9 +1108,11 @@ enum bpf_link_type { BPF_LINK_TYPE_TCX = 11, BPF_LINK_TYPE_UPROBE_MULTI = 12, BPF_LINK_TYPE_NETKIT = 13, - MAX_BPF_LINK_TYPE, + __MAX_BPF_LINK_TYPE, }; +#define MAX_BPF_LINK_TYPE __MAX_BPF_LINK_TYPE + enum bpf_perf_event_type { BPF_PERF_EVENT_UNSPEC = 0, BPF_PERF_EVENT_UPROBE = 1, @@ -1401,6 +1437,7 @@ union bpf_attr { * to using 5 hash functions). */ __u64 map_extra; + __u32 map_token_fd; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -1470,6 +1507,7 @@ union bpf_attr { * truncated), or smaller (if log buffer wasn't filled completely). */ __u32 log_true_size; + __u32 prog_token_fd; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -1582,6 +1620,7 @@ union bpf_attr { * truncated), or smaller (if log buffer wasn't filled completely). */ __u32 btf_log_true_size; + __u32 btf_token_fd; }; struct { @@ -1712,6 +1751,11 @@ union bpf_attr { __u32 flags; /* extra flags */ } prog_bind_map; + struct { /* struct used by BPF_TOKEN_CREATE command */ + __u32 flags; + __u32 bpffs_fd; + } token_create; + } __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index 424c5e28f495..93cb411adf72 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -44,10 +44,13 @@ enum netdev_xdp_act { * timestamp via bpf_xdp_metadata_rx_timestamp(). * @NETDEV_XDP_RX_METADATA_HASH: Device is capable of exposing receive packet * hash via bpf_xdp_metadata_rx_hash(). + * @NETDEV_XDP_RX_METADATA_VLAN_TAG: Device is capable of exposing receive + * packet VLAN tag via bpf_xdp_metadata_rx_vlan_tag(). */ enum netdev_xdp_rx_metadata { NETDEV_XDP_RX_METADATA_TIMESTAMP = 1, NETDEV_XDP_RX_METADATA_HASH = 2, + NETDEV_XDP_RX_METADATA_VLAN_TAG = 4, }; /** diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index f526b7573e97..4ce95acfcaa7 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -6,7 +6,7 @@ cflags-nogcse-$(CONFIG_X86)$(CONFIG_CC_IS_GCC) := -fno-gcse endif CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy) -obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o log.o +obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o log.o token.o obj-$(CONFIG_BPF_SYSCALL) += bpf_iter.o map_iter.o task_iter.o prog_iter.o link_iter.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o bloom_filter.o obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index c85ff9162a5c..13358675ff2e 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -82,7 +82,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY; int numa_node = bpf_map_attr_numa_node(attr); u32 elem_size, index_mask, max_entries; - bool bypass_spec_v1 = bpf_bypass_spec_v1(); + bool bypass_spec_v1 = bpf_bypass_spec_v1(NULL); u64 array_size, mask64; struct bpf_array *array; @@ -867,11 +867,11 @@ int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file, } if (old_ptr) - map->ops->map_fd_put_ptr(old_ptr); + map->ops->map_fd_put_ptr(map, old_ptr, true); return 0; } -static long fd_array_map_delete_elem(struct bpf_map *map, void *key) +static long __fd_array_map_delete_elem(struct bpf_map *map, void *key, bool need_defer) { struct bpf_array *array = container_of(map, struct bpf_array, map); void *old_ptr; @@ -890,13 +890,18 @@ static long fd_array_map_delete_elem(struct bpf_map *map, void *key) } if (old_ptr) { - map->ops->map_fd_put_ptr(old_ptr); + map->ops->map_fd_put_ptr(map, old_ptr, need_defer); return 0; } else { return -ENOENT; } } +static long fd_array_map_delete_elem(struct bpf_map *map, void *key) +{ + return __fd_array_map_delete_elem(map, key, true); +} + static void *prog_fd_array_get_ptr(struct bpf_map *map, struct file *map_file, int fd) { @@ -913,8 +918,9 @@ static void *prog_fd_array_get_ptr(struct bpf_map *map, return prog; } -static void prog_fd_array_put_ptr(void *ptr) +static void prog_fd_array_put_ptr(struct bpf_map *map, void *ptr, bool need_defer) { + /* bpf_prog is freed after one RCU or tasks trace grace period */ bpf_prog_put(ptr); } @@ -924,13 +930,13 @@ static u32 prog_fd_array_sys_lookup_elem(void *ptr) } /* decrement refcnt of all bpf_progs that are stored in this map */ -static void bpf_fd_array_map_clear(struct bpf_map *map) +static void bpf_fd_array_map_clear(struct bpf_map *map, bool need_defer) { struct bpf_array *array = container_of(map, struct bpf_array, map); int i; for (i = 0; i < array->map.max_entries; i++) - fd_array_map_delete_elem(map, &i); + __fd_array_map_delete_elem(map, &i, need_defer); } static void prog_array_map_seq_show_elem(struct bpf_map *map, void *key, @@ -1071,7 +1077,7 @@ static void prog_array_map_clear_deferred(struct work_struct *work) { struct bpf_map *map = container_of(work, struct bpf_array_aux, work)->map; - bpf_fd_array_map_clear(map); + bpf_fd_array_map_clear(map, true); bpf_map_put(map); } @@ -1151,7 +1157,7 @@ static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file, { struct bpf_event_entry *ee; - ee = kzalloc(sizeof(*ee), GFP_ATOMIC); + ee = kzalloc(sizeof(*ee), GFP_KERNEL); if (ee) { ee->event = perf_file->private_data; ee->perf_file = perf_file; @@ -1201,8 +1207,9 @@ err_out: return ee; } -static void perf_event_fd_array_put_ptr(void *ptr) +static void perf_event_fd_array_put_ptr(struct bpf_map *map, void *ptr, bool need_defer) { + /* bpf_perf_event is freed after one RCU grace period */ bpf_event_entry_free_rcu(ptr); } @@ -1220,7 +1227,7 @@ static void perf_event_fd_array_release(struct bpf_map *map, for (i = 0; i < array->map.max_entries; i++) { ee = READ_ONCE(array->ptrs[i]); if (ee && ee->map_file == map_file) - fd_array_map_delete_elem(map, &i); + __fd_array_map_delete_elem(map, &i, true); } rcu_read_unlock(); } @@ -1228,7 +1235,7 @@ static void perf_event_fd_array_release(struct bpf_map *map, static void perf_event_fd_array_map_free(struct bpf_map *map) { if (map->map_flags & BPF_F_PRESERVE_ELEMS) - bpf_fd_array_map_clear(map); + bpf_fd_array_map_clear(map, false); fd_array_map_free(map); } @@ -1256,7 +1263,7 @@ static void *cgroup_fd_array_get_ptr(struct bpf_map *map, return cgroup_get_from_fd(fd); } -static void cgroup_fd_array_put_ptr(void *ptr) +static void cgroup_fd_array_put_ptr(struct bpf_map *map, void *ptr, bool need_defer) { /* cgroup_put free cgrp after a rcu grace period */ cgroup_put(ptr); @@ -1264,7 +1271,7 @@ static void cgroup_fd_array_put_ptr(void *ptr) static void cgroup_fd_array_free(struct bpf_map *map) { - bpf_fd_array_map_clear(map); + bpf_fd_array_map_clear(map, false); fd_array_map_free(map); } @@ -1309,7 +1316,7 @@ static void array_of_map_free(struct bpf_map *map) * is protected by fdget/fdput. */ bpf_map_meta_free(map->inner_map_meta); - bpf_fd_array_map_clear(map); + bpf_fd_array_map_clear(map, false); fd_array_map_free(map); } diff --git a/kernel/bpf/bpf_cgrp_storage.c b/kernel/bpf/bpf_cgrp_storage.c index d44fe8dd9732..28efd0a3f220 100644 --- a/kernel/bpf/bpf_cgrp_storage.c +++ b/kernel/bpf/bpf_cgrp_storage.c @@ -82,7 +82,7 @@ static void *bpf_cgrp_storage_lookup_elem(struct bpf_map *map, void *key) int fd; fd = *(int *)key; - cgroup = cgroup_get_from_fd(fd); + cgroup = cgroup_v1v2_get_from_fd(fd); if (IS_ERR(cgroup)) return ERR_CAST(cgroup); @@ -101,7 +101,7 @@ static long bpf_cgrp_storage_update_elem(struct bpf_map *map, void *key, int fd; fd = *(int *)key; - cgroup = cgroup_get_from_fd(fd); + cgroup = cgroup_v1v2_get_from_fd(fd); if (IS_ERR(cgroup)) return PTR_ERR(cgroup); @@ -131,7 +131,7 @@ static long bpf_cgrp_storage_delete_elem(struct bpf_map *map, void *key) int err, fd; fd = *(int *)key; - cgroup = cgroup_get_from_fd(fd); + cgroup = cgroup_v1v2_get_from_fd(fd); if (IS_ERR(cgroup)) return PTR_ERR(cgroup); diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index e14c822f8911..63b4dc495125 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -260,9 +260,15 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) BTF_SET_START(sleepable_lsm_hooks) BTF_ID(func, bpf_lsm_bpf) BTF_ID(func, bpf_lsm_bpf_map) -BTF_ID(func, bpf_lsm_bpf_map_alloc_security) -BTF_ID(func, bpf_lsm_bpf_map_free_security) +BTF_ID(func, bpf_lsm_bpf_map_create) +BTF_ID(func, bpf_lsm_bpf_map_free) BTF_ID(func, bpf_lsm_bpf_prog) +BTF_ID(func, bpf_lsm_bpf_prog_load) +BTF_ID(func, bpf_lsm_bpf_prog_free) +BTF_ID(func, bpf_lsm_bpf_token_create) +BTF_ID(func, bpf_lsm_bpf_token_free) +BTF_ID(func, bpf_lsm_bpf_token_cmd) +BTF_ID(func, bpf_lsm_bpf_token_capable) BTF_ID(func, bpf_lsm_bprm_check_security) BTF_ID(func, bpf_lsm_bprm_committed_creds) BTF_ID(func, bpf_lsm_bprm_committing_creds) @@ -298,6 +304,18 @@ BTF_ID(func, bpf_lsm_kernel_module_request) BTF_ID(func, bpf_lsm_kernel_read_file) BTF_ID(func, bpf_lsm_kernfs_init_security) +#ifdef CONFIG_SECURITY_PATH +BTF_ID(func, bpf_lsm_path_unlink) +BTF_ID(func, bpf_lsm_path_mkdir) +BTF_ID(func, bpf_lsm_path_rmdir) +BTF_ID(func, bpf_lsm_path_truncate) +BTF_ID(func, bpf_lsm_path_symlink) +BTF_ID(func, bpf_lsm_path_link) +BTF_ID(func, bpf_lsm_path_rename) +BTF_ID(func, bpf_lsm_path_chmod) +BTF_ID(func, bpf_lsm_path_chown) +#endif /* CONFIG_SECURITY_PATH */ + #ifdef CONFIG_KEYS BTF_ID(func, bpf_lsm_key_free) #endif /* CONFIG_KEYS */ @@ -345,9 +363,8 @@ BTF_ID(func, bpf_lsm_userns_create) BTF_SET_END(sleepable_lsm_hooks) BTF_SET_START(untrusted_lsm_hooks) -BTF_ID(func, bpf_lsm_bpf_map_free_security) -BTF_ID(func, bpf_lsm_bpf_prog_alloc_security) -BTF_ID(func, bpf_lsm_bpf_prog_free_security) +BTF_ID(func, bpf_lsm_bpf_map_free) +BTF_ID(func, bpf_lsm_bpf_prog_free) BTF_ID(func, bpf_lsm_file_alloc_security) BTF_ID(func, bpf_lsm_file_free_security) #ifdef CONFIG_SECURITY_NETWORK diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index db6176fb64dc..02068bd0e4d9 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -352,18 +352,24 @@ const struct bpf_link_ops bpf_struct_ops_link_lops = { int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks, struct bpf_tramp_link *link, const struct btf_func_model *model, - void *image, void *image_end) + void *stub_func, void *image, void *image_end) { - u32 flags; + u32 flags = BPF_TRAMP_F_INDIRECT; + int size; tlinks[BPF_TRAMP_FENTRY].links[0] = link; tlinks[BPF_TRAMP_FENTRY].nr_links = 1; - /* BPF_TRAMP_F_RET_FENTRY_RET is only used by bpf_struct_ops, - * and it must be used alone. - */ - flags = model->ret_size > 0 ? BPF_TRAMP_F_RET_FENTRY_RET : 0; + + if (model->ret_size > 0) + flags |= BPF_TRAMP_F_RET_FENTRY_RET; + + size = arch_bpf_trampoline_size(model, flags, tlinks, NULL); + if (size < 0) + return size; + if (size > (unsigned long)image_end - (unsigned long)image) + return -E2BIG; return arch_prepare_bpf_trampoline(NULL, image, image_end, - model, flags, tlinks, NULL); + model, flags, tlinks, stub_func); } static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, @@ -497,11 +503,12 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, err = bpf_struct_ops_prepare_trampoline(tlinks, link, &st_ops->func_models[i], + *(void **)(st_ops->cfi_stubs + moff), image, image_end); if (err < 0) goto reset_unlock; - *(void **)(kdata + moff) = image; + *(void **)(kdata + moff) = image + cfi_get_offset(); image += err; /* put prog_id to udata */ @@ -515,7 +522,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, if (err) goto reset_unlock; } - set_memory_rox((long)st_map->image, 1); + arch_protect_bpf_trampoline(st_map->image, PAGE_SIZE); /* Let bpf_link handle registration & unregistration. * * Pair with smp_load_acquire() during lookup_elem(). @@ -524,7 +531,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, goto unlock; } - set_memory_rox((long)st_map->image, 1); + arch_protect_bpf_trampoline(st_map->image, PAGE_SIZE); err = st_ops->reg(kdata); if (likely(!err)) { /* This refcnt increment on the map here after @@ -547,8 +554,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, * there was a race in registering the struct_ops (under the same name) to * a sub-system through different struct_ops's maps. */ - set_memory_nx((long)st_map->image, 1); - set_memory_rw((long)st_map->image, 1); + arch_unprotect_bpf_trampoline(st_map->image, PAGE_SIZE); reset_unlock: bpf_struct_ops_map_put_progs(st_map); @@ -616,7 +622,7 @@ static void __bpf_struct_ops_map_free(struct bpf_map *map) bpf_struct_ops_map_put_progs(st_map); bpf_map_area_free(st_map->links); if (st_map->image) { - bpf_jit_free_exec(st_map->image); + arch_free_bpf_trampoline(st_map->image, PAGE_SIZE); bpf_jit_uncharge_modmem(PAGE_SIZE); } bpf_map_area_free(st_map->uvalue); @@ -691,7 +697,7 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) return ERR_PTR(ret); } - st_map->image = bpf_jit_alloc_exec(PAGE_SIZE); + st_map->image = arch_alloc_bpf_trampoline(PAGE_SIZE); if (!st_map->image) { /* __bpf_struct_ops_map_free() uses st_map->image as flag * for "charged or not". In this case, we need to unchange @@ -711,7 +717,6 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) } mutex_init(&st_map->lock); - set_vm_flush_reset_perms(st_map->image); bpf_map_init_from_attr(map, attr); return map; diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 63cf4128fc05..d56433bf8aba 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6956,7 +6956,7 @@ int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog, * (either PTR_TO_CTX or SCALAR_VALUE). */ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, - struct bpf_reg_state *regs, bool is_ex_cb) + struct bpf_reg_state *regs, u32 *arg_cnt) { struct bpf_verifier_log *log = &env->log; struct bpf_prog *prog = env->prog; @@ -7013,6 +7013,7 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, tname, nargs, MAX_BPF_FUNC_REG_ARGS); return -EINVAL; } + *arg_cnt = nargs; /* check that function returns int, exception cb also requires this */ t = btf_type_by_id(btf, t->type); while (btf_type_is_modifier(t)) @@ -7062,14 +7063,6 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, i, btf_type_str(t), tname); return -EINVAL; } - /* We have already ensured that the callback returns an integer, just - * like all global subprogs. We need to determine it only has a single - * scalar argument. - */ - if (is_ex_cb && (nargs != 1 || regs[BPF_REG_1].type != SCALAR_VALUE)) { - bpf_log(log, "exception cb only supports single integer argument\n"); - return -EINVAL; - } return 0; } diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 491d20038cbe..98e0e3835b28 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1630,7 +1630,7 @@ cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } @@ -2191,7 +2191,7 @@ sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } @@ -2348,7 +2348,7 @@ cg_sockopt_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index fe254ae035fe..14ace23d517b 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -121,6 +121,9 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag #endif INIT_LIST_HEAD_RCU(&fp->aux->ksym.lnode); +#ifdef CONFIG_FINEIBT + INIT_LIST_HEAD_RCU(&fp->aux->ksym_prefix.lnode); +#endif mutex_init(&fp->aux->used_maps_mutex); mutex_init(&fp->aux->dst_mutex); @@ -679,7 +682,7 @@ static bool bpf_prog_kallsyms_candidate(const struct bpf_prog *fp) void bpf_prog_kallsyms_add(struct bpf_prog *fp) { if (!bpf_prog_kallsyms_candidate(fp) || - !bpf_capable()) + !bpf_token_capable(fp->aux->token, CAP_BPF)) return; bpf_prog_ksym_set_addr(fp); @@ -687,6 +690,23 @@ void bpf_prog_kallsyms_add(struct bpf_prog *fp) fp->aux->ksym.prog = true; bpf_ksym_add(&fp->aux->ksym); + +#ifdef CONFIG_FINEIBT + /* + * When FineIBT, code in the __cfi_foo() symbols can get executed + * and hence unwinder needs help. + */ + if (cfi_mode != CFI_FINEIBT) + return; + + snprintf(fp->aux->ksym_prefix.name, KSYM_NAME_LEN, + "__cfi_%s", fp->aux->ksym.name); + + fp->aux->ksym_prefix.start = (unsigned long) fp->bpf_func - 16; + fp->aux->ksym_prefix.end = (unsigned long) fp->bpf_func; + + bpf_ksym_add(&fp->aux->ksym_prefix); +#endif } void bpf_prog_kallsyms_del(struct bpf_prog *fp) @@ -695,6 +715,11 @@ void bpf_prog_kallsyms_del(struct bpf_prog *fp) return; bpf_ksym_del(&fp->aux->ksym); +#ifdef CONFIG_FINEIBT + if (cfi_mode != CFI_FINEIBT) + return; + bpf_ksym_del(&fp->aux->ksym_prefix); +#endif } static struct bpf_ksym *bpf_ksym_find(unsigned long addr) @@ -932,20 +957,20 @@ out: return ptr; } -void bpf_prog_pack_free(struct bpf_binary_header *hdr) +void bpf_prog_pack_free(void *ptr, u32 size) { struct bpf_prog_pack *pack = NULL, *tmp; unsigned int nbits; unsigned long pos; mutex_lock(&pack_mutex); - if (hdr->size > BPF_PROG_PACK_SIZE) { - bpf_jit_free_exec(hdr); + if (size > BPF_PROG_PACK_SIZE) { + bpf_jit_free_exec(ptr); goto out; } list_for_each_entry(tmp, &pack_list, list) { - if ((void *)hdr >= tmp->ptr && (tmp->ptr + BPF_PROG_PACK_SIZE) > (void *)hdr) { + if (ptr >= tmp->ptr && (tmp->ptr + BPF_PROG_PACK_SIZE) > ptr) { pack = tmp; break; } @@ -954,10 +979,10 @@ void bpf_prog_pack_free(struct bpf_binary_header *hdr) if (WARN_ONCE(!pack, "bpf_prog_pack bug\n")) goto out; - nbits = BPF_PROG_SIZE_TO_NBITS(hdr->size); - pos = ((unsigned long)hdr - (unsigned long)pack->ptr) >> BPF_PROG_CHUNK_SHIFT; + nbits = BPF_PROG_SIZE_TO_NBITS(size); + pos = ((unsigned long)ptr - (unsigned long)pack->ptr) >> BPF_PROG_CHUNK_SHIFT; - WARN_ONCE(bpf_arch_text_invalidate(hdr, hdr->size), + WARN_ONCE(bpf_arch_text_invalidate(ptr, size), "bpf_prog_pack bug: missing bpf_arch_text_invalidate?\n"); bitmap_clear(pack->bitmap, pos, nbits); @@ -1104,8 +1129,7 @@ bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **image_ptr, *rw_header = kvmalloc(size, GFP_KERNEL); if (!*rw_header) { - bpf_arch_text_copy(&ro_header->size, &size, sizeof(size)); - bpf_prog_pack_free(ro_header); + bpf_prog_pack_free(ro_header, size); bpf_jit_uncharge_modmem(size); return NULL; } @@ -1136,7 +1160,7 @@ int bpf_jit_binary_pack_finalize(struct bpf_prog *prog, kvfree(rw_header); if (IS_ERR(ptr)) { - bpf_prog_pack_free(ro_header); + bpf_prog_pack_free(ro_header, ro_header->size); return PTR_ERR(ptr); } return 0; @@ -1157,7 +1181,7 @@ void bpf_jit_binary_pack_free(struct bpf_binary_header *ro_header, { u32 size = ro_header->size; - bpf_prog_pack_free(ro_header); + bpf_prog_pack_free(ro_header, size); kvfree(rw_header); bpf_jit_uncharge_modmem(size); } @@ -2668,12 +2692,16 @@ void __bpf_free_used_maps(struct bpf_prog_aux *aux, struct bpf_map **used_maps, u32 len) { struct bpf_map *map; + bool sleepable; u32 i; + sleepable = aux->sleepable; for (i = 0; i < len; i++) { map = used_maps[i]; if (map->ops->map_poke_untrack) map->ops->map_poke_untrack(map, aux); + if (sleepable) + atomic64_dec(&map->sleepable_refcnt); bpf_map_put(map); } } @@ -2751,6 +2779,7 @@ void bpf_prog_free(struct bpf_prog *fp) if (aux->dst_prog) bpf_prog_put(aux->dst_prog); + bpf_token_put(aux->token); INIT_WORK(&aux->work, bpf_prog_free_deferred); schedule_work(&aux->work); } diff --git a/kernel/bpf/cpumask.c b/kernel/bpf/cpumask.c index e01c741e54e7..2e73533a3811 100644 --- a/kernel/bpf/cpumask.c +++ b/kernel/bpf/cpumask.c @@ -96,6 +96,12 @@ __bpf_kfunc void bpf_cpumask_release(struct bpf_cpumask *cpumask) migrate_enable(); } +__bpf_kfunc void bpf_cpumask_release_dtor(void *cpumask) +{ + bpf_cpumask_release(cpumask); +} +CFI_NOSEAL(bpf_cpumask_release_dtor); + /** * bpf_cpumask_first() - Get the index of the first nonzero bit in the cpumask. * @cpumask: The cpumask being queried. @@ -405,6 +411,17 @@ __bpf_kfunc u32 bpf_cpumask_any_and_distribute(const struct cpumask *src1, return cpumask_any_and_distribute(src1, src2); } +/** + * bpf_cpumask_weight() - Return the number of bits in @cpumask. + * @cpumask: The cpumask being queried. + * + * Count the number of set bits in the given cpumask. + */ +__bpf_kfunc u32 bpf_cpumask_weight(const struct cpumask *cpumask) +{ + return cpumask_weight(cpumask); +} + __bpf_kfunc_end_defs(); BTF_SET8_START(cpumask_kfunc_btf_ids) @@ -432,6 +449,7 @@ BTF_ID_FLAGS(func, bpf_cpumask_full, KF_RCU) BTF_ID_FLAGS(func, bpf_cpumask_copy, KF_RCU) BTF_ID_FLAGS(func, bpf_cpumask_any_distribute, KF_RCU) BTF_ID_FLAGS(func, bpf_cpumask_any_and_distribute, KF_RCU) +BTF_ID_FLAGS(func, bpf_cpumask_weight, KF_RCU) BTF_SET8_END(cpumask_kfunc_btf_ids) static const struct btf_kfunc_id_set cpumask_kfunc_set = { @@ -441,7 +459,7 @@ static const struct btf_kfunc_id_set cpumask_kfunc_set = { BTF_ID_LIST(cpumask_dtor_ids) BTF_ID(struct, bpf_cpumask) -BTF_ID(func, bpf_cpumask_release) +BTF_ID(func, bpf_cpumask_release_dtor) static int __init cpumask_kfunc_init(void) { diff --git a/kernel/bpf/dispatcher.c b/kernel/bpf/dispatcher.c index fa3e9225aedc..70fb82bf1637 100644 --- a/kernel/bpf/dispatcher.c +++ b/kernel/bpf/dispatcher.c @@ -150,14 +150,11 @@ void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, goto out; d->rw_image = bpf_jit_alloc_exec(PAGE_SIZE); if (!d->rw_image) { - u32 size = PAGE_SIZE; - - bpf_arch_text_copy(d->image, &size, sizeof(size)); - bpf_prog_pack_free((struct bpf_binary_header *)d->image); + bpf_prog_pack_free(d->image, PAGE_SIZE); d->image = NULL; goto out; } - bpf_image_ksym_add(d->image, &d->ksym); + bpf_image_ksym_add(d->image, PAGE_SIZE, &d->ksym); } prev_num_progs = d->num_progs; diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index fd8d4b0addfc..ec3bdcc6a3cf 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -897,7 +897,7 @@ static void htab_put_fd_value(struct bpf_htab *htab, struct htab_elem *l) if (map->ops->map_fd_put_ptr) { ptr = fd_htab_map_get_ptr(map, l); - map->ops->map_fd_put_ptr(ptr); + map->ops->map_fd_put_ptr(map, ptr, true); } } @@ -2484,7 +2484,7 @@ static void fd_htab_map_free(struct bpf_map *map) hlist_nulls_for_each_entry_safe(l, n, head, hash_node) { void *ptr = fd_htab_map_get_ptr(map, l); - map->ops->map_fd_put_ptr(ptr); + map->ops->map_fd_put_ptr(map, ptr, false); } } @@ -2523,9 +2523,15 @@ int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file, if (IS_ERR(ptr)) return PTR_ERR(ptr); + /* The htab bucket lock is always held during update operations in fd + * htab map, and the following rcu_read_lock() is only used to avoid + * the WARN_ON_ONCE in htab_map_update_elem(). + */ + rcu_read_lock(); ret = htab_map_update_elem(map, key, &ptr, map_flags); + rcu_read_unlock(); if (ret) - map->ops->map_fd_put_ptr(ptr); + map->ops->map_fd_put_ptr(map, ptr, false); return ret; } diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index b45a8381f9bd..07fd4b5704f3 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -32,12 +32,13 @@ * * Different map implementations will rely on rcu in map methods * lookup/update/delete, therefore eBPF programs must run under rcu lock - * if program is allowed to access maps, so check rcu_read_lock_held in - * all three functions. + * if program is allowed to access maps, so check rcu_read_lock_held() or + * rcu_read_lock_trace_held() in all three functions. */ BPF_CALL_2(bpf_map_lookup_elem, struct bpf_map *, map, void *, key) { - WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); + WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() && + !rcu_read_lock_bh_held()); return (unsigned long) map->ops->map_lookup_elem(map, key); } @@ -53,7 +54,8 @@ const struct bpf_func_proto bpf_map_lookup_elem_proto = { BPF_CALL_4(bpf_map_update_elem, struct bpf_map *, map, void *, key, void *, value, u64, flags) { - WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); + WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() && + !rcu_read_lock_bh_held()); return map->ops->map_update_elem(map, key, value, flags); } @@ -70,7 +72,8 @@ const struct bpf_func_proto bpf_map_update_elem_proto = { BPF_CALL_2(bpf_map_delete_elem, struct bpf_map *, map, void *, key) { - WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); + WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() && + !rcu_read_lock_bh_held()); return map->ops->map_delete_elem(map, key); } @@ -1676,7 +1679,7 @@ const struct bpf_func_proto bpf_probe_read_kernel_str_proto __weak; const struct bpf_func_proto bpf_task_pt_regs_proto __weak; const struct bpf_func_proto * -bpf_base_func_proto(enum bpf_func_id func_id) +bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_map_lookup_elem: @@ -1727,7 +1730,7 @@ bpf_base_func_proto(enum bpf_func_id func_id) break; } - if (!bpf_capable()) + if (!bpf_token_capable(prog->aux->token, CAP_BPF)) return NULL; switch (func_id) { @@ -1785,7 +1788,7 @@ bpf_base_func_proto(enum bpf_func_id func_id) break; } - if (!perfmon_capable()) + if (!bpf_token_capable(prog->aux->token, CAP_PERFMON)) return NULL; switch (func_id) { @@ -2147,6 +2150,12 @@ __bpf_kfunc void bpf_task_release(struct task_struct *p) put_task_struct_rcu_user(p); } +__bpf_kfunc void bpf_task_release_dtor(void *p) +{ + put_task_struct_rcu_user(p); +} +CFI_NOSEAL(bpf_task_release_dtor); + #ifdef CONFIG_CGROUPS /** * bpf_cgroup_acquire - Acquire a reference to a cgroup. A cgroup acquired by @@ -2171,6 +2180,12 @@ __bpf_kfunc void bpf_cgroup_release(struct cgroup *cgrp) cgroup_put(cgrp); } +__bpf_kfunc void bpf_cgroup_release_dtor(void *cgrp) +{ + cgroup_put(cgrp); +} +CFI_NOSEAL(bpf_cgroup_release_dtor); + /** * bpf_cgroup_ancestor - Perform a lookup on an entry in a cgroup's ancestor * array. A cgroup returned by this kfunc which is not subsequently stored in a @@ -2522,7 +2537,7 @@ __bpf_kfunc void bpf_throw(u64 cookie) * which skips compiler generated instrumentation to do the same. */ kasan_unpoison_task_stack_below((void *)(long)ctx.sp); - ctx.aux->bpf_exception_cb(cookie, ctx.sp, ctx.bp); + ctx.aux->bpf_exception_cb(cookie, ctx.sp, ctx.bp, 0, 0); WARN(1, "A call to BPF exception callback should never return\n"); } @@ -2567,10 +2582,10 @@ static const struct btf_kfunc_id_set generic_kfunc_set = { BTF_ID_LIST(generic_dtor_ids) BTF_ID(struct, task_struct) -BTF_ID(func, bpf_task_release) +BTF_ID(func, bpf_task_release_dtor) #ifdef CONFIG_CGROUPS BTF_ID(struct, cgroup) -BTF_ID(func, bpf_cgroup_release) +BTF_ID(func, bpf_cgroup_release_dtor) #endif BTF_SET8_START(common_btf_ids) @@ -2627,6 +2642,7 @@ static int __init kfunc_init(void) ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &generic_kfunc_set); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &generic_kfunc_set); + ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &generic_kfunc_set); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &generic_kfunc_set); ret = ret ?: register_btf_id_dtor_kfuncs(generic_dtors, ARRAY_SIZE(generic_dtors), diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 1aafb2ff2e95..4383b3d13a55 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -20,6 +20,7 @@ #include <linux/filter.h> #include <linux/bpf.h> #include <linux/bpf_trace.h> +#include <linux/kstrtox.h> #include "preload/bpf_preload.h" enum bpf_type { @@ -98,9 +99,9 @@ static const struct inode_operations bpf_prog_iops = { }; static const struct inode_operations bpf_map_iops = { }; static const struct inode_operations bpf_link_iops = { }; -static struct inode *bpf_get_inode(struct super_block *sb, - const struct inode *dir, - umode_t mode) +struct inode *bpf_get_inode(struct super_block *sb, + const struct inode *dir, + umode_t mode) { struct inode *inode; @@ -594,15 +595,183 @@ struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type typ } EXPORT_SYMBOL(bpf_prog_get_type_path); +struct bpffs_btf_enums { + const struct btf *btf; + const struct btf_type *cmd_t; + const struct btf_type *map_t; + const struct btf_type *prog_t; + const struct btf_type *attach_t; +}; + +static int find_bpffs_btf_enums(struct bpffs_btf_enums *info) +{ + const struct btf *btf; + const struct btf_type *t; + const char *name; + int i, n; + + memset(info, 0, sizeof(*info)); + + btf = bpf_get_btf_vmlinux(); + if (IS_ERR(btf)) + return PTR_ERR(btf); + if (!btf) + return -ENOENT; + + info->btf = btf; + + for (i = 1, n = btf_nr_types(btf); i < n; i++) { + t = btf_type_by_id(btf, i); + if (!btf_type_is_enum(t)) + continue; + + name = btf_name_by_offset(btf, t->name_off); + if (!name) + continue; + + if (strcmp(name, "bpf_cmd") == 0) + info->cmd_t = t; + else if (strcmp(name, "bpf_map_type") == 0) + info->map_t = t; + else if (strcmp(name, "bpf_prog_type") == 0) + info->prog_t = t; + else if (strcmp(name, "bpf_attach_type") == 0) + info->attach_t = t; + else + continue; + + if (info->cmd_t && info->map_t && info->prog_t && info->attach_t) + return 0; + } + + return -ESRCH; +} + +static bool find_btf_enum_const(const struct btf *btf, const struct btf_type *enum_t, + const char *prefix, const char *str, int *value) +{ + const struct btf_enum *e; + const char *name; + int i, n, pfx_len = strlen(prefix); + + *value = 0; + + if (!btf || !enum_t) + return false; + + for (i = 0, n = btf_vlen(enum_t); i < n; i++) { + e = &btf_enum(enum_t)[i]; + + name = btf_name_by_offset(btf, e->name_off); + if (!name || strncasecmp(name, prefix, pfx_len) != 0) + continue; + + /* match symbolic name case insensitive and ignoring prefix */ + if (strcasecmp(name + pfx_len, str) == 0) { + *value = e->val; + return true; + } + } + + return false; +} + +static void seq_print_delegate_opts(struct seq_file *m, + const char *opt_name, + const struct btf *btf, + const struct btf_type *enum_t, + const char *prefix, + u64 delegate_msk, u64 any_msk) +{ + const struct btf_enum *e; + bool first = true; + const char *name; + u64 msk; + int i, n, pfx_len = strlen(prefix); + + delegate_msk &= any_msk; /* clear unknown bits */ + + if (delegate_msk == 0) + return; + + seq_printf(m, ",%s", opt_name); + if (delegate_msk == any_msk) { + seq_printf(m, "=any"); + return; + } + + if (btf && enum_t) { + for (i = 0, n = btf_vlen(enum_t); i < n; i++) { + e = &btf_enum(enum_t)[i]; + name = btf_name_by_offset(btf, e->name_off); + if (!name || strncasecmp(name, prefix, pfx_len) != 0) + continue; + msk = 1ULL << e->val; + if (delegate_msk & msk) { + /* emit lower-case name without prefix */ + seq_printf(m, "%c", first ? '=' : ':'); + name += pfx_len; + while (*name) { + seq_printf(m, "%c", tolower(*name)); + name++; + } + + delegate_msk &= ~msk; + first = false; + } + } + } + if (delegate_msk) + seq_printf(m, "%c0x%llx", first ? '=' : ':', delegate_msk); +} + /* * Display the mount options in /proc/mounts. */ static int bpf_show_options(struct seq_file *m, struct dentry *root) { - umode_t mode = d_inode(root)->i_mode & S_IALLUGO & ~S_ISVTX; - + struct bpf_mount_opts *opts = root->d_sb->s_fs_info; + struct inode *inode = d_inode(root); + umode_t mode = inode->i_mode & S_IALLUGO & ~S_ISVTX; + u64 mask; + + if (!uid_eq(inode->i_uid, GLOBAL_ROOT_UID)) + seq_printf(m, ",uid=%u", + from_kuid_munged(&init_user_ns, inode->i_uid)); + if (!gid_eq(inode->i_gid, GLOBAL_ROOT_GID)) + seq_printf(m, ",gid=%u", + from_kgid_munged(&init_user_ns, inode->i_gid)); if (mode != S_IRWXUGO) seq_printf(m, ",mode=%o", mode); + + if (opts->delegate_cmds || opts->delegate_maps || + opts->delegate_progs || opts->delegate_attachs) { + struct bpffs_btf_enums info; + + /* ignore errors, fallback to hex */ + (void)find_bpffs_btf_enums(&info); + + mask = (1ULL << __MAX_BPF_CMD) - 1; + seq_print_delegate_opts(m, "delegate_cmds", + info.btf, info.cmd_t, "BPF_", + opts->delegate_cmds, mask); + + mask = (1ULL << __MAX_BPF_MAP_TYPE) - 1; + seq_print_delegate_opts(m, "delegate_maps", + info.btf, info.map_t, "BPF_MAP_TYPE_", + opts->delegate_maps, mask); + + mask = (1ULL << __MAX_BPF_PROG_TYPE) - 1; + seq_print_delegate_opts(m, "delegate_progs", + info.btf, info.prog_t, "BPF_PROG_TYPE_", + opts->delegate_progs, mask); + + mask = (1ULL << __MAX_BPF_ATTACH_TYPE) - 1; + seq_print_delegate_opts(m, "delegate_attachs", + info.btf, info.attach_t, "BPF_", + opts->delegate_attachs, mask); + } + return 0; } @@ -617,7 +786,7 @@ static void bpf_free_inode(struct inode *inode) free_inode_nonrcu(inode); } -static const struct super_operations bpf_super_ops = { +const struct super_operations bpf_super_ops = { .statfs = simple_statfs, .drop_inode = generic_delete_inode, .show_options = bpf_show_options, @@ -625,23 +794,33 @@ static const struct super_operations bpf_super_ops = { }; enum { + OPT_UID, + OPT_GID, OPT_MODE, + OPT_DELEGATE_CMDS, + OPT_DELEGATE_MAPS, + OPT_DELEGATE_PROGS, + OPT_DELEGATE_ATTACHS, }; static const struct fs_parameter_spec bpf_fs_parameters[] = { + fsparam_u32 ("uid", OPT_UID), + fsparam_u32 ("gid", OPT_GID), fsparam_u32oct ("mode", OPT_MODE), + fsparam_string ("delegate_cmds", OPT_DELEGATE_CMDS), + fsparam_string ("delegate_maps", OPT_DELEGATE_MAPS), + fsparam_string ("delegate_progs", OPT_DELEGATE_PROGS), + fsparam_string ("delegate_attachs", OPT_DELEGATE_ATTACHS), {} }; -struct bpf_mount_opts { - umode_t mode; -}; - static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param) { - struct bpf_mount_opts *opts = fc->fs_private; + struct bpf_mount_opts *opts = fc->s_fs_info; struct fs_parse_result result; - int opt; + kuid_t uid; + kgid_t gid; + int opt, err; opt = fs_parse(fc, bpf_fs_parameters, param, &result); if (opt < 0) { @@ -662,12 +841,104 @@ static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param) } switch (opt) { + case OPT_UID: + uid = make_kuid(current_user_ns(), result.uint_32); + if (!uid_valid(uid)) + goto bad_value; + + /* + * The requested uid must be representable in the + * filesystem's idmapping. + */ + if (!kuid_has_mapping(fc->user_ns, uid)) + goto bad_value; + + opts->uid = uid; + break; + case OPT_GID: + gid = make_kgid(current_user_ns(), result.uint_32); + if (!gid_valid(gid)) + goto bad_value; + + /* + * The requested gid must be representable in the + * filesystem's idmapping. + */ + if (!kgid_has_mapping(fc->user_ns, gid)) + goto bad_value; + + opts->gid = gid; + break; case OPT_MODE: opts->mode = result.uint_32 & S_IALLUGO; break; + case OPT_DELEGATE_CMDS: + case OPT_DELEGATE_MAPS: + case OPT_DELEGATE_PROGS: + case OPT_DELEGATE_ATTACHS: { + struct bpffs_btf_enums info; + const struct btf_type *enum_t; + const char *enum_pfx; + u64 *delegate_msk, msk = 0; + char *p; + int val; + + /* ignore errors, fallback to hex */ + (void)find_bpffs_btf_enums(&info); + + switch (opt) { + case OPT_DELEGATE_CMDS: + delegate_msk = &opts->delegate_cmds; + enum_t = info.cmd_t; + enum_pfx = "BPF_"; + break; + case OPT_DELEGATE_MAPS: + delegate_msk = &opts->delegate_maps; + enum_t = info.map_t; + enum_pfx = "BPF_MAP_TYPE_"; + break; + case OPT_DELEGATE_PROGS: + delegate_msk = &opts->delegate_progs; + enum_t = info.prog_t; + enum_pfx = "BPF_PROG_TYPE_"; + break; + case OPT_DELEGATE_ATTACHS: + delegate_msk = &opts->delegate_attachs; + enum_t = info.attach_t; + enum_pfx = "BPF_"; + break; + default: + return -EINVAL; + } + + while ((p = strsep(¶m->string, ":"))) { + if (strcmp(p, "any") == 0) { + msk |= ~0ULL; + } else if (find_btf_enum_const(info.btf, enum_t, enum_pfx, p, &val)) { + msk |= 1ULL << val; + } else { + err = kstrtou64(p, 0, &msk); + if (err) + return err; + } + } + + /* Setting delegation mount options requires privileges */ + if (msk && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + *delegate_msk |= msk; + break; + } + default: + /* ignore unknown mount options */ + break; } return 0; + +bad_value: + return invalfc(fc, "Bad value for '%s'", param->key); } struct bpf_preload_ops *bpf_preload_ops; @@ -739,10 +1010,14 @@ out: static int bpf_fill_super(struct super_block *sb, struct fs_context *fc) { static const struct tree_descr bpf_rfiles[] = { { "" } }; - struct bpf_mount_opts *opts = fc->fs_private; + struct bpf_mount_opts *opts = sb->s_fs_info; struct inode *inode; int ret; + /* Mounting an instance of BPF FS requires privileges */ + if (fc->user_ns != &init_user_ns && !capable(CAP_SYS_ADMIN)) + return -EPERM; + ret = simple_fill_super(sb, BPF_FS_MAGIC, bpf_rfiles); if (ret) return ret; @@ -750,6 +1025,8 @@ static int bpf_fill_super(struct super_block *sb, struct fs_context *fc) sb->s_op = &bpf_super_ops; inode = sb->s_root->d_inode; + inode->i_uid = opts->uid; + inode->i_gid = opts->gid; inode->i_op = &bpf_dir_iops; inode->i_mode &= ~S_IALLUGO; populate_bpffs(sb->s_root); @@ -764,7 +1041,7 @@ static int bpf_get_tree(struct fs_context *fc) static void bpf_free_fc(struct fs_context *fc) { - kfree(fc->fs_private); + kfree(fc->s_fs_info); } static const struct fs_context_operations bpf_context_ops = { @@ -785,18 +1062,35 @@ static int bpf_init_fs_context(struct fs_context *fc) return -ENOMEM; opts->mode = S_IRWXUGO; + opts->uid = current_fsuid(); + opts->gid = current_fsgid(); + + /* start out with no BPF token delegation enabled */ + opts->delegate_cmds = 0; + opts->delegate_maps = 0; + opts->delegate_progs = 0; + opts->delegate_attachs = 0; - fc->fs_private = opts; + fc->s_fs_info = opts; fc->ops = &bpf_context_ops; return 0; } +static void bpf_kill_super(struct super_block *sb) +{ + struct bpf_mount_opts *opts = sb->s_fs_info; + + kill_litter_super(sb); + kfree(opts); +} + static struct file_system_type bpf_fs_type = { .owner = THIS_MODULE, .name = "bpf", .init_fs_context = bpf_init_fs_context, .parameters = bpf_fs_parameters, - .kill_sb = kill_litter_super, + .kill_sb = bpf_kill_super, + .fs_flags = FS_USERNS_MOUNT, }; static int __init bpf_init(void) diff --git a/kernel/bpf/log.c b/kernel/bpf/log.c index 3505f3e5ae96..594a234f122b 100644 --- a/kernel/bpf/log.c +++ b/kernel/bpf/log.c @@ -539,6 +539,19 @@ static void verbose_snum(struct bpf_verifier_env *env, s64 num) verbose(env, "%#llx", num); } +int tnum_strn(char *str, size_t size, struct tnum a) +{ + /* print as a constant, if tnum is fully known */ + if (a.mask == 0) { + if (is_unum_decimal(a.value)) + return snprintf(str, size, "%llu", a.value); + else + return snprintf(str, size, "%#llx", a.value); + } + return snprintf(str, size, "(%#llx; %#llx)", a.value, a.mask); +} +EXPORT_SYMBOL_GPL(tnum_strn); + static void print_scalar_ranges(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, const char **sep) @@ -615,6 +628,12 @@ static bool type_is_map_ptr(enum bpf_reg_type t) { } } +/* + * _a stands for append, was shortened to avoid multiline statements below. + * This macro is used to output a comma separated list of attributes. + */ +#define verbose_a(fmt, ...) ({ verbose(env, "%s" fmt, sep, ##__VA_ARGS__); sep = ","; }) + static void print_reg_state(struct bpf_verifier_env *env, const struct bpf_func_state *state, const struct bpf_reg_state *reg) @@ -630,11 +649,6 @@ static void print_reg_state(struct bpf_verifier_env *env, verbose_snum(env, reg->var_off.value + reg->off); return; } -/* - * _a stands for append, was shortened to avoid multiline statements below. - * This macro is used to output a comma separated list of attributes. - */ -#define verbose_a(fmt, ...) ({ verbose(env, "%s" fmt, sep, ##__VA_ARGS__); sep = ","; }) verbose(env, "%s", reg_type_str(env, t)); if (t == PTR_TO_STACK) { @@ -669,6 +683,12 @@ static void print_reg_state(struct bpf_verifier_env *env, verbose_a("r="); verbose_unum(env, reg->range); } + if (base_type(t) == PTR_TO_MEM) { + verbose_a("sz="); + verbose_unum(env, reg->mem_size); + } + if (t == CONST_PTR_TO_DYNPTR) + verbose_a("type=%s", dynptr_type_str(reg->dynptr.type)); if (tnum_is_const(reg->var_off)) { /* a pointer register with fixed offset */ if (reg->var_off.value) { @@ -685,8 +705,6 @@ static void print_reg_state(struct bpf_verifier_env *env, } } verbose(env, ")"); - -#undef verbose_a } void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_func_state *state, @@ -710,6 +728,7 @@ void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_func_st } for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { char types_buf[BPF_REG_SIZE + 1]; + const char *sep = ""; bool valid = false; u8 slot_type; int j; @@ -748,9 +767,14 @@ void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_func_st verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); print_liveness(env, reg->live); - verbose(env, "=dynptr_%s", dynptr_type_str(reg->dynptr.type)); + verbose(env, "=dynptr_%s(", dynptr_type_str(reg->dynptr.type)); + if (reg->id) + verbose_a("id=%d", reg->id); if (reg->ref_obj_id) - verbose(env, "(ref_id=%d)", reg->ref_obj_id); + verbose_a("ref_id=%d", reg->ref_obj_id); + if (reg->dynptr_id) + verbose_a("dynptr_id=%d", reg->dynptr_id); + verbose(env, ")"); break; case STACK_ITER: /* only main slot has ref_obj_id set; skip others */ diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c index cd5eafaba97e..8ef269e66ba5 100644 --- a/kernel/bpf/map_in_map.c +++ b/kernel/bpf/map_in_map.c @@ -127,12 +127,21 @@ void *bpf_map_fd_get_ptr(struct bpf_map *map, return inner_map; } -void bpf_map_fd_put_ptr(void *ptr) +void bpf_map_fd_put_ptr(struct bpf_map *map, void *ptr, bool need_defer) { - /* ptr->ops->map_free() has to go through one - * rcu grace period by itself. + struct bpf_map *inner_map = ptr; + + /* Defer the freeing of inner map according to the sleepable attribute + * of bpf program which owns the outer map, so unnecessary waiting for + * RCU tasks trace grace period can be avoided. */ - bpf_map_put(ptr); + if (need_defer) { + if (atomic64_read(&map->sleepable_refcnt)) + WRITE_ONCE(inner_map->free_after_mult_rcu_gp, true); + else + WRITE_ONCE(inner_map->free_after_rcu_gp, true); + } + bpf_map_put(inner_map); } u32 bpf_map_fd_sys_lookup_elem(void *ptr) diff --git a/kernel/bpf/map_in_map.h b/kernel/bpf/map_in_map.h index bcb7534afb3c..7d61602354de 100644 --- a/kernel/bpf/map_in_map.h +++ b/kernel/bpf/map_in_map.h @@ -13,7 +13,7 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd); void bpf_map_meta_free(struct bpf_map *map_meta); void *bpf_map_fd_get_ptr(struct bpf_map *map, struct file *map_file, int ufd); -void bpf_map_fd_put_ptr(void *ptr); +void bpf_map_fd_put_ptr(struct bpf_map *map, void *ptr, bool need_defer); u32 bpf_map_fd_sys_lookup_elem(void *ptr); #endif diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 5e43ddd1b83f..8faa1a20edf8 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -142,9 +142,13 @@ static u32 bpf_map_value_size(const struct bpf_map *map) static void maybe_wait_bpf_programs(struct bpf_map *map) { - /* Wait for any running BPF programs to complete so that - * userspace, when we return to it, knows that all programs - * that could be running use the new map value. + /* Wait for any running non-sleepable BPF programs to complete so that + * userspace, when we return to it, knows that all non-sleepable + * programs that could be running use the new map value. For sleepable + * BPF programs, synchronize_rcu_tasks_trace() should be used to wait + * for the completions of these programs, but considering the waiting + * time can be very long and userspace may think it will hang forever, + * so don't handle sleepable BPF programs now. */ if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS || map->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS) @@ -180,15 +184,11 @@ static int bpf_map_update_value(struct bpf_map *map, struct file *map_file, err = bpf_percpu_cgroup_storage_update(map, key, value, flags); } else if (IS_FD_ARRAY(map)) { - rcu_read_lock(); err = bpf_fd_array_map_update_elem(map, map_file, key, value, flags); - rcu_read_unlock(); } else if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) { - rcu_read_lock(); err = bpf_fd_htab_map_update_elem(map, map_file, key, value, flags); - rcu_read_unlock(); } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { /* rcu_read_lock() is not needed */ err = bpf_fd_reuseport_array_update_elem(map, key, value, @@ -203,7 +203,6 @@ static int bpf_map_update_value(struct bpf_map *map, struct file *map_file, rcu_read_unlock(); } bpf_enable_instrumentation(); - maybe_wait_bpf_programs(map); return err; } @@ -264,7 +263,6 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value, } bpf_enable_instrumentation(); - maybe_wait_bpf_programs(map); return err; } @@ -694,6 +692,7 @@ static void bpf_map_free_deferred(struct work_struct *work) { struct bpf_map *map = container_of(work, struct bpf_map, work); struct btf_record *rec = map->record; + struct btf *btf = map->btf; security_bpf_map_free(map); bpf_map_release_memcg(map); @@ -709,6 +708,10 @@ static void bpf_map_free_deferred(struct work_struct *work) * template bpf_map struct used during verification. */ btf_record_free(rec); + /* Delay freeing of btf for maps, as map_free callback may need + * struct_meta info which will be freed with btf_put(). + */ + btf_put(btf); } static void bpf_map_put_uref(struct bpf_map *map) @@ -719,6 +722,28 @@ static void bpf_map_put_uref(struct bpf_map *map) } } +static void bpf_map_free_in_work(struct bpf_map *map) +{ + INIT_WORK(&map->work, bpf_map_free_deferred); + /* Avoid spawning kworkers, since they all might contend + * for the same mutex like slab_mutex. + */ + queue_work(system_unbound_wq, &map->work); +} + +static void bpf_map_free_rcu_gp(struct rcu_head *rcu) +{ + bpf_map_free_in_work(container_of(rcu, struct bpf_map, rcu)); +} + +static void bpf_map_free_mult_rcu_gp(struct rcu_head *rcu) +{ + if (rcu_trace_implies_rcu_gp()) + bpf_map_free_rcu_gp(rcu); + else + call_rcu(rcu, bpf_map_free_rcu_gp); +} + /* decrement map refcnt and schedule it for freeing via workqueue * (underlying map implementation ops->map_free() might sleep) */ @@ -727,12 +752,14 @@ void bpf_map_put(struct bpf_map *map) if (atomic64_dec_and_test(&map->refcnt)) { /* bpf_map_free_id() must be called first */ bpf_map_free_id(map); - btf_put(map->btf); - INIT_WORK(&map->work, bpf_map_free_deferred); - /* Avoid spawning kworkers, since they all might contend - * for the same mutex like slab_mutex. - */ - queue_work(system_unbound_wq, &map->work); + + WARN_ON_ONCE(atomic64_read(&map->sleepable_refcnt)); + if (READ_ONCE(map->free_after_mult_rcu_gp)) + call_rcu_tasks_trace(&map->rcu, bpf_map_free_mult_rcu_gp); + else if (READ_ONCE(map->free_after_rcu_gp)) + call_rcu(&map->rcu, bpf_map_free_rcu_gp); + else + bpf_map_free_in_work(map); } } EXPORT_SYMBOL_GPL(bpf_map_put); @@ -984,8 +1011,8 @@ int map_check_no_btf(const struct bpf_map *map, return -ENOTSUPP; } -static int map_check_btf(struct bpf_map *map, const struct btf *btf, - u32 btf_key_id, u32 btf_value_id) +static int map_check_btf(struct bpf_map *map, struct bpf_token *token, + const struct btf *btf, u32 btf_key_id, u32 btf_value_id) { const struct btf_type *key_type, *value_type; u32 key_size, value_size; @@ -1013,7 +1040,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, if (!IS_ERR_OR_NULL(map->record)) { int i; - if (!bpf_capable()) { + if (!bpf_token_capable(token, CAP_BPF)) { ret = -EPERM; goto free_map_tab; } @@ -1096,11 +1123,17 @@ free_map_tab: return ret; } -#define BPF_MAP_CREATE_LAST_FIELD map_extra +static bool bpf_net_capable(void) +{ + return capable(CAP_NET_ADMIN) || capable(CAP_SYS_ADMIN); +} + +#define BPF_MAP_CREATE_LAST_FIELD map_token_fd /* called via syscall */ static int map_create(union bpf_attr *attr) { const struct bpf_map_ops *ops; + struct bpf_token *token = NULL; int numa_node = bpf_map_attr_numa_node(attr); u32 map_type = attr->map_type; struct bpf_map *map; @@ -1151,14 +1184,32 @@ static int map_create(union bpf_attr *attr) if (!ops->map_mem_usage) return -EINVAL; + if (attr->map_token_fd) { + token = bpf_token_get_from_fd(attr->map_token_fd); + if (IS_ERR(token)) + return PTR_ERR(token); + + /* if current token doesn't grant map creation permissions, + * then we can't use this token, so ignore it and rely on + * system-wide capabilities checks + */ + if (!bpf_token_allow_cmd(token, BPF_MAP_CREATE) || + !bpf_token_allow_map_type(token, attr->map_type)) { + bpf_token_put(token); + token = NULL; + } + } + + err = -EPERM; + /* Intent here is for unprivileged_bpf_disabled to block BPF map * creation for unprivileged users; other actions depend * on fd availability and access to bpffs, so are dependent on * object creation success. Even with unprivileged BPF disabled, * capability checks are still carried out. */ - if (sysctl_unprivileged_bpf_disabled && !bpf_capable()) - return -EPERM; + if (sysctl_unprivileged_bpf_disabled && !bpf_token_capable(token, CAP_BPF)) + goto put_token; /* check privileged map type permissions */ switch (map_type) { @@ -1191,25 +1242,27 @@ static int map_create(union bpf_attr *attr) case BPF_MAP_TYPE_LRU_PERCPU_HASH: case BPF_MAP_TYPE_STRUCT_OPS: case BPF_MAP_TYPE_CPUMAP: - if (!bpf_capable()) - return -EPERM; + if (!bpf_token_capable(token, CAP_BPF)) + goto put_token; break; case BPF_MAP_TYPE_SOCKMAP: case BPF_MAP_TYPE_SOCKHASH: case BPF_MAP_TYPE_DEVMAP: case BPF_MAP_TYPE_DEVMAP_HASH: case BPF_MAP_TYPE_XSKMAP: - if (!capable(CAP_NET_ADMIN)) - return -EPERM; + if (!bpf_token_capable(token, CAP_NET_ADMIN)) + goto put_token; break; default: WARN(1, "unsupported map type %d", map_type); - return -EPERM; + goto put_token; } map = ops->map_alloc(attr); - if (IS_ERR(map)) - return PTR_ERR(map); + if (IS_ERR(map)) { + err = PTR_ERR(map); + goto put_token; + } map->ops = ops; map->map_type = map_type; @@ -1246,7 +1299,7 @@ static int map_create(union bpf_attr *attr) map->btf = btf; if (attr->btf_value_type_id) { - err = map_check_btf(map, btf, attr->btf_key_type_id, + err = map_check_btf(map, token, btf, attr->btf_key_type_id, attr->btf_value_type_id); if (err) goto free_map; @@ -1258,15 +1311,16 @@ static int map_create(union bpf_attr *attr) attr->btf_vmlinux_value_type_id; } - err = security_bpf_map_alloc(map); + err = security_bpf_map_create(map, attr, token); if (err) - goto free_map; + goto free_map_sec; err = bpf_map_alloc_id(map); if (err) goto free_map_sec; bpf_map_save_memcg(map); + bpf_token_put(token); err = bpf_map_new_fd(map, f_flags); if (err < 0) { @@ -1287,6 +1341,8 @@ free_map_sec: free_map: btf_put(map->btf); map->ops->map_free(map); +put_token: + bpf_token_put(token); return err; } @@ -1524,6 +1580,8 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr) } err = bpf_map_update_value(map, f.file, key, value, attr->flags); + if (!err) + maybe_wait_bpf_programs(map); kvfree(value); free_key: @@ -1579,7 +1637,8 @@ static int map_delete_elem(union bpf_attr *attr, bpfptr_t uattr) err = map->ops->map_delete_elem(map, key); rcu_read_unlock(); bpf_enable_instrumentation(); - maybe_wait_bpf_programs(map); + if (!err) + maybe_wait_bpf_programs(map); out: kvfree(key); err_put: @@ -1676,6 +1735,9 @@ int generic_map_delete_batch(struct bpf_map *map, if (!max_count) return 0; + if (put_user(0, &uattr->batch.count)) + return -EFAULT; + key = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN); if (!key) return -ENOMEM; @@ -1705,7 +1767,6 @@ int generic_map_delete_batch(struct bpf_map *map, kvfree(key); - maybe_wait_bpf_programs(map); return err; } @@ -1733,6 +1794,9 @@ int generic_map_update_batch(struct bpf_map *map, struct file *map_file, if (!max_count) return 0; + if (put_user(0, &uattr->batch.count)) + return -EFAULT; + key = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN); if (!key) return -ENOMEM; @@ -1763,6 +1827,7 @@ int generic_map_update_batch(struct bpf_map *map, struct file *map_file, kvfree(value); kvfree(key); + return err; } @@ -2108,7 +2173,7 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu) kvfree(aux->func_info); kfree(aux->func_info_aux); free_uid(aux->user); - security_bpf_prog_free(aux); + security_bpf_prog_free(aux->prog); bpf_prog_free(aux->prog); } @@ -2554,13 +2619,15 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type) } /* last field in 'union bpf_attr' used by this command */ -#define BPF_PROG_LOAD_LAST_FIELD log_true_size +#define BPF_PROG_LOAD_LAST_FIELD prog_token_fd static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) { enum bpf_prog_type type = attr->prog_type; struct bpf_prog *prog, *dst_prog = NULL; struct btf *attach_btf = NULL; + struct bpf_token *token = NULL; + bool bpf_cap; int err; char license[128]; @@ -2577,10 +2644,31 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) BPF_F_TEST_REG_INVARIANTS)) return -EINVAL; + bpf_prog_load_fixup_attach_type(attr); + + if (attr->prog_token_fd) { + token = bpf_token_get_from_fd(attr->prog_token_fd); + if (IS_ERR(token)) + return PTR_ERR(token); + /* if current token doesn't grant prog loading permissions, + * then we can't use this token, so ignore it and rely on + * system-wide capabilities checks + */ + if (!bpf_token_allow_cmd(token, BPF_PROG_LOAD) || + !bpf_token_allow_prog_type(token, attr->prog_type, + attr->expected_attach_type)) { + bpf_token_put(token); + token = NULL; + } + } + + bpf_cap = bpf_token_capable(token, CAP_BPF); + err = -EPERM; + if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && (attr->prog_flags & BPF_F_ANY_ALIGNMENT) && - !bpf_capable()) - return -EPERM; + !bpf_cap) + goto put_token; /* Intent here is for unprivileged_bpf_disabled to block BPF program * creation for unprivileged users; other actions depend @@ -2589,21 +2677,23 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) * capability checks are still carried out for these * and other operations. */ - if (sysctl_unprivileged_bpf_disabled && !bpf_capable()) - return -EPERM; + if (sysctl_unprivileged_bpf_disabled && !bpf_cap) + goto put_token; if (attr->insn_cnt == 0 || - attr->insn_cnt > (bpf_capable() ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS)) - return -E2BIG; + attr->insn_cnt > (bpf_cap ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS)) { + err = -E2BIG; + goto put_token; + } if (type != BPF_PROG_TYPE_SOCKET_FILTER && type != BPF_PROG_TYPE_CGROUP_SKB && - !bpf_capable()) - return -EPERM; + !bpf_cap) + goto put_token; - if (is_net_admin_prog_type(type) && !capable(CAP_NET_ADMIN) && !capable(CAP_SYS_ADMIN)) - return -EPERM; - if (is_perfmon_prog_type(type) && !perfmon_capable()) - return -EPERM; + if (is_net_admin_prog_type(type) && !bpf_token_capable(token, CAP_NET_ADMIN)) + goto put_token; + if (is_perfmon_prog_type(type) && !bpf_token_capable(token, CAP_PERFMON)) + goto put_token; /* attach_prog_fd/attach_btf_obj_fd can specify fd of either bpf_prog * or btf, we need to check which one it is @@ -2613,27 +2703,33 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) if (IS_ERR(dst_prog)) { dst_prog = NULL; attach_btf = btf_get_by_fd(attr->attach_btf_obj_fd); - if (IS_ERR(attach_btf)) - return -EINVAL; + if (IS_ERR(attach_btf)) { + err = -EINVAL; + goto put_token; + } if (!btf_is_kernel(attach_btf)) { /* attaching through specifying bpf_prog's BTF * objects directly might be supported eventually */ btf_put(attach_btf); - return -ENOTSUPP; + err = -ENOTSUPP; + goto put_token; } } } else if (attr->attach_btf_id) { /* fall back to vmlinux BTF, if BTF type ID is specified */ attach_btf = bpf_get_btf_vmlinux(); - if (IS_ERR(attach_btf)) - return PTR_ERR(attach_btf); - if (!attach_btf) - return -EINVAL; + if (IS_ERR(attach_btf)) { + err = PTR_ERR(attach_btf); + goto put_token; + } + if (!attach_btf) { + err = -EINVAL; + goto put_token; + } btf_get(attach_btf); } - bpf_prog_load_fixup_attach_type(attr); if (bpf_prog_load_check_attach(type, attr->expected_attach_type, attach_btf, attr->attach_btf_id, dst_prog)) { @@ -2641,7 +2737,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) bpf_prog_put(dst_prog); if (attach_btf) btf_put(attach_btf); - return -EINVAL; + err = -EINVAL; + goto put_token; } /* plain bpf_prog allocation */ @@ -2651,7 +2748,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) bpf_prog_put(dst_prog); if (attach_btf) btf_put(attach_btf); - return -ENOMEM; + err = -EINVAL; + goto put_token; } prog->expected_attach_type = attr->expected_attach_type; @@ -2662,9 +2760,9 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE; prog->aux->xdp_has_frags = attr->prog_flags & BPF_F_XDP_HAS_FRAGS; - err = security_bpf_prog_alloc(prog->aux); - if (err) - goto free_prog; + /* move token into prog->aux, reuse taken refcnt */ + prog->aux->token = token; + token = NULL; prog->aux->user = get_current_user(); prog->len = attr->insn_cnt; @@ -2673,12 +2771,12 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) if (copy_from_bpfptr(prog->insns, make_bpfptr(attr->insns, uattr.is_kernel), bpf_prog_insn_size(prog)) != 0) - goto free_prog_sec; + goto free_prog; /* copy eBPF program license from user space */ if (strncpy_from_bpfptr(license, make_bpfptr(attr->license, uattr.is_kernel), sizeof(license) - 1) < 0) - goto free_prog_sec; + goto free_prog; license[sizeof(license) - 1] = 0; /* eBPF programs must be GPL compatible to use GPL-ed functions */ @@ -2692,25 +2790,29 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) if (bpf_prog_is_dev_bound(prog->aux)) { err = bpf_prog_dev_bound_init(prog, attr); if (err) - goto free_prog_sec; + goto free_prog; } if (type == BPF_PROG_TYPE_EXT && dst_prog && bpf_prog_is_dev_bound(dst_prog->aux)) { err = bpf_prog_dev_bound_inherit(prog, dst_prog); if (err) - goto free_prog_sec; + goto free_prog; } /* find program type: socket_filter vs tracing_filter */ err = find_prog_type(type, prog); if (err < 0) - goto free_prog_sec; + goto free_prog; prog->aux->load_time = ktime_get_boottime_ns(); err = bpf_obj_name_cpy(prog->aux->name, attr->prog_name, sizeof(attr->prog_name)); if (err < 0) + goto free_prog; + + err = security_bpf_prog_load(prog, attr, token); + if (err) goto free_prog_sec; /* run eBPF verifier */ @@ -2756,13 +2858,16 @@ free_used_maps: */ __bpf_prog_put_noref(prog, prog->aux->real_func_cnt); return err; + free_prog_sec: - free_uid(prog->aux->user); - security_bpf_prog_free(prog->aux); + security_bpf_prog_free(prog); free_prog: + free_uid(prog->aux->user); if (prog->aux->attach_btf) btf_put(prog->aux->attach_btf); bpf_prog_free(prog); +put_token: + bpf_token_put(token); return err; } @@ -3752,7 +3857,7 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, case BPF_PROG_TYPE_SK_LOOKUP: return attach_type == prog->expected_attach_type ? 0 : -EINVAL; case BPF_PROG_TYPE_CGROUP_SKB: - if (!capable(CAP_NET_ADMIN)) + if (!bpf_token_capable(prog->aux->token, CAP_NET_ADMIN)) /* cg-skb progs can be loaded by unpriv user. * check permissions at attach time. */ @@ -3955,7 +4060,7 @@ static int bpf_prog_detach(const union bpf_attr *attr) static int bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { - if (!capable(CAP_NET_ADMIN)) + if (!bpf_net_capable()) return -EPERM; if (CHECK_ATTR(BPF_PROG_QUERY)) return -EINVAL; @@ -4723,15 +4828,31 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr, return err; } -#define BPF_BTF_LOAD_LAST_FIELD btf_log_true_size +#define BPF_BTF_LOAD_LAST_FIELD btf_token_fd static int bpf_btf_load(const union bpf_attr *attr, bpfptr_t uattr, __u32 uattr_size) { + struct bpf_token *token = NULL; + if (CHECK_ATTR(BPF_BTF_LOAD)) return -EINVAL; - if (!bpf_capable()) + if (attr->btf_token_fd) { + token = bpf_token_get_from_fd(attr->btf_token_fd); + if (IS_ERR(token)) + return PTR_ERR(token); + if (!bpf_token_allow_cmd(token, BPF_BTF_LOAD)) { + bpf_token_put(token); + token = NULL; + } + } + + if (!bpf_token_capable(token, CAP_BPF)) { + bpf_token_put(token); return -EPERM; + } + + bpf_token_put(token); return btf_new_fd(attr, uattr, uattr_size); } @@ -4920,8 +5041,10 @@ static int bpf_map_do_batch(const union bpf_attr *attr, else BPF_DO_BATCH(map->ops->map_delete_batch, map, attr, uattr); err_put: - if (has_write) + if (has_write) { + maybe_wait_bpf_programs(map); bpf_map_write_active_dec(map); + } fdput(f); return err; } @@ -5323,6 +5446,11 @@ static int bpf_prog_bind_map(union bpf_attr *attr) goto out_unlock; } + /* The bpf program will not access the bpf map, but for the sake of + * simplicity, increase sleepable_refcnt for sleepable program as well. + */ + if (prog->aux->sleepable) + atomic64_inc(&map->sleepable_refcnt); memcpy(used_maps_new, used_maps_old, sizeof(used_maps_old[0]) * prog->aux->used_map_cnt); used_maps_new[prog->aux->used_map_cnt] = map; @@ -5342,6 +5470,20 @@ out_prog_put: return ret; } +#define BPF_TOKEN_CREATE_LAST_FIELD token_create.bpffs_fd + +static int token_create(union bpf_attr *attr) +{ + if (CHECK_ATTR(BPF_TOKEN_CREATE)) + return -EINVAL; + + /* no flags are supported yet */ + if (attr->token_create.flags) + return -EINVAL; + + return bpf_token_create(attr); +} + static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size) { union bpf_attr attr; @@ -5475,6 +5617,9 @@ static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size) case BPF_PROG_BIND_MAP: err = bpf_prog_bind_map(&attr); break; + case BPF_TOKEN_CREATE: + err = token_create(&attr); + break; default: err = -EINVAL; break; @@ -5581,7 +5726,7 @@ static const struct bpf_func_proto bpf_sys_bpf_proto = { const struct bpf_func_proto * __weak tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } BPF_CALL_1(bpf_sys_close, u32, fd) @@ -5631,7 +5776,8 @@ syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_sys_bpf: - return !perfmon_capable() ? NULL : &bpf_sys_bpf_proto; + return !bpf_token_capable(prog->aux->token, CAP_PERFMON) + ? NULL : &bpf_sys_bpf_proto; case BPF_FUNC_btf_find_by_name_kind: return &bpf_btf_find_by_name_kind_proto; case BPF_FUNC_sys_close: diff --git a/kernel/bpf/tnum.c b/kernel/bpf/tnum.c index f4c91c9b27d7..9dbc31b25e3d 100644 --- a/kernel/bpf/tnum.c +++ b/kernel/bpf/tnum.c @@ -172,12 +172,6 @@ bool tnum_in(struct tnum a, struct tnum b) return a.value == b.value; } -int tnum_strn(char *str, size_t size, struct tnum a) -{ - return snprintf(str, size, "(%#llx; %#llx)", a.value, a.mask); -} -EXPORT_SYMBOL_GPL(tnum_strn); - int tnum_sbin(char *str, size_t size, struct tnum a) { size_t n; diff --git a/kernel/bpf/token.c b/kernel/bpf/token.c new file mode 100644 index 000000000000..a86fccd57e2d --- /dev/null +++ b/kernel/bpf/token.c @@ -0,0 +1,271 @@ +#include <linux/bpf.h> +#include <linux/vmalloc.h> +#include <linux/fdtable.h> +#include <linux/file.h> +#include <linux/fs.h> +#include <linux/kernel.h> +#include <linux/idr.h> +#include <linux/namei.h> +#include <linux/user_namespace.h> +#include <linux/security.h> + +bool bpf_token_capable(const struct bpf_token *token, int cap) +{ + /* BPF token allows ns_capable() level of capabilities, but only if + * token's userns is *exactly* the same as current user's userns + */ + if (token && current_user_ns() == token->userns) { + if (ns_capable(token->userns, cap) || + (cap != CAP_SYS_ADMIN && ns_capable(token->userns, CAP_SYS_ADMIN))) + return security_bpf_token_capable(token, cap) == 0; + } + /* otherwise fallback to capable() checks */ + return capable(cap) || (cap != CAP_SYS_ADMIN && capable(CAP_SYS_ADMIN)); +} + +void bpf_token_inc(struct bpf_token *token) +{ + atomic64_inc(&token->refcnt); +} + +static void bpf_token_free(struct bpf_token *token) +{ + security_bpf_token_free(token); + put_user_ns(token->userns); + kvfree(token); +} + +static void bpf_token_put_deferred(struct work_struct *work) +{ + struct bpf_token *token = container_of(work, struct bpf_token, work); + + bpf_token_free(token); +} + +void bpf_token_put(struct bpf_token *token) +{ + if (!token) + return; + + if (!atomic64_dec_and_test(&token->refcnt)) + return; + + INIT_WORK(&token->work, bpf_token_put_deferred); + schedule_work(&token->work); +} + +static int bpf_token_release(struct inode *inode, struct file *filp) +{ + struct bpf_token *token = filp->private_data; + + bpf_token_put(token); + return 0; +} + +static void bpf_token_show_fdinfo(struct seq_file *m, struct file *filp) +{ + struct bpf_token *token = filp->private_data; + u64 mask; + + BUILD_BUG_ON(__MAX_BPF_CMD >= 64); + mask = (1ULL << __MAX_BPF_CMD) - 1; + if ((token->allowed_cmds & mask) == mask) + seq_printf(m, "allowed_cmds:\tany\n"); + else + seq_printf(m, "allowed_cmds:\t0x%llx\n", token->allowed_cmds); + + BUILD_BUG_ON(__MAX_BPF_MAP_TYPE >= 64); + mask = (1ULL << __MAX_BPF_MAP_TYPE) - 1; + if ((token->allowed_maps & mask) == mask) + seq_printf(m, "allowed_maps:\tany\n"); + else + seq_printf(m, "allowed_maps:\t0x%llx\n", token->allowed_maps); + + BUILD_BUG_ON(__MAX_BPF_PROG_TYPE >= 64); + mask = (1ULL << __MAX_BPF_PROG_TYPE) - 1; + if ((token->allowed_progs & mask) == mask) + seq_printf(m, "allowed_progs:\tany\n"); + else + seq_printf(m, "allowed_progs:\t0x%llx\n", token->allowed_progs); + + BUILD_BUG_ON(__MAX_BPF_ATTACH_TYPE >= 64); + mask = (1ULL << __MAX_BPF_ATTACH_TYPE) - 1; + if ((token->allowed_attachs & mask) == mask) + seq_printf(m, "allowed_attachs:\tany\n"); + else + seq_printf(m, "allowed_attachs:\t0x%llx\n", token->allowed_attachs); +} + +#define BPF_TOKEN_INODE_NAME "bpf-token" + +static const struct inode_operations bpf_token_iops = { }; + +static const struct file_operations bpf_token_fops = { + .release = bpf_token_release, + .show_fdinfo = bpf_token_show_fdinfo, +}; + +int bpf_token_create(union bpf_attr *attr) +{ + struct bpf_mount_opts *mnt_opts; + struct bpf_token *token = NULL; + struct user_namespace *userns; + struct inode *inode; + struct file *file; + struct path path; + struct fd f; + umode_t mode; + int err, fd; + + f = fdget(attr->token_create.bpffs_fd); + if (!f.file) + return -EBADF; + + path = f.file->f_path; + path_get(&path); + fdput(f); + + if (path.dentry != path.mnt->mnt_sb->s_root) { + err = -EINVAL; + goto out_path; + } + if (path.mnt->mnt_sb->s_op != &bpf_super_ops) { + err = -EINVAL; + goto out_path; + } + err = path_permission(&path, MAY_ACCESS); + if (err) + goto out_path; + + userns = path.dentry->d_sb->s_user_ns; + /* + * Enforce that creators of BPF tokens are in the same user + * namespace as the BPF FS instance. This makes reasoning about + * permissions a lot easier and we can always relax this later. + */ + if (current_user_ns() != userns) { + err = -EPERM; + goto out_path; + } + if (!ns_capable(userns, CAP_BPF)) { + err = -EPERM; + goto out_path; + } + + mnt_opts = path.dentry->d_sb->s_fs_info; + if (mnt_opts->delegate_cmds == 0 && + mnt_opts->delegate_maps == 0 && + mnt_opts->delegate_progs == 0 && + mnt_opts->delegate_attachs == 0) { + err = -ENOENT; /* no BPF token delegation is set up */ + goto out_path; + } + + mode = S_IFREG | ((S_IRUSR | S_IWUSR) & ~current_umask()); + inode = bpf_get_inode(path.mnt->mnt_sb, NULL, mode); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + goto out_path; + } + + inode->i_op = &bpf_token_iops; + inode->i_fop = &bpf_token_fops; + clear_nlink(inode); /* make sure it is unlinked */ + + file = alloc_file_pseudo(inode, path.mnt, BPF_TOKEN_INODE_NAME, O_RDWR, &bpf_token_fops); + if (IS_ERR(file)) { + iput(inode); + err = PTR_ERR(file); + goto out_path; + } + + token = kvzalloc(sizeof(*token), GFP_USER); + if (!token) { + err = -ENOMEM; + goto out_file; + } + + atomic64_set(&token->refcnt, 1); + + /* remember bpffs owning userns for future ns_capable() checks */ + token->userns = get_user_ns(userns); + + token->allowed_cmds = mnt_opts->delegate_cmds; + token->allowed_maps = mnt_opts->delegate_maps; + token->allowed_progs = mnt_opts->delegate_progs; + token->allowed_attachs = mnt_opts->delegate_attachs; + + err = security_bpf_token_create(token, attr, &path); + if (err) + goto out_token; + + fd = get_unused_fd_flags(O_CLOEXEC); + if (fd < 0) { + err = fd; + goto out_token; + } + + file->private_data = token; + fd_install(fd, file); + + path_put(&path); + return fd; + +out_token: + bpf_token_free(token); +out_file: + fput(file); +out_path: + path_put(&path); + return err; +} + +struct bpf_token *bpf_token_get_from_fd(u32 ufd) +{ + struct fd f = fdget(ufd); + struct bpf_token *token; + + if (!f.file) + return ERR_PTR(-EBADF); + if (f.file->f_op != &bpf_token_fops) { + fdput(f); + return ERR_PTR(-EINVAL); + } + + token = f.file->private_data; + bpf_token_inc(token); + fdput(f); + + return token; +} + +bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd) +{ + /* BPF token can be used only within exactly the same userns in which + * it was created + */ + if (!token || current_user_ns() != token->userns) + return false; + if (!(token->allowed_cmds & (1ULL << cmd))) + return false; + return security_bpf_token_cmd(token, cmd) == 0; +} + +bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type) +{ + if (!token || type >= __MAX_BPF_MAP_TYPE) + return false; + + return token->allowed_maps & (1ULL << type); +} + +bool bpf_token_allow_prog_type(const struct bpf_token *token, + enum bpf_prog_type prog_type, + enum bpf_attach_type attach_type) +{ + if (!token || prog_type >= __MAX_BPF_PROG_TYPE || attach_type >= __MAX_BPF_ATTACH_TYPE) + return false; + + return (token->allowed_progs & (1ULL << prog_type)) && + (token->allowed_attachs & (1ULL << attach_type)); +} diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index e97aeda3a86b..d382f5ebe06c 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -115,10 +115,10 @@ bool bpf_prog_has_trampoline(const struct bpf_prog *prog) (ptype == BPF_PROG_TYPE_LSM && eatype == BPF_LSM_MAC); } -void bpf_image_ksym_add(void *data, struct bpf_ksym *ksym) +void bpf_image_ksym_add(void *data, unsigned int size, struct bpf_ksym *ksym) { ksym->start = (unsigned long) data; - ksym->end = ksym->start + PAGE_SIZE; + ksym->end = ksym->start + size; bpf_ksym_add(ksym); perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF, ksym->start, PAGE_SIZE, false, ksym->name); @@ -254,8 +254,8 @@ bpf_trampoline_get_progs(const struct bpf_trampoline *tr, int *total, bool *ip_a static void bpf_tramp_image_free(struct bpf_tramp_image *im) { bpf_image_ksym_del(&im->ksym); - bpf_jit_free_exec(im->image); - bpf_jit_uncharge_modmem(PAGE_SIZE); + arch_free_bpf_trampoline(im->image, im->size); + bpf_jit_uncharge_modmem(im->size); percpu_ref_exit(&im->pcref); kfree_rcu(im, rcu); } @@ -349,7 +349,7 @@ static void bpf_tramp_image_put(struct bpf_tramp_image *im) call_rcu_tasks_trace(&im->rcu, __bpf_tramp_image_put_rcu_tasks); } -static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key) +static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key, int size) { struct bpf_tramp_image *im; struct bpf_ksym *ksym; @@ -360,15 +360,15 @@ static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key) if (!im) goto out; - err = bpf_jit_charge_modmem(PAGE_SIZE); + err = bpf_jit_charge_modmem(size); if (err) goto out_free_im; + im->size = size; err = -ENOMEM; - im->image = image = bpf_jit_alloc_exec(PAGE_SIZE); + im->image = image = arch_alloc_bpf_trampoline(size); if (!image) goto out_uncharge; - set_vm_flush_reset_perms(image); err = percpu_ref_init(&im->pcref, __bpf_tramp_image_release, 0, GFP_KERNEL); if (err) @@ -377,13 +377,13 @@ static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key) ksym = &im->ksym; INIT_LIST_HEAD_RCU(&ksym->lnode); snprintf(ksym->name, KSYM_NAME_LEN, "bpf_trampoline_%llu", key); - bpf_image_ksym_add(image, ksym); + bpf_image_ksym_add(image, size, ksym); return im; out_free_image: - bpf_jit_free_exec(im->image); + arch_free_bpf_trampoline(im->image, im->size); out_uncharge: - bpf_jit_uncharge_modmem(PAGE_SIZE); + bpf_jit_uncharge_modmem(size); out_free_im: kfree(im); out: @@ -396,7 +396,7 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut struct bpf_tramp_links *tlinks; u32 orig_flags = tr->flags; bool ip_arg = false; - int err, total; + int err, total, size; tlinks = bpf_trampoline_get_progs(tr, &total, &ip_arg); if (IS_ERR(tlinks)) @@ -409,12 +409,6 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut goto out; } - im = bpf_tramp_image_alloc(tr->key); - if (IS_ERR(im)) { - err = PTR_ERR(im); - goto out; - } - /* clear all bits except SHARE_IPMODIFY and TAIL_CALL_CTX */ tr->flags &= (BPF_TRAMP_F_SHARE_IPMODIFY | BPF_TRAMP_F_TAIL_CALL_CTX); @@ -438,13 +432,31 @@ again: tr->flags |= BPF_TRAMP_F_ORIG_STACK; #endif - err = arch_prepare_bpf_trampoline(im, im->image, im->image + PAGE_SIZE, + size = arch_bpf_trampoline_size(&tr->func.model, tr->flags, + tlinks, tr->func.addr); + if (size < 0) { + err = size; + goto out; + } + + if (size > PAGE_SIZE) { + err = -E2BIG; + goto out; + } + + im = bpf_tramp_image_alloc(tr->key, size); + if (IS_ERR(im)) { + err = PTR_ERR(im); + goto out; + } + + err = arch_prepare_bpf_trampoline(im, im->image, im->image + size, &tr->func.model, tr->flags, tlinks, tr->func.addr); if (err < 0) goto out_free; - set_memory_rox((long)im->image, 1); + arch_protect_bpf_trampoline(im->image, im->size); WARN_ON(tr->cur_image && total == 0); if (tr->cur_image) @@ -464,9 +476,8 @@ again: tr->fops->func = NULL; tr->fops->trampoline = 0; - /* reset im->image memory attr for arch_prepare_bpf_trampoline */ - set_memory_nx((long)im->image, 1); - set_memory_rw((long)im->image, 1); + /* free im memory and reallocate later */ + bpf_tramp_image_free(im); goto again; } #endif @@ -1032,10 +1043,50 @@ bpf_trampoline_exit_t bpf_trampoline_exit(const struct bpf_prog *prog) } int __weak -arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end, +arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end, const struct btf_func_model *m, u32 flags, struct bpf_tramp_links *tlinks, - void *orig_call) + void *func_addr) +{ + return -ENOTSUPP; +} + +void * __weak arch_alloc_bpf_trampoline(unsigned int size) +{ + void *image; + + if (WARN_ON_ONCE(size > PAGE_SIZE)) + return NULL; + image = bpf_jit_alloc_exec(PAGE_SIZE); + if (image) + set_vm_flush_reset_perms(image); + return image; +} + +void __weak arch_free_bpf_trampoline(void *image, unsigned int size) +{ + WARN_ON_ONCE(size > PAGE_SIZE); + /* bpf_jit_free_exec doesn't need "size", but + * bpf_prog_pack_free() needs it. + */ + bpf_jit_free_exec(image); +} + +void __weak arch_protect_bpf_trampoline(void *image, unsigned int size) +{ + WARN_ON_ONCE(size > PAGE_SIZE); + set_memory_rox((long)image, 1); +} + +void __weak arch_unprotect_bpf_trampoline(void *image, unsigned int size) +{ + WARN_ON_ONCE(size > PAGE_SIZE); + set_memory_nx((long)image, 1); + set_memory_rw((long)image, 1); +} + +int __weak arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, + struct bpf_tramp_links *tlinks, void *func_addr) { return -ENOTSUPP; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 8e7b6072e3f4..9456ee0ad129 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -362,20 +362,23 @@ __printf(2, 3) static void verbose(void *private_data, const char *fmt, ...) static void verbose_invalid_scalar(struct bpf_verifier_env *env, struct bpf_reg_state *reg, - struct tnum *range, const char *ctx, + struct bpf_retval_range range, const char *ctx, const char *reg_name) { - char tn_buf[48]; + bool unknown = true; - verbose(env, "At %s the register %s ", ctx, reg_name); - if (!tnum_is_unknown(reg->var_off)) { - tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose(env, "has value %s", tn_buf); - } else { - verbose(env, "has unknown scalar value"); + verbose(env, "%s the register %s has", ctx, reg_name); + if (reg->smin_value > S64_MIN) { + verbose(env, " smin=%lld", reg->smin_value); + unknown = false; + } + if (reg->smax_value < S64_MAX) { + verbose(env, " smax=%lld", reg->smax_value); + unknown = false; } - tnum_strn(tn_buf, sizeof(tn_buf), *range); - verbose(env, " should have been in %s\n", tn_buf); + if (unknown) + verbose(env, " unknown scalar value"); + verbose(env, " should have been in [%d, %d]\n", range.minval, range.maxval); } static bool type_may_be_null(u32 type) @@ -439,6 +442,25 @@ static struct bpf_func_info_aux *subprog_aux(const struct bpf_verifier_env *env, return &env->prog->aux->func_info_aux[subprog]; } +static struct bpf_subprog_info *subprog_info(struct bpf_verifier_env *env, int subprog) +{ + return &env->subprog_info[subprog]; +} + +static void mark_subprog_exc_cb(struct bpf_verifier_env *env, int subprog) +{ + struct bpf_subprog_info *info = subprog_info(env, subprog); + + info->is_cb = true; + info->is_async_cb = true; + info->is_exception_cb = true; +} + +static bool subprog_is_exc_cb(struct bpf_verifier_env *env, int subprog) +{ + return subprog_info(env, subprog)->is_exception_cb; +} + static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg) { return btf_record_has_field(reg_btf_record(reg), BPF_SPIN_LOCK); @@ -1141,6 +1163,21 @@ static bool is_spilled_scalar_reg(const struct bpf_stack_state *stack) stack->spilled_ptr.type == SCALAR_VALUE; } +/* Mark stack slot as STACK_MISC, unless it is already STACK_INVALID, in which + * case they are equivalent, or it's STACK_ZERO, in which case we preserve + * more precise STACK_ZERO. + * Note, in uprivileged mode leaving STACK_INVALID is wrong, so we take + * env->allow_ptr_leaks into account and force STACK_MISC, if necessary. + */ +static void mark_stack_slot_misc(struct bpf_verifier_env *env, u8 *stype) +{ + if (*stype == STACK_ZERO) + return; + if (env->allow_ptr_leaks && *stype == STACK_INVALID) + return; + *stype = STACK_MISC; +} + static void scrub_spilled_slot(u8 *stype) { if (*stype != STACK_INVALID) @@ -1241,9 +1278,16 @@ static int resize_reference_state(struct bpf_func_state *state, size_t n) return 0; } -static int grow_stack_state(struct bpf_func_state *state, int size) +/* Possibly update state->allocated_stack to be at least size bytes. Also + * possibly update the function's high-water mark in its bpf_subprog_info. + */ +static int grow_stack_state(struct bpf_verifier_env *env, struct bpf_func_state *state, int size) { - size_t old_n = state->allocated_stack / BPF_REG_SIZE, n = size / BPF_REG_SIZE; + size_t old_n = state->allocated_stack / BPF_REG_SIZE, n; + + /* The stack size is always a multiple of BPF_REG_SIZE. */ + size = round_up(size, BPF_REG_SIZE); + n = size / BPF_REG_SIZE; if (old_n >= n) return 0; @@ -1253,6 +1297,11 @@ static int grow_stack_state(struct bpf_func_state *state, int size) return -ENOMEM; state->allocated_stack = size; + + /* update known max for given subprogram */ + if (env->subprog_info[state->subprogno].stack_depth < size) + env->subprog_info[state->subprogno].stack_depth = size; + return 0; } @@ -1352,8 +1401,8 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state, int i, err; dst_state->jmp_history = copy_array(dst_state->jmp_history, src->jmp_history, - src->jmp_history_cnt, sizeof(struct bpf_idx_pair), - GFP_USER); + src->jmp_history_cnt, sizeof(*dst_state->jmp_history), + GFP_USER); if (!dst_state->jmp_history) return -ENOMEM; dst_state->jmp_history_cnt = src->jmp_history_cnt; @@ -1728,10 +1777,14 @@ static void __mark_reg_known_zero(struct bpf_reg_state *reg) __mark_reg_known(reg, 0); } -static void __mark_reg_const_zero(struct bpf_reg_state *reg) +static void __mark_reg_const_zero(const struct bpf_verifier_env *env, struct bpf_reg_state *reg) { __mark_reg_known(reg, 0); reg->type = SCALAR_VALUE; + /* all scalars are assumed imprecise initially (unless unprivileged, + * in which case everything is forced to be precise) + */ + reg->precise = !env->bpf_capable; } static void mark_reg_known_zero(struct bpf_verifier_env *env, @@ -2305,6 +2358,11 @@ static void init_reg_state(struct bpf_verifier_env *env, regs[BPF_REG_FP].frameno = state->frameno; } +static struct bpf_retval_range retval_range(s32 minval, s32 maxval) +{ + return (struct bpf_retval_range){ minval, maxval }; +} + #define BPF_MAIN_FUNC (-1) static void init_func_state(struct bpf_verifier_env *env, struct bpf_func_state *state, @@ -2313,7 +2371,7 @@ static void init_func_state(struct bpf_verifier_env *env, state->callsite = callsite; state->frameno = frameno; state->subprogno = subprogno; - state->callback_ret_range = tnum_range(0, 0); + state->callback_ret_range = retval_range(0, 0); init_reg_state(env, state); mark_verifier_state_scratched(env); } @@ -2857,6 +2915,7 @@ static int add_subprog_and_kfunc(struct bpf_verifier_env *env) if (env->subprog_info[i].start != ex_cb_insn) continue; env->exception_callback_subprog = i; + mark_subprog_exc_cb(env, i); break; } } @@ -3213,6 +3272,21 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, return __check_reg_arg(env, state->regs, regno, t); } +static int insn_stack_access_flags(int frameno, int spi) +{ + return INSN_F_STACK_ACCESS | (spi << INSN_F_SPI_SHIFT) | frameno; +} + +static int insn_stack_access_spi(int insn_flags) +{ + return (insn_flags >> INSN_F_SPI_SHIFT) & INSN_F_SPI_MASK; +} + +static int insn_stack_access_frameno(int insn_flags) +{ + return insn_flags & INSN_F_FRAMENO_MASK; +} + static void mark_jmp_point(struct bpf_verifier_env *env, int idx) { env->insn_aux_data[idx].jmp_point = true; @@ -3224,28 +3298,51 @@ static bool is_jmp_point(struct bpf_verifier_env *env, int insn_idx) } /* for any branch, call, exit record the history of jmps in the given state */ -static int push_jmp_history(struct bpf_verifier_env *env, - struct bpf_verifier_state *cur) +static int push_jmp_history(struct bpf_verifier_env *env, struct bpf_verifier_state *cur, + int insn_flags) { u32 cnt = cur->jmp_history_cnt; - struct bpf_idx_pair *p; + struct bpf_jmp_history_entry *p; size_t alloc_size; - if (!is_jmp_point(env, env->insn_idx)) + /* combine instruction flags if we already recorded this instruction */ + if (env->cur_hist_ent) { + /* atomic instructions push insn_flags twice, for READ and + * WRITE sides, but they should agree on stack slot + */ + WARN_ONCE((env->cur_hist_ent->flags & insn_flags) && + (env->cur_hist_ent->flags & insn_flags) != insn_flags, + "verifier insn history bug: insn_idx %d cur flags %x new flags %x\n", + env->insn_idx, env->cur_hist_ent->flags, insn_flags); + env->cur_hist_ent->flags |= insn_flags; return 0; + } cnt++; alloc_size = kmalloc_size_roundup(size_mul(cnt, sizeof(*p))); p = krealloc(cur->jmp_history, alloc_size, GFP_USER); if (!p) return -ENOMEM; - p[cnt - 1].idx = env->insn_idx; - p[cnt - 1].prev_idx = env->prev_insn_idx; cur->jmp_history = p; + + p = &cur->jmp_history[cnt - 1]; + p->idx = env->insn_idx; + p->prev_idx = env->prev_insn_idx; + p->flags = insn_flags; cur->jmp_history_cnt = cnt; + env->cur_hist_ent = p; + return 0; } +static struct bpf_jmp_history_entry *get_jmp_hist_entry(struct bpf_verifier_state *st, + u32 hist_end, int insn_idx) +{ + if (hist_end > 0 && st->jmp_history[hist_end - 1].idx == insn_idx) + return &st->jmp_history[hist_end - 1]; + return NULL; +} + /* Backtrack one insn at a time. If idx is not at the top of recorded * history then previous instruction came from straight line execution. * Return -ENOENT if we exhausted all instructions within given state. @@ -3372,16 +3469,6 @@ static inline void bt_clear_frame_slot(struct backtrack_state *bt, u32 frame, u3 bt->stack_masks[frame] &= ~(1ull << slot); } -static inline void bt_set_slot(struct backtrack_state *bt, u32 slot) -{ - bt_set_frame_slot(bt, bt->frame, slot); -} - -static inline void bt_clear_slot(struct backtrack_state *bt, u32 slot) -{ - bt_clear_frame_slot(bt, bt->frame, slot); -} - static inline u32 bt_frame_reg_mask(struct backtrack_state *bt, u32 frame) { return bt->reg_masks[frame]; @@ -3407,9 +3494,9 @@ static inline bool bt_is_reg_set(struct backtrack_state *bt, u32 reg) return bt->reg_masks[bt->frame] & (1 << reg); } -static inline bool bt_is_slot_set(struct backtrack_state *bt, u32 slot) +static inline bool bt_is_frame_slot_set(struct backtrack_state *bt, u32 frame, u32 slot) { - return bt->stack_masks[bt->frame] & (1ull << slot); + return bt->stack_masks[frame] & (1ull << slot); } /* format registers bitmask, e.g., "r0,r2,r4" for 0x15 mask */ @@ -3463,7 +3550,7 @@ static bool calls_callback(struct bpf_verifier_env *env, int insn_idx); * - *was* processed previously during backtracking. */ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, - struct backtrack_state *bt) + struct bpf_jmp_history_entry *hist, struct backtrack_state *bt) { const struct bpf_insn_cbs cbs = { .cb_call = disasm_kfunc_name, @@ -3476,7 +3563,7 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, u8 mode = BPF_MODE(insn->code); u32 dreg = insn->dst_reg; u32 sreg = insn->src_reg; - u32 spi, i; + u32 spi, i, fr; if (insn->code == 0) return 0; @@ -3537,20 +3624,15 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, * by 'precise' mark in corresponding register of this state. * No further tracking necessary. */ - if (insn->src_reg != BPF_REG_FP) + if (!hist || !(hist->flags & INSN_F_STACK_ACCESS)) return 0; - /* dreg = *(u64 *)[fp - off] was a fill from the stack. * that [fp - off] slot contains scalar that needs to be * tracked with precision */ - spi = (-insn->off - 1) / BPF_REG_SIZE; - if (spi >= 64) { - verbose(env, "BUG spi %d\n", spi); - WARN_ONCE(1, "verifier backtracking bug"); - return -EFAULT; - } - bt_set_slot(bt, spi); + spi = insn_stack_access_spi(hist->flags); + fr = insn_stack_access_frameno(hist->flags); + bt_set_frame_slot(bt, fr, spi); } else if (class == BPF_STX || class == BPF_ST) { if (bt_is_reg_set(bt, dreg)) /* stx & st shouldn't be using _scalar_ dst_reg @@ -3559,17 +3641,13 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, */ return -ENOTSUPP; /* scalars can only be spilled into stack */ - if (insn->dst_reg != BPF_REG_FP) + if (!hist || !(hist->flags & INSN_F_STACK_ACCESS)) return 0; - spi = (-insn->off - 1) / BPF_REG_SIZE; - if (spi >= 64) { - verbose(env, "BUG spi %d\n", spi); - WARN_ONCE(1, "verifier backtracking bug"); - return -EFAULT; - } - if (!bt_is_slot_set(bt, spi)) + spi = insn_stack_access_spi(hist->flags); + fr = insn_stack_access_frameno(hist->flags); + if (!bt_is_frame_slot_set(bt, fr, spi)) return 0; - bt_clear_slot(bt, spi); + bt_clear_frame_slot(bt, fr, spi); if (class == BPF_STX) bt_set_reg(bt, sreg); } else if (class == BPF_JMP || class == BPF_JMP32) { @@ -3613,10 +3691,14 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, WARN_ONCE(1, "verifier backtracking bug"); return -EFAULT; } - /* we don't track register spills perfectly, - * so fallback to force-precise instead of failing */ - if (bt_stack_mask(bt) != 0) - return -ENOTSUPP; + /* we are now tracking register spills correctly, + * so any instance of leftover slots is a bug + */ + if (bt_stack_mask(bt) != 0) { + verbose(env, "BUG stack slots %llx\n", bt_stack_mask(bt)); + WARN_ONCE(1, "verifier backtracking bug (subprog leftover stack slots)"); + return -EFAULT; + } /* propagate r1-r5 to the caller */ for (i = BPF_REG_1; i <= BPF_REG_5; i++) { if (bt_is_reg_set(bt, i)) { @@ -3641,8 +3723,11 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, WARN_ONCE(1, "verifier backtracking bug"); return -EFAULT; } - if (bt_stack_mask(bt) != 0) - return -ENOTSUPP; + if (bt_stack_mask(bt) != 0) { + verbose(env, "BUG stack slots %llx\n", bt_stack_mask(bt)); + WARN_ONCE(1, "verifier backtracking bug (callback leftover stack slots)"); + return -EFAULT; + } /* clear r1-r5 in callback subprog's mask */ for (i = BPF_REG_1; i <= BPF_REG_5; i++) bt_clear_reg(bt, i); @@ -4079,6 +4164,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno) for (;;) { DECLARE_BITMAP(mask, 64); u32 history = st->jmp_history_cnt; + struct bpf_jmp_history_entry *hist; if (env->log.level & BPF_LOG_LEVEL2) { verbose(env, "mark_precise: frame%d: last_idx %d first_idx %d subseq_idx %d \n", @@ -4142,7 +4228,8 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno) err = 0; skip_first = false; } else { - err = backtrack_insn(env, i, subseq_idx, bt); + hist = get_jmp_hist_entry(st, history, i); + err = backtrack_insn(env, i, subseq_idx, hist, bt); } if (err == -ENOTSUPP) { mark_all_scalars_precise(env, env->cur_state); @@ -4195,22 +4282,10 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno) bitmap_from_u64(mask, bt_frame_stack_mask(bt, fr)); for_each_set_bit(i, mask, 64) { if (i >= func->allocated_stack / BPF_REG_SIZE) { - /* the sequence of instructions: - * 2: (bf) r3 = r10 - * 3: (7b) *(u64 *)(r3 -8) = r0 - * 4: (79) r4 = *(u64 *)(r10 -8) - * doesn't contain jmps. It's backtracked - * as a single block. - * During backtracking insn 3 is not recognized as - * stack access, so at the end of backtracking - * stack slot fp-8 is still marked in stack_mask. - * However the parent state may not have accessed - * fp-8 and it's "unallocated" stack space. - * In such case fallback to conservative. - */ - mark_all_scalars_precise(env, env->cur_state); - bt_reset(bt); - return 0; + verbose(env, "BUG backtracking (stack slot %d, total slots %d)\n", + i, func->allocated_stack / BPF_REG_SIZE); + WARN_ONCE(1, "verifier backtracking bug (stack slot out of bounds)"); + return -EFAULT; } if (!is_spilled_scalar_reg(&func->stack[i])) { @@ -4347,7 +4422,8 @@ static void copy_register_state(struct bpf_reg_state *dst, const struct bpf_reg_ dst->live = live; } -static void save_register_state(struct bpf_func_state *state, +static void save_register_state(struct bpf_verifier_env *env, + struct bpf_func_state *state, int spi, struct bpf_reg_state *reg, int size) { @@ -4362,7 +4438,7 @@ static void save_register_state(struct bpf_func_state *state, /* size < 8 bytes spill */ for (; i; i--) - scrub_spilled_slot(&state->stack[spi].slot_type[i - 1]); + mark_stack_slot_misc(env, &state->stack[spi].slot_type[i - 1]); } static bool is_bpf_st_mem(struct bpf_insn *insn) @@ -4383,16 +4459,13 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, int i, slot = -off - 1, spi = slot / BPF_REG_SIZE, err; struct bpf_insn *insn = &env->prog->insnsi[insn_idx]; struct bpf_reg_state *reg = NULL; - u32 dst_reg = insn->dst_reg; + int insn_flags = insn_stack_access_flags(state->frameno, spi); - err = grow_stack_state(state, round_up(slot + 1, BPF_REG_SIZE)); - if (err) - return err; /* caller checked that off % size == 0 and -MAX_BPF_STACK <= off < 0, * so it's aligned access and [off, off + size) are within stack limits */ if (!env->allow_ptr_leaks && - state->stack[spi].slot_type[0] == STACK_SPILL && + is_spilled_reg(&state->stack[spi]) && size != BPF_REG_SIZE) { verbose(env, "attempt to corrupt spilled pointer on stack\n"); return -EACCES; @@ -4422,20 +4495,8 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, return err; mark_stack_slot_scratched(env, spi); - if (reg && !(off % BPF_REG_SIZE) && register_is_bounded(reg) && - !register_is_null(reg) && env->bpf_capable) { - if (dst_reg != BPF_REG_FP) { - /* The backtracking logic can only recognize explicit - * stack slot address like [fp - 8]. Other spill of - * scalar via different register has to be conservative. - * Backtrack from here and mark all registers as precise - * that contributed into 'reg' being a constant. - */ - err = mark_chain_precision(env, value_regno); - if (err) - return err; - } - save_register_state(state, spi, reg, size); + if (reg && !(off % BPF_REG_SIZE) && register_is_bounded(reg) && env->bpf_capable) { + save_register_state(env, state, spi, reg, size); /* Break the relation on a narrowing spill. */ if (fls64(reg->umax_value) > BITS_PER_BYTE * size) state->stack[spi].spilled_ptr.id = 0; @@ -4445,7 +4506,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, __mark_reg_known(&fake_reg, insn->imm); fake_reg.type = SCALAR_VALUE; - save_register_state(state, spi, &fake_reg, size); + save_register_state(env, state, spi, &fake_reg, size); } else if (reg && is_spillable_regtype(reg->type)) { /* register containing pointer is being spilled into stack */ if (size != BPF_REG_SIZE) { @@ -4457,7 +4518,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, verbose(env, "cannot spill pointers to stack into stack frame of the caller\n"); return -EINVAL; } - save_register_state(state, spi, reg, size); + save_register_state(env, state, spi, reg, size); } else { u8 type = STACK_MISC; @@ -4482,7 +4543,12 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, /* when we zero initialize stack slots mark them as such */ if ((reg && register_is_null(reg)) || (!reg && is_bpf_st_mem(insn) && insn->imm == 0)) { - /* backtracking doesn't work for STACK_ZERO yet. */ + /* STACK_ZERO case happened because register spill + * wasn't properly aligned at the stack slot boundary, + * so it's not a register spill anymore; force + * originating register to be precise to make + * STACK_ZERO correct for subsequent states + */ err = mark_chain_precision(env, value_regno); if (err) return err; @@ -4491,9 +4557,12 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, /* Mark slots affected by this stack write. */ for (i = 0; i < size; i++) - state->stack[spi].slot_type[(slot - i) % BPF_REG_SIZE] = - type; + state->stack[spi].slot_type[(slot - i) % BPF_REG_SIZE] = type; + insn_flags = 0; /* not a register spill */ } + + if (insn_flags) + return push_jmp_history(env, env->cur_state, insn_flags); return 0; } @@ -4543,10 +4612,6 @@ static int check_stack_write_var_off(struct bpf_verifier_env *env, (!value_reg && is_bpf_st_mem(insn) && insn->imm == 0)) writing_zero = true; - err = grow_stack_state(state, round_up(-min_off, BPF_REG_SIZE)); - if (err) - return err; - for (i = min_off; i < max_off; i++) { int spi; @@ -4645,21 +4710,10 @@ static void mark_reg_stack_read(struct bpf_verifier_env *env, zeros++; } if (zeros == max_off - min_off) { - /* any access_size read into register is zero extended, - * so the whole register == const_zero + /* Any access_size read into register is zero extended, + * so the whole register == const_zero. */ - __mark_reg_const_zero(&state->regs[dst_regno]); - /* backtracking doesn't support STACK_ZERO yet, - * so mark it precise here, so that later - * backtracking can stop here. - * Backtracking may not need this if this register - * doesn't participate in pointer adjustment. - * Forward propagation of precise flag is not - * necessary either. This mark is only to stop - * backtracking. Any register that contributed - * to const 0 was marked precise before spill. - */ - state->regs[dst_regno].precise = true; + __mark_reg_const_zero(env, &state->regs[dst_regno]); } else { /* have read misc data from the stack */ mark_reg_unknown(env, state->regs, dst_regno); @@ -4686,6 +4740,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, int i, slot = -off - 1, spi = slot / BPF_REG_SIZE; struct bpf_reg_state *reg; u8 *stype, type; + int insn_flags = insn_stack_access_flags(reg_state->frameno, spi); stype = reg_state->stack[spi].slot_type; reg = ®_state->stack[spi].spilled_ptr; @@ -4718,25 +4773,42 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, copy_register_state(&state->regs[dst_regno], reg); state->regs[dst_regno].subreg_def = subreg_def; } else { + int spill_cnt = 0, zero_cnt = 0; + for (i = 0; i < size; i++) { type = stype[(slot - i) % BPF_REG_SIZE]; - if (type == STACK_SPILL) + if (type == STACK_SPILL) { + spill_cnt++; continue; + } if (type == STACK_MISC) continue; + if (type == STACK_ZERO) { + zero_cnt++; + continue; + } if (type == STACK_INVALID && env->allow_uninit_stack) continue; verbose(env, "invalid read from stack off %d+%d size %d\n", off, i, size); return -EACCES; } - mark_reg_unknown(env, state->regs, dst_regno); + + if (spill_cnt == size && + tnum_is_const(reg->var_off) && reg->var_off.value == 0) { + __mark_reg_const_zero(env, &state->regs[dst_regno]); + /* this IS register fill, so keep insn_flags */ + } else if (zero_cnt == size) { + /* similarly to mark_reg_stack_read(), preserve zeroes */ + __mark_reg_const_zero(env, &state->regs[dst_regno]); + insn_flags = 0; /* not restoring original register state */ + } else { + mark_reg_unknown(env, state->regs, dst_regno); + insn_flags = 0; /* not restoring original register state */ + } } state->regs[dst_regno].live |= REG_LIVE_WRITTEN; - return 0; - } - - if (dst_regno >= 0) { + } else if (dst_regno >= 0) { /* restore register state from stack */ copy_register_state(&state->regs[dst_regno], reg); /* mark reg as written since spilled pointer state likely @@ -4772,7 +4844,10 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64); if (dst_regno >= 0) mark_reg_stack_read(env, reg_state, off, off + size, dst_regno); + insn_flags = 0; /* we are not restoring spilled register */ } + if (insn_flags) + return push_jmp_history(env, env->cur_state, insn_flags); return 0; } @@ -5701,20 +5776,6 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, strict); } -static int update_stack_depth(struct bpf_verifier_env *env, - const struct bpf_func_state *func, - int off) -{ - u16 stack = env->subprog_info[func->subprogno].stack_depth; - - if (stack >= -off) - return 0; - - /* update known max for given subprogram */ - env->subprog_info[func->subprogno].stack_depth = -off; - return 0; -} - /* starting from main bpf function walk all instructions of the function * and recursively walk all callees that given function can call. * Ignore jump and exit insns. @@ -6504,13 +6565,14 @@ static int check_ptr_to_map_access(struct bpf_verifier_env *env, * The minimum valid offset is -MAX_BPF_STACK for writes, and * -state->allocated_stack for reads. */ -static int check_stack_slot_within_bounds(int off, - struct bpf_func_state *state, - enum bpf_access_type t) +static int check_stack_slot_within_bounds(struct bpf_verifier_env *env, + s64 off, + struct bpf_func_state *state, + enum bpf_access_type t) { int min_valid_off; - if (t == BPF_WRITE) + if (t == BPF_WRITE || env->allow_uninit_stack) min_valid_off = -MAX_BPF_STACK; else min_valid_off = -state->allocated_stack; @@ -6533,7 +6595,7 @@ static int check_stack_access_within_bounds( struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *reg = regs + regno; struct bpf_func_state *state = func(env, reg); - int min_off, max_off; + s64 min_off, max_off; int err; char *err_extra; @@ -6546,11 +6608,8 @@ static int check_stack_access_within_bounds( err_extra = " write to"; if (tnum_is_const(reg->var_off)) { - min_off = reg->var_off.value + off; - if (access_size > 0) - max_off = min_off + access_size - 1; - else - max_off = min_off; + min_off = (s64)reg->var_off.value + off; + max_off = min_off + access_size; } else { if (reg->smax_value >= BPF_MAX_VAR_OFF || reg->smin_value <= -BPF_MAX_VAR_OFF) { @@ -6559,15 +6618,12 @@ static int check_stack_access_within_bounds( return -EACCES; } min_off = reg->smin_value + off; - if (access_size > 0) - max_off = reg->smax_value + off + access_size - 1; - else - max_off = min_off; + max_off = reg->smax_value + off + access_size; } - err = check_stack_slot_within_bounds(min_off, state, type); - if (!err) - err = check_stack_slot_within_bounds(max_off, state, type); + err = check_stack_slot_within_bounds(env, min_off, state, type); + if (!err && max_off > 0) + err = -EINVAL; /* out of stack access into non-negative offsets */ if (err) { if (tnum_is_const(reg->var_off)) { @@ -6577,11 +6633,16 @@ static int check_stack_access_within_bounds( char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose(env, "invalid variable-offset%s stack R%d var_off=%s size=%d\n", - err_extra, regno, tn_buf, access_size); + verbose(env, "invalid variable-offset%s stack R%d var_off=%s off=%d size=%d\n", + err_extra, regno, tn_buf, off, access_size); } + return err; } - return err; + + /* Note that there is no stack access with offset zero, so the needed stack + * size is -min_off, not -min_off+1. + */ + return grow_stack_state(env, state, -min_off /* size */); } /* check whether memory at (regno + off) is accessible for t = (read | write) @@ -6596,7 +6657,6 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn { struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *reg = regs + regno; - struct bpf_func_state *state; int size, err = 0; size = bpf_size_to_bytes(bpf_size); @@ -6739,11 +6799,6 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn if (err) return err; - state = func(env, reg); - err = update_stack_depth(env, state, off); - if (err) - return err; - if (t == BPF_READ) err = check_stack_read(env, regno, off, size, value_regno); @@ -6932,13 +6987,13 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i BPF_SIZE(insn->code), BPF_WRITE, -1, true, false); if (err) return err; - return 0; } /* When register 'regno' is used to read the stack (either directly or through * a helper function) make sure that it's within stack boundary and, depending - * on the access type, that all elements of the stack are initialized. + * on the access type and privileges, that all elements of the stack are + * initialized. * * 'off' includes 'regno->off', but not its dynamic part (if any). * @@ -7046,8 +7101,11 @@ static int check_stack_range_initialized( slot = -i - 1; spi = slot / BPF_REG_SIZE; - if (state->allocated_stack <= slot) - goto err; + if (state->allocated_stack <= slot) { + verbose(env, "verifier bug: allocated_stack too small"); + return -EFAULT; + } + stype = &state->stack[spi].slot_type[slot % BPF_REG_SIZE]; if (*stype == STACK_MISC) goto mark; @@ -7071,7 +7129,6 @@ static int check_stack_range_initialized( goto mark; } -err: if (tnum_is_const(reg->var_off)) { verbose(env, "invalid%s read from stack R%d off %d+%d size %d\n", err_extra, regno, min_off, i - min_off, access_size); @@ -7096,7 +7153,7 @@ mark: * helper may write to the entire memory range. */ } - return update_stack_depth(env, state, min_off); + return 0; } static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, @@ -7192,6 +7249,12 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, } } +/* verify arguments to helpers or kfuncs consisting of a pointer and an access + * size. + * + * @regno is the register containing the access size. regno-1 is the register + * containing the pointer. + */ static int check_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, bool zero_size_allowed, @@ -7893,7 +7956,7 @@ static int process_iter_next_call(struct bpf_verifier_env *env, int insn_idx, /* switch to DRAINED state, but keep the depth unchanged */ /* mark current iter state as drained and assume returned NULL */ cur_iter->iter.state = BPF_ITER_STATE_DRAINED; - __mark_reg_const_zero(&cur_fr->regs[BPF_REG_0]); + __mark_reg_const_zero(env, &cur_fr->regs[BPF_REG_0]); return 0; } @@ -9396,7 +9459,7 @@ static int set_map_elem_callback_state(struct bpf_verifier_env *env, return err; callee->in_callback_fn = true; - callee->callback_ret_range = tnum_range(0, 1); + callee->callback_ret_range = retval_range(0, 1); return 0; } @@ -9418,7 +9481,7 @@ static int set_loop_callback_state(struct bpf_verifier_env *env, __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); callee->in_callback_fn = true; - callee->callback_ret_range = tnum_range(0, 1); + callee->callback_ret_range = retval_range(0, 1); return 0; } @@ -9448,7 +9511,7 @@ static int set_timer_callback_state(struct bpf_verifier_env *env, __mark_reg_not_init(env, &callee->regs[BPF_REG_4]); __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); callee->in_async_callback_fn = true; - callee->callback_ret_range = tnum_range(0, 1); + callee->callback_ret_range = retval_range(0, 1); return 0; } @@ -9476,7 +9539,7 @@ static int set_find_vma_callback_state(struct bpf_verifier_env *env, __mark_reg_not_init(env, &callee->regs[BPF_REG_4]); __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); callee->in_callback_fn = true; - callee->callback_ret_range = tnum_range(0, 1); + callee->callback_ret_range = retval_range(0, 1); return 0; } @@ -9499,7 +9562,7 @@ static int set_user_ringbuf_callback_state(struct bpf_verifier_env *env, __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); callee->in_callback_fn = true; - callee->callback_ret_range = tnum_range(0, 1); + callee->callback_ret_range = retval_range(0, 1); return 0; } @@ -9531,7 +9594,7 @@ static int set_rbtree_add_callback_state(struct bpf_verifier_env *env, __mark_reg_not_init(env, &callee->regs[BPF_REG_4]); __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); callee->in_callback_fn = true; - callee->callback_ret_range = tnum_range(0, 1); + callee->callback_ret_range = retval_range(0, 1); return 0; } @@ -9560,6 +9623,11 @@ static bool in_rbtree_lock_required_cb(struct bpf_verifier_env *env) return is_rbtree_lock_required_kfunc(kfunc_btf_id); } +static bool retval_range_within(struct bpf_retval_range range, const struct bpf_reg_state *reg) +{ + return range.minval <= reg->smin_value && reg->smax_value <= range.maxval; +} + static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) { struct bpf_verifier_state *state = env->cur_state, *prev_st; @@ -9583,15 +9651,21 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) caller = state->frame[state->curframe - 1]; if (callee->in_callback_fn) { - /* enforce R0 return value range [0, 1]. */ - struct tnum range = callee->callback_ret_range; - if (r0->type != SCALAR_VALUE) { verbose(env, "R0 not a scalar value\n"); return -EACCES; } - if (!tnum_in(range, r0->var_off)) { - verbose_invalid_scalar(env, r0, &range, "callback return", "R0"); + + /* we are going to rely on register's precise value */ + err = mark_reg_read(env, r0, r0->parent, REG_LIVE_READ64); + err = err ?: mark_chain_precision(env, BPF_REG_0); + if (err) + return err; + + /* enforce R0 return value range */ + if (!retval_range_within(callee->callback_ret_range, r0)) { + verbose_invalid_scalar(env, r0, callee->callback_ret_range, + "At callback return", "R0"); return -EINVAL; } if (!calls_callback(env, callee->callsite)) { @@ -11805,7 +11879,7 @@ static int fetch_kfunc_meta(struct bpf_verifier_env *env, return 0; } -static int check_return_code(struct bpf_verifier_env *env, int regno); +static int check_return_code(struct bpf_verifier_env *env, int regno, const char *reg_name); static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx_p) @@ -11942,7 +12016,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, * to bpf_throw becomes the return value of the program. */ if (!env->exception_callback_subprog) { - err = check_return_code(env, BPF_REG_1); + err = check_return_code(env, BPF_REG_1, "R1"); if (err < 0) return err; } @@ -14972,12 +15046,13 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return 0; } -static int check_return_code(struct bpf_verifier_env *env, int regno) +static int check_return_code(struct bpf_verifier_env *env, int regno, const char *reg_name) { + const char *exit_ctx = "At program exit"; struct tnum enforce_attach_type_range = tnum_unknown; const struct bpf_prog *prog = env->prog; struct bpf_reg_state *reg; - struct tnum range = tnum_range(0, 1), const_0 = tnum_const(0); + struct bpf_retval_range range = retval_range(0, 1); enum bpf_prog_type prog_type = resolve_prog_type(env->prog); int err; struct bpf_func_state *frame = env->cur_state->frame[0]; @@ -15019,17 +15094,9 @@ static int check_return_code(struct bpf_verifier_env *env, int regno) if (frame->in_async_callback_fn) { /* enforce return zero from async callbacks like timer */ - if (reg->type != SCALAR_VALUE) { - verbose(env, "In async callback the register R%d is not a known value (%s)\n", - regno, reg_type_str(env, reg->type)); - return -EINVAL; - } - - if (!tnum_in(const_0, reg->var_off)) { - verbose_invalid_scalar(env, reg, &const_0, "async callback", "R0"); - return -EINVAL; - } - return 0; + exit_ctx = "At async callback return"; + range = retval_range(0, 0); + goto enforce_retval; } if (is_subprog && !frame->in_exception_callback_fn) { @@ -15052,14 +15119,14 @@ static int check_return_code(struct bpf_verifier_env *env, int regno) env->prog->expected_attach_type == BPF_CGROUP_INET4_GETSOCKNAME || env->prog->expected_attach_type == BPF_CGROUP_INET6_GETSOCKNAME || env->prog->expected_attach_type == BPF_CGROUP_UNIX_GETSOCKNAME) - range = tnum_range(1, 1); + range = retval_range(1, 1); if (env->prog->expected_attach_type == BPF_CGROUP_INET4_BIND || env->prog->expected_attach_type == BPF_CGROUP_INET6_BIND) - range = tnum_range(0, 3); + range = retval_range(0, 3); break; case BPF_PROG_TYPE_CGROUP_SKB: if (env->prog->expected_attach_type == BPF_CGROUP_INET_EGRESS) { - range = tnum_range(0, 3); + range = retval_range(0, 3); enforce_attach_type_range = tnum_range(2, 3); } break; @@ -15072,13 +15139,13 @@ static int check_return_code(struct bpf_verifier_env *env, int regno) case BPF_PROG_TYPE_RAW_TRACEPOINT: if (!env->prog->aux->attach_btf_id) return 0; - range = tnum_const(0); + range = retval_range(0, 0); break; case BPF_PROG_TYPE_TRACING: switch (env->prog->expected_attach_type) { case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: - range = tnum_const(0); + range = retval_range(0, 0); break; case BPF_TRACE_RAW_TP: case BPF_MODIFY_RETURN: @@ -15090,7 +15157,7 @@ static int check_return_code(struct bpf_verifier_env *env, int regno) } break; case BPF_PROG_TYPE_SK_LOOKUP: - range = tnum_range(SK_DROP, SK_PASS); + range = retval_range(SK_DROP, SK_PASS); break; case BPF_PROG_TYPE_LSM: @@ -15104,12 +15171,12 @@ static int check_return_code(struct bpf_verifier_env *env, int regno) /* Make sure programs that attach to void * hooks don't try to modify return value. */ - range = tnum_range(1, 1); + range = retval_range(1, 1); } break; case BPF_PROG_TYPE_NETFILTER: - range = tnum_range(NF_DROP, NF_ACCEPT); + range = retval_range(NF_DROP, NF_ACCEPT); break; case BPF_PROG_TYPE_EXT: /* freplace program can return anything as its return value @@ -15119,15 +15186,21 @@ static int check_return_code(struct bpf_verifier_env *env, int regno) return 0; } +enforce_retval: if (reg->type != SCALAR_VALUE) { - verbose(env, "At program exit the register R%d is not a known value (%s)\n", - regno, reg_type_str(env, reg->type)); + verbose(env, "%s the register R%d is not a known value (%s)\n", + exit_ctx, regno, reg_type_str(env, reg->type)); return -EINVAL; } - if (!tnum_in(range, reg->var_off)) { - verbose_invalid_scalar(env, reg, &range, "program exit", "R0"); - if (prog->expected_attach_type == BPF_LSM_CGROUP && + err = mark_chain_precision(env, regno); + if (err) + return err; + + if (!retval_range_within(range, reg)) { + verbose_invalid_scalar(env, reg, range, exit_ctx, reg_name); + if (!is_subprog && + prog->expected_attach_type == BPF_LSM_CGROUP && prog_type == BPF_PROG_TYPE_LSM && !prog->aux->attach_func_proto->type) verbose(env, "Note, BPF_LSM_CGROUP that attach to void LSM hooks can't modify return value!\n"); @@ -16892,7 +16965,8 @@ hit: * the precision needs to be propagated back in * the current state. */ - err = err ? : push_jmp_history(env, cur); + if (is_jmp_point(env, env->insn_idx)) + err = err ? : push_jmp_history(env, cur, 0); err = err ? : propagate_precision(env, &sl->state); if (err) return err; @@ -17117,6 +17191,9 @@ static int do_check(struct bpf_verifier_env *env) u8 class; int err; + /* reset current history entry on each new instruction */ + env->cur_hist_ent = NULL; + env->prev_insn_idx = prev_insn_idx; if (env->insn_idx >= insn_cnt) { verbose(env, "invalid insn idx %d insn_cnt %d\n", @@ -17156,7 +17233,7 @@ static int do_check(struct bpf_verifier_env *env) } if (is_jmp_point(env, env->insn_idx)) { - err = push_jmp_history(env, state); + err = push_jmp_history(env, state, 0); if (err) return err; } @@ -17410,7 +17487,7 @@ process_bpf_exit_full: continue; } - err = check_return_code(env, BPF_REG_0); + err = check_return_code(env, BPF_REG_0, "R0"); if (err) return err; process_bpf_exit: @@ -17871,10 +17948,12 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) return -E2BIG; } + if (env->prog->aux->sleepable) + atomic64_inc(&map->sleepable_refcnt); /* hold the map. If the program is rejected by verifier, * the map will be released by release_maps() or it * will be used by the valid program until it's unloaded - * and all maps are released in free_used_maps() + * and all maps are released in bpf_free_used_maps() */ bpf_map_inc(map); @@ -19091,9 +19170,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) env->exception_callback_subprog = env->subprog_cnt - 1; /* Don't update insn_cnt, as add_hidden_subprog always appends insns */ - env->subprog_info[env->exception_callback_subprog].is_cb = true; - env->subprog_info[env->exception_callback_subprog].is_async_cb = true; - env->subprog_info[env->exception_callback_subprog].is_exception_cb = true; + mark_subprog_exc_cb(env, env->exception_callback_subprog); } for (i = 0; i < insn_cnt; i++, insn++) { @@ -19793,7 +19870,7 @@ static void free_states(struct bpf_verifier_env *env) } } -static int do_check_common(struct bpf_verifier_env *env, int subprog, bool is_ex_cb) +static int do_check_common(struct bpf_verifier_env *env, int subprog) { bool pop_log = !(env->log.level & BPF_LOG_LEVEL2); struct bpf_verifier_state *state; @@ -19824,9 +19901,23 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog, bool is_ex regs = state->frame[state->curframe]->regs; if (subprog || env->prog->type == BPF_PROG_TYPE_EXT) { - ret = btf_prepare_func_args(env, subprog, regs, is_ex_cb); + u32 nargs; + + ret = btf_prepare_func_args(env, subprog, regs, &nargs); if (ret) goto out; + if (subprog_is_exc_cb(env, subprog)) { + state->frame[0]->in_exception_callback_fn = true; + /* We have already ensured that the callback returns an integer, just + * like all global subprogs. We need to determine it only has a single + * scalar argument. + */ + if (nargs != 1 || regs[BPF_REG_1].type != SCALAR_VALUE) { + verbose(env, "exception cb only supports single integer argument\n"); + ret = -EINVAL; + goto out; + } + } for (i = BPF_REG_1; i <= BPF_REG_5; i++) { if (regs[i].type == PTR_TO_CTX) mark_reg_known_zero(env, regs, i); @@ -19840,12 +19931,6 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog, bool is_ex regs[i].id = ++env->id_gen; } } - if (is_ex_cb) { - state->frame[0]->in_exception_callback_fn = true; - env->subprog_info[subprog].is_cb = true; - env->subprog_info[subprog].is_async_cb = true; - env->subprog_info[subprog].is_exception_cb = true; - } } else { /* 1st arg to a function */ regs[BPF_REG_1].type = PTR_TO_CTX; @@ -19925,7 +20010,7 @@ again: env->insn_idx = env->subprog_info[i].start; WARN_ON_ONCE(env->insn_idx == 0); - ret = do_check_common(env, i, env->exception_callback_subprog == i); + ret = do_check_common(env, i); if (ret) { return ret; } else if (env->log.level & BPF_LOG_LEVEL) { @@ -19955,7 +20040,7 @@ static int do_check_main(struct bpf_verifier_env *env) int ret; env->insn_idx = 0; - ret = do_check_common(env, 0, false); + ret = do_check_common(env, 0); if (!ret) env->prog->aux->stack_depth = env->subprog_info[0].stack_depth; return ret; @@ -20509,7 +20594,12 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3 env->prog = *prog; env->ops = bpf_verifier_ops[env->prog->type]; env->fd_array = make_bpfptr(attr->fd_array, uattr.is_kernel); - is_priv = bpf_capable(); + + env->allow_ptr_leaks = bpf_allow_ptr_leaks(env->prog->aux->token); + env->allow_uninit_stack = bpf_allow_uninit_stack(env->prog->aux->token); + env->bypass_spec_v1 = bpf_bypass_spec_v1(env->prog->aux->token); + env->bypass_spec_v4 = bpf_bypass_spec_v4(env->prog->aux->token); + env->bpf_capable = is_priv = bpf_token_capable(env->prog->aux->token, CAP_BPF); bpf_get_btf_vmlinux(); @@ -20541,12 +20631,6 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3 if (attr->prog_flags & BPF_F_ANY_ALIGNMENT) env->strict_alignment = false; - env->allow_ptr_leaks = bpf_allow_ptr_leaks(); - env->allow_uninit_stack = bpf_allow_uninit_stack(); - env->bypass_spec_v1 = bpf_bypass_spec_v1(); - env->bypass_spec_v4 = bpf_bypass_spec_v4(); - env->bpf_capable = bpf_capable(); - if (is_priv) env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ; env->test_reg_invariants = attr->prog_flags & BPF_F_TEST_REG_INVARIANTS; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index c284a4ad0315..492d60e9c480 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -24,6 +24,7 @@ #include <linux/key.h> #include <linux/verification.h> #include <linux/namei.h> +#include <linux/fileattr.h> #include <net/bpf_sk_storage.h> @@ -41,6 +42,9 @@ #define bpf_event_rcu_dereference(p) \ rcu_dereference_protected(p, lockdep_is_held(&bpf_event_mutex)) +#define MAX_UPROBE_MULTI_CNT (1U << 20) +#define MAX_KPROBE_MULTI_CNT (1U << 20) + #ifdef CONFIG_MODULES struct bpf_trace_module { struct module *module; @@ -1431,6 +1435,72 @@ static int __init bpf_key_sig_kfuncs_init(void) late_initcall(bpf_key_sig_kfuncs_init); #endif /* CONFIG_KEYS */ +/* filesystem kfuncs */ +__bpf_kfunc_start_defs(); + +/** + * bpf_get_file_xattr - get xattr of a file + * @file: file to get xattr from + * @name__str: name of the xattr + * @value_ptr: output buffer of the xattr value + * + * Get xattr *name__str* of *file* and store the output in *value_ptr*. + * + * For security reasons, only *name__str* with prefix "user." is allowed. + * + * Return: 0 on success, a negative value on error. + */ +__bpf_kfunc int bpf_get_file_xattr(struct file *file, const char *name__str, + struct bpf_dynptr_kern *value_ptr) +{ + struct dentry *dentry; + u32 value_len; + void *value; + int ret; + + if (strncmp(name__str, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)) + return -EPERM; + + value_len = __bpf_dynptr_size(value_ptr); + value = __bpf_dynptr_data_rw(value_ptr, value_len); + if (!value) + return -EINVAL; + + dentry = file_dentry(file); + ret = inode_permission(&nop_mnt_idmap, dentry->d_inode, MAY_READ); + if (ret) + return ret; + return __vfs_getxattr(dentry, dentry->d_inode, name__str, value, value_len); +} + +__bpf_kfunc_end_defs(); + +BTF_SET8_START(fs_kfunc_set_ids) +BTF_ID_FLAGS(func, bpf_get_file_xattr, KF_SLEEPABLE | KF_TRUSTED_ARGS) +BTF_SET8_END(fs_kfunc_set_ids) + +static int bpf_get_file_xattr_filter(const struct bpf_prog *prog, u32 kfunc_id) +{ + if (!btf_id_set8_contains(&fs_kfunc_set_ids, kfunc_id)) + return 0; + + /* Only allow to attach from LSM hooks, to avoid recursion */ + return prog->type != BPF_PROG_TYPE_LSM ? -EACCES : 0; +} + +static const struct btf_kfunc_id_set bpf_fs_kfunc_set = { + .owner = THIS_MODULE, + .set = &fs_kfunc_set_ids, + .filter = bpf_get_file_xattr_filter, +}; + +static int __init bpf_fs_kfuncs_init(void) +{ + return register_btf_kfunc_id_set(BPF_PROG_TYPE_LSM, &bpf_fs_kfunc_set); +} + +late_initcall(bpf_fs_kfuncs_init); + static const struct bpf_func_proto * bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -1559,7 +1629,7 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_trace_vprintk: return bpf_get_trace_vprintk_proto(); default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } @@ -2903,6 +2973,8 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr cnt = attr->link_create.kprobe_multi.cnt; if (!cnt) return -EINVAL; + if (cnt > MAX_KPROBE_MULTI_CNT) + return -E2BIG; size = cnt * sizeof(*addrs); addrs = kvmalloc_array(cnt, sizeof(*addrs), GFP_KERNEL); @@ -3277,6 +3349,8 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr if (!upath || !uoffsets || !cnt) return -EINVAL; + if (cnt > MAX_UPROBE_MULTI_CNT) + return -E2BIG; uref_ctr_offsets = u64_to_user_ptr(attr->link_create.uprobe_multi.ref_ctr_offsets); ucookies = u64_to_user_ptr(attr->link_create.uprobe_multi.cookies); @@ -3317,15 +3391,19 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr goto error_free; for (i = 0; i < cnt; i++) { - if (ucookies && __get_user(uprobes[i].cookie, ucookies + i)) { + if (__get_user(uprobes[i].offset, uoffsets + i)) { err = -EFAULT; goto error_free; } + if (uprobes[i].offset < 0) { + err = -EINVAL; + goto error_free; + } if (uref_ctr_offsets && __get_user(uprobes[i].ref_ctr_offset, uref_ctr_offsets + i)) { err = -EFAULT; goto error_free; } - if (__get_user(uprobes[i].offset, uoffsets + i)) { + if (ucookies && __get_user(uprobes[i].cookie, ucookies + i)) { err = -EFAULT; goto error_free; } diff --git a/lib/test_bpf.c b/lib/test_bpf.c index e380fdf756db..569e6d2dc55c 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -6277,7 +6277,7 @@ static struct bpf_test tests[] = { }, /* BPF_ALU64 | BPF_MOD | BPF_K off=1 (SMOD64) */ { - "ALU64_SMOD_X: -7 % 2 = -1", + "ALU64_SMOD_K: -7 % 2 = -1", .u.insns_int = { BPF_LD_IMM64(R0, -7), BPF_ALU64_IMM_OFF(BPF_MOD, R0, 2, 1), diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c index 5918d1b32e19..8906f7bdf4a9 100644 --- a/net/bpf/bpf_dummy_struct_ops.c +++ b/net/bpf/bpf_dummy_struct_ops.c @@ -12,6 +12,11 @@ extern struct bpf_struct_ops bpf_bpf_dummy_ops; /* A common type for test_N with return value in bpf_dummy_ops */ typedef int (*dummy_ops_test_ret_fn)(struct bpf_dummy_ops_state *state, ...); +static int dummy_ops_test_ret_function(struct bpf_dummy_ops_state *state, ...) +{ + return 0; +} + struct bpf_dummy_ops_test_args { u64 args[MAX_BPF_FUNC_ARGS]; struct bpf_dummy_ops_state state; @@ -62,7 +67,7 @@ static int dummy_ops_copy_args(struct bpf_dummy_ops_test_args *args) static int dummy_ops_call_op(void *image, struct bpf_dummy_ops_test_args *args) { - dummy_ops_test_ret_fn test = (void *)image; + dummy_ops_test_ret_fn test = (void *)image + cfi_get_offset(); struct bpf_dummy_ops_state *state = NULL; /* state needs to be NULL if args[0] is 0 */ @@ -101,12 +106,11 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, goto out; } - image = bpf_jit_alloc_exec(PAGE_SIZE); + image = arch_alloc_bpf_trampoline(PAGE_SIZE); if (!image) { err = -ENOMEM; goto out; } - set_vm_flush_reset_perms(image); link = kzalloc(sizeof(*link), GFP_USER); if (!link) { @@ -120,11 +124,12 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, op_idx = prog->expected_attach_type; err = bpf_struct_ops_prepare_trampoline(tlinks, link, &st_ops->func_models[op_idx], + &dummy_ops_test_ret_function, image, image + PAGE_SIZE); if (err < 0) goto out; - set_memory_rox((long)image, 1); + arch_protect_bpf_trampoline(image, PAGE_SIZE); prog_ret = dummy_ops_call_op(image, args); err = dummy_ops_copy_args(args); @@ -134,7 +139,7 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, err = -EFAULT; out: kfree(args); - bpf_jit_free_exec(image); + arch_free_bpf_trampoline(image, PAGE_SIZE); if (link) bpf_link_put(&link->link); kfree(tlinks); @@ -220,6 +225,28 @@ static void bpf_dummy_unreg(void *kdata) { } +static int bpf_dummy_test_1(struct bpf_dummy_ops_state *cb) +{ + return 0; +} + +static int bpf_dummy_test_2(struct bpf_dummy_ops_state *cb, int a1, unsigned short a2, + char a3, unsigned long a4) +{ + return 0; +} + +static int bpf_dummy_test_sleepable(struct bpf_dummy_ops_state *cb) +{ + return 0; +} + +static struct bpf_dummy_ops __bpf_bpf_dummy_ops = { + .test_1 = bpf_dummy_test_1, + .test_2 = bpf_dummy_test_2, + .test_sleepable = bpf_dummy_test_sleepable, +}; + struct bpf_struct_ops bpf_bpf_dummy_ops = { .verifier_ops = &bpf_dummy_verifier_ops, .init = bpf_dummy_init, @@ -228,4 +255,5 @@ struct bpf_struct_ops bpf_bpf_dummy_ops = { .reg = bpf_dummy_reg, .unreg = bpf_dummy_unreg, .name = "bpf_dummy_ops", + .cfi_stubs = &__bpf_bpf_dummy_ops, }; diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 711cf5d59816..dfd919374017 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -600,10 +600,21 @@ __bpf_kfunc void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) refcount_dec(&p->cnt); } +__bpf_kfunc void bpf_kfunc_call_test_release_dtor(void *p) +{ + bpf_kfunc_call_test_release(p); +} +CFI_NOSEAL(bpf_kfunc_call_test_release_dtor); + __bpf_kfunc void bpf_kfunc_call_memb_release(struct prog_test_member *p) { } +__bpf_kfunc void bpf_kfunc_call_memb_release_dtor(void *p) +{ +} +CFI_NOSEAL(bpf_kfunc_call_memb_release_dtor); + __bpf_kfunc_end_defs(); BTF_SET8_START(bpf_test_modify_return_ids) @@ -1671,9 +1682,9 @@ static const struct btf_kfunc_id_set bpf_prog_test_kfunc_set = { BTF_ID_LIST(bpf_prog_test_dtor_kfunc_ids) BTF_ID(struct, prog_test_ref_kfunc) -BTF_ID(func, bpf_kfunc_call_test_release) +BTF_ID(func, bpf_kfunc_call_test_release_dtor) BTF_ID(struct, prog_test_member) -BTF_ID(func, bpf_kfunc_call_memb_release) +BTF_ID(func, bpf_kfunc_call_memb_release_dtor) static int __init bpf_prog_test_run_init(void) { diff --git a/net/core/filter.c b/net/core/filter.c index 6d89a9cf33c9..4ff6100c6a27 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -87,7 +87,7 @@ #include "dev.h" static const struct bpf_func_proto * -bpf_sk_base_func_proto(enum bpf_func_id func_id); +bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog); int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len) { @@ -7862,7 +7862,7 @@ sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } @@ -7955,7 +7955,7 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return NULL; } default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -7974,7 +7974,7 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_perf_event_output: return &bpf_skb_event_output_proto; default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -8161,7 +8161,7 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) #endif #endif default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -8220,7 +8220,7 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) #endif #endif default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } #if IS_MODULE(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES) @@ -8281,7 +8281,7 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_tcp_sock_proto; #endif /* CONFIG_INET */ default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -8323,7 +8323,7 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_cgroup_classid_curr_proto; #endif default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -8367,7 +8367,7 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_skc_lookup_tcp_proto; #endif default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -8378,7 +8378,7 @@ flow_dissector_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_skb_load_bytes: return &bpf_flow_dissector_load_bytes_proto; default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -8405,7 +8405,7 @@ lwt_out_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_skb_under_cgroup: return &bpf_skb_under_cgroup_proto; default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -8580,7 +8580,7 @@ static bool cg_skb_is_valid_access(int off, int size, return false; case bpf_ctx_range(struct __sk_buff, data): case bpf_ctx_range(struct __sk_buff, data_end): - if (!bpf_capable()) + if (!bpf_token_capable(prog->aux->token, CAP_BPF)) return false; break; } @@ -8592,7 +8592,7 @@ static bool cg_skb_is_valid_access(int off, int size, case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): break; case bpf_ctx_range(struct __sk_buff, tstamp): - if (!bpf_capable()) + if (!bpf_token_capable(prog->aux->token, CAP_BPF)) return false; break; default: @@ -11236,7 +11236,7 @@ sk_reuseport_func_proto(enum bpf_func_id func_id, case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } @@ -11418,7 +11418,7 @@ sk_lookup_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_sk_release: return &bpf_sk_release_proto; default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -11752,7 +11752,7 @@ const struct bpf_func_proto bpf_sock_from_file_proto = { }; static const struct bpf_func_proto * -bpf_sk_base_func_proto(enum bpf_func_id func_id) +bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { const struct bpf_func_proto *func; @@ -11781,10 +11781,10 @@ bpf_sk_base_func_proto(enum bpf_func_id func_id) case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } - if (!perfmon_capable()) + if (!bpf_token_capable(prog->aux->token, CAP_PERFMON)) return NULL; return func; diff --git a/net/core/xdp.c b/net/core/xdp.c index b6f1d6dab3f2..4869c1c2d8f3 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -736,6 +736,39 @@ __bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash, return -EOPNOTSUPP; } +/** + * bpf_xdp_metadata_rx_vlan_tag - Get XDP packet outermost VLAN tag + * @ctx: XDP context pointer. + * @vlan_proto: Destination pointer for VLAN Tag protocol identifier (TPID). + * @vlan_tci: Destination pointer for VLAN TCI (VID + DEI + PCP) + * + * In case of success, ``vlan_proto`` contains *Tag protocol identifier (TPID)*, + * usually ``ETH_P_8021Q`` or ``ETH_P_8021AD``, but some networks can use + * custom TPIDs. ``vlan_proto`` is stored in **network byte order (BE)** + * and should be used as follows: + * ``if (vlan_proto == bpf_htons(ETH_P_8021Q)) do_something();`` + * + * ``vlan_tci`` contains the remaining 16 bits of a VLAN tag. + * Driver is expected to provide those in **host byte order (usually LE)**, + * so the bpf program should not perform byte conversion. + * According to 802.1Q standard, *VLAN TCI (Tag control information)* + * is a bit field that contains: + * *VLAN identifier (VID)* that can be read with ``vlan_tci & 0xfff``, + * *Drop eligible indicator (DEI)* - 1 bit, + * *Priority code point (PCP)* - 3 bits. + * For detailed meaning of DEI and PCP, please refer to other sources. + * + * Return: + * * Returns 0 on success or ``-errno`` on error. + * * ``-EOPNOTSUPP`` : device driver doesn't implement kfunc + * * ``-ENODATA`` : VLAN tag was not stripped or is not available + */ +__bpf_kfunc int bpf_xdp_metadata_rx_vlan_tag(const struct xdp_md *ctx, + __be16 *vlan_proto, u16 *vlan_tci) +{ + return -EOPNOTSUPP; +} + __bpf_kfunc_end_defs(); BTF_SET8_START(xdp_metadata_kfunc_ids) diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 39dcccf0f174..634cfafa583d 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -191,7 +191,7 @@ bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id, case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } @@ -271,6 +271,74 @@ static int bpf_tcp_ca_validate(void *kdata) return tcp_validate_congestion_control(kdata); } +static u32 bpf_tcp_ca_ssthresh(struct sock *sk) +{ + return 0; +} + +static void bpf_tcp_ca_cong_avoid(struct sock *sk, u32 ack, u32 acked) +{ +} + +static void bpf_tcp_ca_set_state(struct sock *sk, u8 new_state) +{ +} + +static void bpf_tcp_ca_cwnd_event(struct sock *sk, enum tcp_ca_event ev) +{ +} + +static void bpf_tcp_ca_in_ack_event(struct sock *sk, u32 flags) +{ +} + +static void bpf_tcp_ca_pkts_acked(struct sock *sk, const struct ack_sample *sample) +{ +} + +static u32 bpf_tcp_ca_min_tso_segs(struct sock *sk) +{ + return 0; +} + +static void bpf_tcp_ca_cong_control(struct sock *sk, const struct rate_sample *rs) +{ +} + +static u32 bpf_tcp_ca_undo_cwnd(struct sock *sk) +{ + return 0; +} + +static u32 bpf_tcp_ca_sndbuf_expand(struct sock *sk) +{ + return 0; +} + +static void __bpf_tcp_ca_init(struct sock *sk) +{ +} + +static void __bpf_tcp_ca_release(struct sock *sk) +{ +} + +static struct tcp_congestion_ops __bpf_ops_tcp_congestion_ops = { + .ssthresh = bpf_tcp_ca_ssthresh, + .cong_avoid = bpf_tcp_ca_cong_avoid, + .set_state = bpf_tcp_ca_set_state, + .cwnd_event = bpf_tcp_ca_cwnd_event, + .in_ack_event = bpf_tcp_ca_in_ack_event, + .pkts_acked = bpf_tcp_ca_pkts_acked, + .min_tso_segs = bpf_tcp_ca_min_tso_segs, + .cong_control = bpf_tcp_ca_cong_control, + .undo_cwnd = bpf_tcp_ca_undo_cwnd, + .sndbuf_expand = bpf_tcp_ca_sndbuf_expand, + + .init = __bpf_tcp_ca_init, + .release = __bpf_tcp_ca_release, +}; + struct bpf_struct_ops bpf_tcp_congestion_ops = { .verifier_ops = &bpf_tcp_ca_verifier_ops, .reg = bpf_tcp_ca_reg, @@ -281,6 +349,7 @@ struct bpf_struct_ops bpf_tcp_congestion_ops = { .init = bpf_tcp_ca_init, .validate = bpf_tcp_ca_validate, .name = "tcp_congestion_ops", + .cfi_stubs = &__bpf_ops_tcp_congestion_ops, }; static int __init bpf_tcp_ca_kfunc_init(void) diff --git a/net/netfilter/nf_bpf_link.c b/net/netfilter/nf_bpf_link.c index 0e4beae421f8..5257d5e7eb09 100644 --- a/net/netfilter/nf_bpf_link.c +++ b/net/netfilter/nf_bpf_link.c @@ -314,7 +314,7 @@ static bool nf_is_valid_access(int off, int size, enum bpf_access_type type, static const struct bpf_func_proto * bpf_nf_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } const struct bpf_verifier_ops netfilter_verifier_ops = { diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index 4f6f538a5462..28711cc44ced 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -125,6 +125,18 @@ void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq) } EXPORT_SYMBOL(xp_set_rxq_info); +void xp_fill_cb(struct xsk_buff_pool *pool, struct xsk_cb_desc *desc) +{ + u32 i; + + for (i = 0; i < pool->heads_cnt; i++) { + struct xdp_buff_xsk *xskb = &pool->heads[i]; + + memcpy(xskb->cb + desc->off, desc->src, desc->bytes); + } +} +EXPORT_SYMBOL(xp_fill_cb); + static void xp_disable_drv_zc(struct xsk_buff_pool *pool) { struct netdev_bpf bpf; diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile index cd47f88921f5..547cec77ba03 100644 --- a/net/xfrm/Makefile +++ b/net/xfrm/Makefile @@ -21,3 +21,4 @@ obj-$(CONFIG_XFRM_USER_COMPAT) += xfrm_compat.o obj-$(CONFIG_XFRM_IPCOMP) += xfrm_ipcomp.o obj-$(CONFIG_XFRM_INTERFACE) += xfrm_interface.o obj-$(CONFIG_XFRM_ESPINTCP) += espintcp.o +obj-$(CONFIG_DEBUG_INFO_BTF) += xfrm_state_bpf.o diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index c13dc3ef7910..1b7e75159727 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -4218,6 +4218,8 @@ void __init xfrm_init(void) #ifdef CONFIG_XFRM_ESPINTCP espintcp_init(); #endif + + register_xfrm_state_bpf(); } #ifdef CONFIG_AUDITSYSCALL diff --git a/net/xfrm/xfrm_state_bpf.c b/net/xfrm/xfrm_state_bpf.c new file mode 100644 index 000000000000..9e20d4a377f7 --- /dev/null +++ b/net/xfrm/xfrm_state_bpf.c @@ -0,0 +1,134 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Unstable XFRM state BPF helpers. + * + * Note that it is allowed to break compatibility for these functions since the + * interface they are exposed through to BPF programs is explicitly unstable. + */ + +#include <linux/bpf.h> +#include <linux/btf.h> +#include <linux/btf_ids.h> +#include <net/xdp.h> +#include <net/xfrm.h> + +/* bpf_xfrm_state_opts - Options for XFRM state lookup helpers + * + * Members: + * @error - Out parameter, set for any errors encountered + * Values: + * -EINVAL - netns_id is less than -1 + * -EINVAL - opts__sz isn't BPF_XFRM_STATE_OPTS_SZ + * -ENONET - No network namespace found for netns_id + * -ENOENT - No xfrm_state found + * @netns_id - Specify the network namespace for lookup + * Values: + * BPF_F_CURRENT_NETNS (-1) + * Use namespace associated with ctx + * [0, S32_MAX] + * Network Namespace ID + * @mark - XFRM mark to match on + * @daddr - Destination address to match on + * @spi - Security parameter index to match on + * @proto - IP protocol to match on (eg. IPPROTO_ESP) + * @family - Protocol family to match on (AF_INET/AF_INET6) + */ +struct bpf_xfrm_state_opts { + s32 error; + s32 netns_id; + u32 mark; + xfrm_address_t daddr; + __be32 spi; + u8 proto; + u16 family; +}; + +enum { + BPF_XFRM_STATE_OPTS_SZ = sizeof(struct bpf_xfrm_state_opts), +}; + +__bpf_kfunc_start_defs(); + +/* bpf_xdp_get_xfrm_state - Get XFRM state + * + * A `struct xfrm_state *`, if found, must be released with a corresponding + * bpf_xdp_xfrm_state_release. + * + * Parameters: + * @ctx - Pointer to ctx (xdp_md) in XDP program + * Cannot be NULL + * @opts - Options for lookup (documented above) + * Cannot be NULL + * @opts__sz - Length of the bpf_xfrm_state_opts structure + * Must be BPF_XFRM_STATE_OPTS_SZ + */ +__bpf_kfunc struct xfrm_state * +bpf_xdp_get_xfrm_state(struct xdp_md *ctx, struct bpf_xfrm_state_opts *opts, u32 opts__sz) +{ + struct xdp_buff *xdp = (struct xdp_buff *)ctx; + struct net *net = dev_net(xdp->rxq->dev); + struct xfrm_state *x; + + if (!opts || opts__sz < sizeof(opts->error)) + return NULL; + + if (opts__sz != BPF_XFRM_STATE_OPTS_SZ) { + opts->error = -EINVAL; + return NULL; + } + + if (unlikely(opts->netns_id < BPF_F_CURRENT_NETNS)) { + opts->error = -EINVAL; + return NULL; + } + + if (opts->netns_id >= 0) { + net = get_net_ns_by_id(net, opts->netns_id); + if (unlikely(!net)) { + opts->error = -ENONET; + return NULL; + } + } + + x = xfrm_state_lookup(net, opts->mark, &opts->daddr, opts->spi, + opts->proto, opts->family); + + if (opts->netns_id >= 0) + put_net(net); + if (!x) + opts->error = -ENOENT; + + return x; +} + +/* bpf_xdp_xfrm_state_release - Release acquired xfrm_state object + * + * This must be invoked for referenced PTR_TO_BTF_ID, and the verifier rejects + * the program if any references remain in the program in all of the explored + * states. + * + * Parameters: + * @x - Pointer to referenced xfrm_state object, obtained using + * bpf_xdp_get_xfrm_state. + */ +__bpf_kfunc void bpf_xdp_xfrm_state_release(struct xfrm_state *x) +{ + xfrm_state_put(x); +} + +__bpf_kfunc_end_defs(); + +BTF_SET8_START(xfrm_state_kfunc_set) +BTF_ID_FLAGS(func, bpf_xdp_get_xfrm_state, KF_RET_NULL | KF_ACQUIRE) +BTF_ID_FLAGS(func, bpf_xdp_xfrm_state_release, KF_RELEASE) +BTF_SET8_END(xfrm_state_kfunc_set) + +static const struct btf_kfunc_id_set xfrm_state_xdp_kfunc_set = { + .owner = THIS_MODULE, + .set = &xfrm_state_kfunc_set, +}; + +int __init register_xfrm_state_bpf(void) +{ + return register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, + &xfrm_state_xdp_kfunc_set); +} diff --git a/security/security.c b/security/security.c index dcb3e7014f9b..088a79c35c26 100644 --- a/security/security.c +++ b/security/security.c @@ -5167,29 +5167,87 @@ int security_bpf_prog(struct bpf_prog *prog) } /** - * security_bpf_map_alloc() - Allocate a bpf map LSM blob - * @map: bpf map + * security_bpf_map_create() - Check if BPF map creation is allowed + * @map: BPF map object + * @attr: BPF syscall attributes used to create BPF map + * @token: BPF token used to grant user access + * + * Do a check when the kernel creates a new BPF map. This is also the + * point where LSM blob is allocated for LSMs that need them. + * + * Return: Returns 0 on success, error on failure. + */ +int security_bpf_map_create(struct bpf_map *map, union bpf_attr *attr, + struct bpf_token *token) +{ + return call_int_hook(bpf_map_create, 0, map, attr, token); +} + +/** + * security_bpf_prog_load() - Check if loading of BPF program is allowed + * @prog: BPF program object + * @attr: BPF syscall attributes used to create BPF program + * @token: BPF token used to grant user access to BPF subsystem * - * Initialize the security field inside bpf map. + * Perform an access control check when the kernel loads a BPF program and + * allocates associated BPF program object. This hook is also responsible for + * allocating any required LSM state for the BPF program. * * Return: Returns 0 on success, error on failure. */ -int security_bpf_map_alloc(struct bpf_map *map) +int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, + struct bpf_token *token) { - return call_int_hook(bpf_map_alloc_security, 0, map); + return call_int_hook(bpf_prog_load, 0, prog, attr, token); } /** - * security_bpf_prog_alloc() - Allocate a bpf program LSM blob - * @aux: bpf program aux info struct + * security_bpf_token_create() - Check if creating of BPF token is allowed + * @token: BPF token object + * @attr: BPF syscall attributes used to create BPF token + * @path: path pointing to BPF FS mount point from which BPF token is created * - * Initialize the security field inside bpf program. + * Do a check when the kernel instantiates a new BPF token object from BPF FS + * instance. This is also the point where LSM blob can be allocated for LSMs. * * Return: Returns 0 on success, error on failure. */ -int security_bpf_prog_alloc(struct bpf_prog_aux *aux) +int security_bpf_token_create(struct bpf_token *token, union bpf_attr *attr, + struct path *path) { - return call_int_hook(bpf_prog_alloc_security, 0, aux); + return call_int_hook(bpf_token_create, 0, token, attr, path); +} + +/** + * security_bpf_token_cmd() - Check if BPF token is allowed to delegate + * requested BPF syscall command + * @token: BPF token object + * @cmd: BPF syscall command requested to be delegated by BPF token + * + * Do a check when the kernel decides whether provided BPF token should allow + * delegation of requested BPF syscall command. + * + * Return: Returns 0 on success, error on failure. + */ +int security_bpf_token_cmd(const struct bpf_token *token, enum bpf_cmd cmd) +{ + return call_int_hook(bpf_token_cmd, 0, token, cmd); +} + +/** + * security_bpf_token_capable() - Check if BPF token is allowed to delegate + * requested BPF-related capability + * @token: BPF token object + * @cap: capabilities requested to be delegated by BPF token + * + * Do a check when the kernel decides whether provided BPF token should allow + * delegation of requested BPF-related capabilities. + * + * Return: Returns 0 on success, error on failure. + */ +int security_bpf_token_capable(const struct bpf_token *token, int cap) +{ + return call_int_hook(bpf_token_capable, 0, token, cap); } /** @@ -5200,18 +5258,29 @@ int security_bpf_prog_alloc(struct bpf_prog_aux *aux) */ void security_bpf_map_free(struct bpf_map *map) { - call_void_hook(bpf_map_free_security, map); + call_void_hook(bpf_map_free, map); +} + +/** + * security_bpf_prog_free() - Free a BPF program's LSM blob + * @prog: BPF program struct + * + * Clean up the security information stored inside BPF program. + */ +void security_bpf_prog_free(struct bpf_prog *prog) +{ + call_void_hook(bpf_prog_free, prog); } /** - * security_bpf_prog_free() - Free a bpf program's LSM blob - * @aux: bpf program aux info struct + * security_bpf_token_free() - Free a BPF token's LSM blob + * @token: BPF token struct * - * Clean up the security information stored inside bpf prog. + * Clean up the security information stored inside BPF token. */ -void security_bpf_prog_free(struct bpf_prog_aux *aux) +void security_bpf_token_free(struct bpf_token *token) { - call_void_hook(bpf_prog_free_security, aux); + call_void_hook(bpf_token_free, token); } #endif /* CONFIG_BPF_SYSCALL */ diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index feda711c6b7b..1501e95366a1 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -6783,7 +6783,8 @@ static int selinux_bpf_prog(struct bpf_prog *prog) BPF__PROG_RUN, NULL); } -static int selinux_bpf_map_alloc(struct bpf_map *map) +static int selinux_bpf_map_create(struct bpf_map *map, union bpf_attr *attr, + struct bpf_token *token) { struct bpf_security_struct *bpfsec; @@ -6805,7 +6806,8 @@ static void selinux_bpf_map_free(struct bpf_map *map) kfree(bpfsec); } -static int selinux_bpf_prog_alloc(struct bpf_prog_aux *aux) +static int selinux_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, + struct bpf_token *token) { struct bpf_security_struct *bpfsec; @@ -6814,16 +6816,39 @@ static int selinux_bpf_prog_alloc(struct bpf_prog_aux *aux) return -ENOMEM; bpfsec->sid = current_sid(); - aux->security = bpfsec; + prog->aux->security = bpfsec; return 0; } -static void selinux_bpf_prog_free(struct bpf_prog_aux *aux) +static void selinux_bpf_prog_free(struct bpf_prog *prog) { - struct bpf_security_struct *bpfsec = aux->security; + struct bpf_security_struct *bpfsec = prog->aux->security; - aux->security = NULL; + prog->aux->security = NULL; + kfree(bpfsec); +} + +static int selinux_bpf_token_create(struct bpf_token *token, union bpf_attr *attr, + struct path *path) +{ + struct bpf_security_struct *bpfsec; + + bpfsec = kzalloc(sizeof(*bpfsec), GFP_KERNEL); + if (!bpfsec) + return -ENOMEM; + + bpfsec->sid = current_sid(); + token->security = bpfsec; + + return 0; +} + +static void selinux_bpf_token_free(struct bpf_token *token) +{ + struct bpf_security_struct *bpfsec = token->security; + + token->security = NULL; kfree(bpfsec); } #endif @@ -7179,8 +7204,9 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = { LSM_HOOK_INIT(bpf, selinux_bpf), LSM_HOOK_INIT(bpf_map, selinux_bpf_map), LSM_HOOK_INIT(bpf_prog, selinux_bpf_prog), - LSM_HOOK_INIT(bpf_map_free_security, selinux_bpf_map_free), - LSM_HOOK_INIT(bpf_prog_free_security, selinux_bpf_prog_free), + LSM_HOOK_INIT(bpf_map_free, selinux_bpf_map_free), + LSM_HOOK_INIT(bpf_prog_free, selinux_bpf_prog_free), + LSM_HOOK_INIT(bpf_token_free, selinux_bpf_token_free), #endif #ifdef CONFIG_PERF_EVENTS @@ -7237,8 +7263,9 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = { LSM_HOOK_INIT(audit_rule_init, selinux_audit_rule_init), #endif #ifdef CONFIG_BPF_SYSCALL - LSM_HOOK_INIT(bpf_map_alloc_security, selinux_bpf_map_alloc), - LSM_HOOK_INIT(bpf_prog_alloc_security, selinux_bpf_prog_alloc), + LSM_HOOK_INIT(bpf_map_create, selinux_bpf_map_create), + LSM_HOOK_INIT(bpf_prog_load, selinux_bpf_prog_load), + LSM_HOOK_INIT(bpf_token_create, selinux_bpf_token_create), #endif #ifdef CONFIG_PERF_EVENTS LSM_HOOK_INIT(perf_event_alloc, selinux_perf_event_alloc), diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index e88746ba7d21..e0545201b55f 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -847,6 +847,36 @@ union bpf_iter_link_info { * Returns zero on success. On error, -1 is returned and *errno* * is set appropriately. * + * BPF_TOKEN_CREATE + * Description + * Create BPF token with embedded information about what + * BPF-related functionality it allows: + * - a set of allowed bpf() syscall commands; + * - a set of allowed BPF map types to be created with + * BPF_MAP_CREATE command, if BPF_MAP_CREATE itself is allowed; + * - a set of allowed BPF program types and BPF program attach + * types to be loaded with BPF_PROG_LOAD command, if + * BPF_PROG_LOAD itself is allowed. + * + * BPF token is created (derived) from an instance of BPF FS, + * assuming it has necessary delegation mount options specified. + * This BPF token can be passed as an extra parameter to various + * bpf() syscall commands to grant BPF subsystem functionality to + * unprivileged processes. + * + * When created, BPF token is "associated" with the owning + * user namespace of BPF FS instance (super block) that it was + * derived from, and subsequent BPF operations performed with + * BPF token would be performing capabilities checks (i.e., + * CAP_BPF, CAP_PERFMON, CAP_NET_ADMIN, CAP_SYS_ADMIN) within + * that user namespace. Without BPF token, such capabilities + * have to be granted in init user namespace, making bpf() + * syscall incompatible with user namespace, for the most part. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * * NOTES * eBPF objects (maps and programs) can be shared between processes. * @@ -901,6 +931,8 @@ enum bpf_cmd { BPF_ITER_CREATE, BPF_LINK_DETACH, BPF_PROG_BIND_MAP, + BPF_TOKEN_CREATE, + __MAX_BPF_CMD, }; enum bpf_map_type { @@ -951,6 +983,7 @@ enum bpf_map_type { BPF_MAP_TYPE_BLOOM_FILTER, BPF_MAP_TYPE_USER_RINGBUF, BPF_MAP_TYPE_CGRP_STORAGE, + __MAX_BPF_MAP_TYPE }; /* Note that tracing related programs such as @@ -995,6 +1028,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_SK_LOOKUP, BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */ BPF_PROG_TYPE_NETFILTER, + __MAX_BPF_PROG_TYPE }; enum bpf_attach_type { @@ -1074,9 +1108,11 @@ enum bpf_link_type { BPF_LINK_TYPE_TCX = 11, BPF_LINK_TYPE_UPROBE_MULTI = 12, BPF_LINK_TYPE_NETKIT = 13, - MAX_BPF_LINK_TYPE, + __MAX_BPF_LINK_TYPE, }; +#define MAX_BPF_LINK_TYPE __MAX_BPF_LINK_TYPE + enum bpf_perf_event_type { BPF_PERF_EVENT_UNSPEC = 0, BPF_PERF_EVENT_UPROBE = 1, @@ -1401,6 +1437,7 @@ union bpf_attr { * to using 5 hash functions). */ __u64 map_extra; + __u32 map_token_fd; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -1470,6 +1507,7 @@ union bpf_attr { * truncated), or smaller (if log buffer wasn't filled completely). */ __u32 log_true_size; + __u32 prog_token_fd; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -1582,6 +1620,7 @@ union bpf_attr { * truncated), or smaller (if log buffer wasn't filled completely). */ __u32 btf_log_true_size; + __u32 btf_token_fd; }; struct { @@ -1712,6 +1751,11 @@ union bpf_attr { __u32 flags; /* extra flags */ } prog_bind_map; + struct { /* struct used by BPF_TOKEN_CREATE command */ + __u32 flags; + __u32 bpffs_fd; + } token_create; + } __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 424c5e28f495..93cb411adf72 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -44,10 +44,13 @@ enum netdev_xdp_act { * timestamp via bpf_xdp_metadata_rx_timestamp(). * @NETDEV_XDP_RX_METADATA_HASH: Device is capable of exposing receive packet * hash via bpf_xdp_metadata_rx_hash(). + * @NETDEV_XDP_RX_METADATA_VLAN_TAG: Device is capable of exposing receive + * packet VLAN tag via bpf_xdp_metadata_rx_vlan_tag(). */ enum netdev_xdp_rx_metadata { NETDEV_XDP_RX_METADATA_TIMESTAMP = 1, NETDEV_XDP_RX_METADATA_HASH = 2, + NETDEV_XDP_RX_METADATA_VLAN_TAG = 4, }; /** diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build index 2d0c282c8588..b6619199a706 100644 --- a/tools/lib/bpf/Build +++ b/tools/lib/bpf/Build @@ -1,4 +1,4 @@ libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o \ netlink.o bpf_prog_linfo.o libbpf_probes.o hashmap.o \ btf_dump.o ringbuf.o strset.o linker.o gen_loader.o relo_core.o \ - usdt.o zip.o elf.o + usdt.o zip.o elf.o features.o diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 9dc9625651dc..0ad8e532b3cf 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -103,7 +103,7 @@ int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int attempts) * [0] https://lore.kernel.org/bpf/20201201215900.3569844-1-guro@fb.com/ * [1] d05512618056 ("bpf: Add bpf_ktime_get_coarse_ns helper") */ -int probe_memcg_account(void) +int probe_memcg_account(int token_fd) { const size_t attr_sz = offsetofend(union bpf_attr, attach_btf_obj_fd); struct bpf_insn insns[] = { @@ -120,6 +120,7 @@ int probe_memcg_account(void) attr.insns = ptr_to_u64(insns); attr.insn_cnt = insn_cnt; attr.license = ptr_to_u64("GPL"); + attr.prog_token_fd = token_fd; prog_fd = sys_bpf_fd(BPF_PROG_LOAD, &attr, attr_sz); if (prog_fd >= 0) { @@ -146,7 +147,7 @@ int bump_rlimit_memlock(void) struct rlimit rlim; /* if kernel supports memcg-based accounting, skip bumping RLIMIT_MEMLOCK */ - if (memlock_bumped || kernel_supports(NULL, FEAT_MEMCG_ACCOUNT)) + if (memlock_bumped || feat_supported(NULL, FEAT_MEMCG_ACCOUNT)) return 0; memlock_bumped = true; @@ -169,7 +170,7 @@ int bpf_map_create(enum bpf_map_type map_type, __u32 max_entries, const struct bpf_map_create_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, map_extra); + const size_t attr_sz = offsetofend(union bpf_attr, map_token_fd); union bpf_attr attr; int fd; @@ -181,7 +182,7 @@ int bpf_map_create(enum bpf_map_type map_type, return libbpf_err(-EINVAL); attr.map_type = map_type; - if (map_name && kernel_supports(NULL, FEAT_PROG_NAME)) + if (map_name && feat_supported(NULL, FEAT_PROG_NAME)) libbpf_strlcpy(attr.map_name, map_name, sizeof(attr.map_name)); attr.key_size = key_size; attr.value_size = value_size; @@ -198,6 +199,8 @@ int bpf_map_create(enum bpf_map_type map_type, attr.numa_node = OPTS_GET(opts, numa_node, 0); attr.map_ifindex = OPTS_GET(opts, map_ifindex, 0); + attr.map_token_fd = OPTS_GET(opts, token_fd, 0); + fd = sys_bpf_fd(BPF_MAP_CREATE, &attr, attr_sz); return libbpf_err_errno(fd); } @@ -232,7 +235,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, size_t insn_cnt, struct bpf_prog_load_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, log_true_size); + const size_t attr_sz = offsetofend(union bpf_attr, prog_token_fd); void *finfo = NULL, *linfo = NULL; const char *func_info, *line_info; __u32 log_size, log_level, attach_prog_fd, attach_btf_obj_fd; @@ -261,8 +264,9 @@ int bpf_prog_load(enum bpf_prog_type prog_type, attr.prog_flags = OPTS_GET(opts, prog_flags, 0); attr.prog_ifindex = OPTS_GET(opts, prog_ifindex, 0); attr.kern_version = OPTS_GET(opts, kern_version, 0); + attr.prog_token_fd = OPTS_GET(opts, token_fd, 0); - if (prog_name && kernel_supports(NULL, FEAT_PROG_NAME)) + if (prog_name && feat_supported(NULL, FEAT_PROG_NAME)) libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name)); attr.license = ptr_to_u64(license); @@ -1182,7 +1186,7 @@ int bpf_raw_tracepoint_open(const char *name, int prog_fd) int bpf_btf_load(const void *btf_data, size_t btf_size, struct bpf_btf_load_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, btf_log_true_size); + const size_t attr_sz = offsetofend(union bpf_attr, btf_token_fd); union bpf_attr attr; char *log_buf; size_t log_size; @@ -1207,6 +1211,8 @@ int bpf_btf_load(const void *btf_data, size_t btf_size, struct bpf_btf_load_opts attr.btf = ptr_to_u64(btf_data); attr.btf_size = btf_size; + attr.btf_token_fd = OPTS_GET(opts, token_fd, 0); + /* log_level == 0 and log_buf != NULL means "try loading without * log_buf, but retry with log_buf and log_level=1 on error", which is * consistent across low-level and high-level BTF and program loading @@ -1287,3 +1293,20 @@ int bpf_prog_bind_map(int prog_fd, int map_fd, ret = sys_bpf(BPF_PROG_BIND_MAP, &attr, attr_sz); return libbpf_err_errno(ret); } + +int bpf_token_create(int bpffs_fd, struct bpf_token_create_opts *opts) +{ + const size_t attr_sz = offsetofend(union bpf_attr, token_create); + union bpf_attr attr; + int fd; + + if (!OPTS_VALID(opts, bpf_token_create_opts)) + return libbpf_err(-EINVAL); + + memset(&attr, 0, attr_sz); + attr.token_create.bpffs_fd = bpffs_fd; + attr.token_create.flags = OPTS_GET(opts, flags, 0); + + fd = sys_bpf_fd(BPF_TOKEN_CREATE, &attr, attr_sz); + return libbpf_err_errno(fd); +} diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index d0f53772bdc0..991b86bfe7e4 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -51,8 +51,11 @@ struct bpf_map_create_opts { __u32 numa_node; __u32 map_ifindex; + + __u32 token_fd; + size_t :0; }; -#define bpf_map_create_opts__last_field map_ifindex +#define bpf_map_create_opts__last_field token_fd LIBBPF_API int bpf_map_create(enum bpf_map_type map_type, const char *map_name, @@ -102,9 +105,10 @@ struct bpf_prog_load_opts { * If kernel doesn't support this feature, log_size is left unchanged. */ __u32 log_true_size; + __u32 token_fd; size_t :0; }; -#define bpf_prog_load_opts__last_field log_true_size +#define bpf_prog_load_opts__last_field token_fd LIBBPF_API int bpf_prog_load(enum bpf_prog_type prog_type, const char *prog_name, const char *license, @@ -130,9 +134,10 @@ struct bpf_btf_load_opts { * If kernel doesn't support this feature, log_size is left unchanged. */ __u32 log_true_size; + __u32 token_fd; size_t :0; }; -#define bpf_btf_load_opts__last_field log_true_size +#define bpf_btf_load_opts__last_field token_fd LIBBPF_API int bpf_btf_load(const void *btf_data, size_t btf_size, struct bpf_btf_load_opts *opts); @@ -640,6 +645,30 @@ struct bpf_test_run_opts { LIBBPF_API int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts); +struct bpf_token_create_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + __u32 flags; + size_t :0; +}; +#define bpf_token_create_opts__last_field flags + +/** + * @brief **bpf_token_create()** creates a new instance of BPF token derived + * from specified BPF FS mount point. + * + * BPF token created with this API can be passed to bpf() syscall for + * commands like BPF_PROG_LOAD, BPF_MAP_CREATE, etc. + * + * @param bpffs_fd FD for BPF FS instance from which to derive a BPF token + * instance. + * @param opts optional BPF token creation options, can be NULL + * + * @return BPF token FD > 0, on success; negative error code, otherwise (errno + * is also set to the error code) + */ +LIBBPF_API int bpf_token_create(int bpffs_fd, + struct bpf_token_create_opts *opts); + #ifdef __cplusplus } /* extern "C" */ #endif diff --git a/tools/lib/bpf/bpf_core_read.h b/tools/lib/bpf/bpf_core_read.h index 1ac57bb7ac55..7325a12692a3 100644 --- a/tools/lib/bpf/bpf_core_read.h +++ b/tools/lib/bpf/bpf_core_read.h @@ -111,6 +111,38 @@ enum bpf_enum_value_kind { val; \ }) +/* + * Write to a bitfield, identified by s->field. + * This is the inverse of BPF_CORE_WRITE_BITFIELD(). + */ +#define BPF_CORE_WRITE_BITFIELD(s, field, new_val) ({ \ + void *p = (void *)s + __CORE_RELO(s, field, BYTE_OFFSET); \ + unsigned int byte_size = __CORE_RELO(s, field, BYTE_SIZE); \ + unsigned int lshift = __CORE_RELO(s, field, LSHIFT_U64); \ + unsigned int rshift = __CORE_RELO(s, field, RSHIFT_U64); \ + unsigned long long mask, val, nval = new_val; \ + unsigned int rpad = rshift - lshift; \ + \ + asm volatile("" : "+r"(p)); \ + \ + switch (byte_size) { \ + case 1: val = *(unsigned char *)p; break; \ + case 2: val = *(unsigned short *)p; break; \ + case 4: val = *(unsigned int *)p; break; \ + case 8: val = *(unsigned long long *)p; break; \ + } \ + \ + mask = (~0ULL << rshift) >> lshift; \ + val = (val & ~mask) | ((nval << rpad) & mask); \ + \ + switch (byte_size) { \ + case 1: *(unsigned char *)p = val; break; \ + case 2: *(unsigned short *)p = val; break; \ + case 4: *(unsigned int *)p = val; break; \ + case 8: *(unsigned long long *)p = val; break; \ + } \ +}) + #define ___bpf_field_ref1(field) (field) #define ___bpf_field_ref2(type, field) (((typeof(type) *)0)->field) #define ___bpf_field_ref(args...) \ diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index ee95fd379d4d..63033c334320 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -1317,7 +1317,9 @@ struct btf *btf__parse_split(const char *path, struct btf *base_btf) static void *btf_get_raw_data(const struct btf *btf, __u32 *size, bool swap_endian); -int btf_load_into_kernel(struct btf *btf, char *log_buf, size_t log_sz, __u32 log_level) +int btf_load_into_kernel(struct btf *btf, + char *log_buf, size_t log_sz, __u32 log_level, + int token_fd) { LIBBPF_OPTS(bpf_btf_load_opts, opts); __u32 buf_sz = 0, raw_size; @@ -1367,6 +1369,7 @@ retry_load: opts.log_level = log_level; } + opts.token_fd = token_fd; btf->fd = bpf_btf_load(raw_data, raw_size, &opts); if (btf->fd < 0) { /* time to turn on verbose mode and try again */ @@ -1394,7 +1397,7 @@ done: int btf__load_into_kernel(struct btf *btf) { - return btf_load_into_kernel(btf, NULL, 0, 0); + return btf_load_into_kernel(btf, NULL, 0, 0, 0); } int btf__fd(const struct btf *btf) diff --git a/tools/lib/bpf/elf.c b/tools/lib/bpf/elf.c index b02faec748a5..c92e02394159 100644 --- a/tools/lib/bpf/elf.c +++ b/tools/lib/bpf/elf.c @@ -11,8 +11,6 @@ #include "libbpf_internal.h" #include "str_error.h" -#define STRERR_BUFSIZE 128 - /* A SHT_GNU_versym section holds 16-bit words. This bit is set if * the symbol is hidden and can only be seen when referenced using an * explicit version number. This is a GNU extension. diff --git a/tools/lib/bpf/features.c b/tools/lib/bpf/features.c new file mode 100644 index 000000000000..ce98a334be21 --- /dev/null +++ b/tools/lib/bpf/features.c @@ -0,0 +1,478 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ +#include <linux/kernel.h> +#include <linux/filter.h> +#include "bpf.h" +#include "libbpf.h" +#include "libbpf_common.h" +#include "libbpf_internal.h" +#include "str_error.h" + +static inline __u64 ptr_to_u64(const void *ptr) +{ + return (__u64)(unsigned long)ptr; +} + +static int probe_fd(int fd) +{ + if (fd >= 0) + close(fd); + return fd >= 0; +} + +static int probe_kern_prog_name(int token_fd) +{ + const size_t attr_sz = offsetofend(union bpf_attr, prog_name); + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + union bpf_attr attr; + int ret; + + memset(&attr, 0, attr_sz); + attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; + attr.license = ptr_to_u64("GPL"); + attr.insns = ptr_to_u64(insns); + attr.insn_cnt = (__u32)ARRAY_SIZE(insns); + attr.prog_token_fd = token_fd; + libbpf_strlcpy(attr.prog_name, "libbpf_nametest", sizeof(attr.prog_name)); + + /* make sure loading with name works */ + ret = sys_bpf_prog_load(&attr, attr_sz, PROG_LOAD_ATTEMPTS); + return probe_fd(ret); +} + +static int probe_kern_global_data(int token_fd) +{ + char *cp, errmsg[STRERR_BUFSIZE]; + struct bpf_insn insns[] = { + BPF_LD_MAP_VALUE(BPF_REG_1, 0, 16), + BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 42), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + LIBBPF_OPTS(bpf_map_create_opts, map_opts, .token_fd = token_fd); + LIBBPF_OPTS(bpf_prog_load_opts, prog_opts, .token_fd = token_fd); + int ret, map, insn_cnt = ARRAY_SIZE(insns); + + map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_global", sizeof(int), 32, 1, &map_opts); + if (map < 0) { + ret = -errno; + cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); + pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n", + __func__, cp, -ret); + return ret; + } + + insns[0].imm = map; + + ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, &prog_opts); + close(map); + return probe_fd(ret); +} + +static int probe_kern_btf(int token_fd) +{ + static const char strs[] = "\0int"; + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs), token_fd)); +} + +static int probe_kern_btf_func(int token_fd) +{ + static const char strs[] = "\0int\0x\0a"; + /* void x(int a) {} */ + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* FUNC_PROTO */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0), + BTF_PARAM_ENC(7, 1), + /* FUNC x */ /* [3] */ + BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0), 2), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs), token_fd)); +} + +static int probe_kern_btf_func_global(int token_fd) +{ + static const char strs[] = "\0int\0x\0a"; + /* static void x(int a) {} */ + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* FUNC_PROTO */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0), + BTF_PARAM_ENC(7, 1), + /* FUNC x BTF_FUNC_GLOBAL */ /* [3] */ + BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 2), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs), token_fd)); +} + +static int probe_kern_btf_datasec(int token_fd) +{ + static const char strs[] = "\0x\0.data"; + /* static int a; */ + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* VAR x */ /* [2] */ + BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1), + BTF_VAR_STATIC, + /* DATASEC val */ /* [3] */ + BTF_TYPE_ENC(3, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4), + BTF_VAR_SECINFO_ENC(2, 0, 4), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs), token_fd)); +} + +static int probe_kern_btf_float(int token_fd) +{ + static const char strs[] = "\0float"; + __u32 types[] = { + /* float */ + BTF_TYPE_FLOAT_ENC(1, 4), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs), token_fd)); +} + +static int probe_kern_btf_decl_tag(int token_fd) +{ + static const char strs[] = "\0tag"; + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* VAR x */ /* [2] */ + BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1), + BTF_VAR_STATIC, + /* attr */ + BTF_TYPE_DECL_TAG_ENC(1, 2, -1), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs), token_fd)); +} + +static int probe_kern_btf_type_tag(int token_fd) +{ + static const char strs[] = "\0tag"; + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* attr */ + BTF_TYPE_TYPE_TAG_ENC(1, 1), /* [2] */ + /* ptr */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 2), /* [3] */ + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs), token_fd)); +} + +static int probe_kern_array_mmap(int token_fd) +{ + LIBBPF_OPTS(bpf_map_create_opts, opts, + .map_flags = BPF_F_MMAPABLE, + .token_fd = token_fd, + ); + int fd; + + fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_mmap", sizeof(int), sizeof(int), 1, &opts); + return probe_fd(fd); +} + +static int probe_kern_exp_attach_type(int token_fd) +{ + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE, + .token_fd = token_fd, + ); + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int fd, insn_cnt = ARRAY_SIZE(insns); + + /* use any valid combination of program type and (optional) + * non-zero expected attach type (i.e., not a BPF_CGROUP_INET_INGRESS) + * to see if kernel supports expected_attach_type field for + * BPF_PROG_LOAD command + */ + fd = bpf_prog_load(BPF_PROG_TYPE_CGROUP_SOCK, NULL, "GPL", insns, insn_cnt, &opts); + return probe_fd(fd); +} + +static int probe_kern_probe_read_kernel(int token_fd) +{ + LIBBPF_OPTS(bpf_prog_load_opts, opts, .token_fd = token_fd); + struct bpf_insn insns[] = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), /* r1 = r10 (fp) */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), /* r1 += -8 */ + BPF_MOV64_IMM(BPF_REG_2, 8), /* r2 = 8 */ + BPF_MOV64_IMM(BPF_REG_3, 0), /* r3 = 0 */ + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_probe_read_kernel), + BPF_EXIT_INSN(), + }; + int fd, insn_cnt = ARRAY_SIZE(insns); + + fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, &opts); + return probe_fd(fd); +} + +static int probe_prog_bind_map(int token_fd) +{ + char *cp, errmsg[STRERR_BUFSIZE]; + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + LIBBPF_OPTS(bpf_map_create_opts, map_opts, .token_fd = token_fd); + LIBBPF_OPTS(bpf_prog_load_opts, prog_opts, .token_fd = token_fd); + int ret, map, prog, insn_cnt = ARRAY_SIZE(insns); + + map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_det_bind", sizeof(int), 32, 1, &map_opts); + if (map < 0) { + ret = -errno; + cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); + pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n", + __func__, cp, -ret); + return ret; + } + + prog = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, &prog_opts); + if (prog < 0) { + close(map); + return 0; + } + + ret = bpf_prog_bind_map(prog, map, NULL); + + close(map); + close(prog); + + return ret >= 0; +} + +static int probe_module_btf(int token_fd) +{ + static const char strs[] = "\0int"; + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), + }; + struct bpf_btf_info info; + __u32 len = sizeof(info); + char name[16]; + int fd, err; + + fd = libbpf__load_raw_btf((char *)types, sizeof(types), strs, sizeof(strs), token_fd); + if (fd < 0) + return 0; /* BTF not supported at all */ + + memset(&info, 0, sizeof(info)); + info.name = ptr_to_u64(name); + info.name_len = sizeof(name); + + /* check that BPF_OBJ_GET_INFO_BY_FD supports specifying name pointer; + * kernel's module BTF support coincides with support for + * name/name_len fields in struct bpf_btf_info. + */ + err = bpf_btf_get_info_by_fd(fd, &info, &len); + close(fd); + return !err; +} + +static int probe_perf_link(int token_fd) +{ + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + LIBBPF_OPTS(bpf_prog_load_opts, opts, .token_fd = token_fd); + int prog_fd, link_fd, err; + + prog_fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", + insns, ARRAY_SIZE(insns), &opts); + if (prog_fd < 0) + return -errno; + + /* use invalid perf_event FD to get EBADF, if link is supported; + * otherwise EINVAL should be returned + */ + link_fd = bpf_link_create(prog_fd, -1, BPF_PERF_EVENT, NULL); + err = -errno; /* close() can clobber errno */ + + if (link_fd >= 0) + close(link_fd); + close(prog_fd); + + return link_fd < 0 && err == -EBADF; +} + +static int probe_uprobe_multi_link(int token_fd) +{ + LIBBPF_OPTS(bpf_prog_load_opts, load_opts, + .expected_attach_type = BPF_TRACE_UPROBE_MULTI, + .token_fd = token_fd, + ); + LIBBPF_OPTS(bpf_link_create_opts, link_opts); + struct bpf_insn insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + int prog_fd, link_fd, err; + unsigned long offset = 0; + + prog_fd = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, "GPL", + insns, ARRAY_SIZE(insns), &load_opts); + if (prog_fd < 0) + return -errno; + + /* Creating uprobe in '/' binary should fail with -EBADF. */ + link_opts.uprobe_multi.path = "/"; + link_opts.uprobe_multi.offsets = &offset; + link_opts.uprobe_multi.cnt = 1; + + link_fd = bpf_link_create(prog_fd, -1, BPF_TRACE_UPROBE_MULTI, &link_opts); + err = -errno; /* close() can clobber errno */ + + if (link_fd >= 0) + close(link_fd); + close(prog_fd); + + return link_fd < 0 && err == -EBADF; +} + +static int probe_kern_bpf_cookie(int token_fd) +{ + struct bpf_insn insns[] = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_attach_cookie), + BPF_EXIT_INSN(), + }; + LIBBPF_OPTS(bpf_prog_load_opts, opts, .token_fd = token_fd); + int ret, insn_cnt = ARRAY_SIZE(insns); + + ret = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, &opts); + return probe_fd(ret); +} + +static int probe_kern_btf_enum64(int token_fd) +{ + static const char strs[] = "\0enum64"; + __u32 types[] = { + BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 0), 8), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs), token_fd)); +} + +typedef int (*feature_probe_fn)(int /* token_fd */); + +static struct kern_feature_cache feature_cache; + +static struct kern_feature_desc { + const char *desc; + feature_probe_fn probe; +} feature_probes[__FEAT_CNT] = { + [FEAT_PROG_NAME] = { + "BPF program name", probe_kern_prog_name, + }, + [FEAT_GLOBAL_DATA] = { + "global variables", probe_kern_global_data, + }, + [FEAT_BTF] = { + "minimal BTF", probe_kern_btf, + }, + [FEAT_BTF_FUNC] = { + "BTF functions", probe_kern_btf_func, + }, + [FEAT_BTF_GLOBAL_FUNC] = { + "BTF global function", probe_kern_btf_func_global, + }, + [FEAT_BTF_DATASEC] = { + "BTF data section and variable", probe_kern_btf_datasec, + }, + [FEAT_ARRAY_MMAP] = { + "ARRAY map mmap()", probe_kern_array_mmap, + }, + [FEAT_EXP_ATTACH_TYPE] = { + "BPF_PROG_LOAD expected_attach_type attribute", + probe_kern_exp_attach_type, + }, + [FEAT_PROBE_READ_KERN] = { + "bpf_probe_read_kernel() helper", probe_kern_probe_read_kernel, + }, + [FEAT_PROG_BIND_MAP] = { + "BPF_PROG_BIND_MAP support", probe_prog_bind_map, + }, + [FEAT_MODULE_BTF] = { + "module BTF support", probe_module_btf, + }, + [FEAT_BTF_FLOAT] = { + "BTF_KIND_FLOAT support", probe_kern_btf_float, + }, + [FEAT_PERF_LINK] = { + "BPF perf link support", probe_perf_link, + }, + [FEAT_BTF_DECL_TAG] = { + "BTF_KIND_DECL_TAG support", probe_kern_btf_decl_tag, + }, + [FEAT_BTF_TYPE_TAG] = { + "BTF_KIND_TYPE_TAG support", probe_kern_btf_type_tag, + }, + [FEAT_MEMCG_ACCOUNT] = { + "memcg-based memory accounting", probe_memcg_account, + }, + [FEAT_BPF_COOKIE] = { + "BPF cookie support", probe_kern_bpf_cookie, + }, + [FEAT_BTF_ENUM64] = { + "BTF_KIND_ENUM64 support", probe_kern_btf_enum64, + }, + [FEAT_SYSCALL_WRAPPER] = { + "Kernel using syscall wrapper", probe_kern_syscall_wrapper, + }, + [FEAT_UPROBE_MULTI_LINK] = { + "BPF multi-uprobe link support", probe_uprobe_multi_link, + }, +}; + +bool feat_supported(struct kern_feature_cache *cache, enum kern_feature_id feat_id) +{ + struct kern_feature_desc *feat = &feature_probes[feat_id]; + int ret; + + /* assume global feature cache, unless custom one is provided */ + if (!cache) + cache = &feature_cache; + + if (READ_ONCE(cache->res[feat_id]) == FEAT_UNKNOWN) { + ret = feat->probe(cache->token_fd); + if (ret > 0) { + WRITE_ONCE(cache->res[feat_id], FEAT_SUPPORTED); + } else if (ret == 0) { + WRITE_ONCE(cache->res[feat_id], FEAT_MISSING); + } else { + pr_warn("Detection of kernel %s support failed: %d\n", feat->desc, ret); + WRITE_ONCE(cache->res[feat_id], FEAT_MISSING); + } + } + + return READ_ONCE(cache->res[feat_id]) == FEAT_SUPPORTED; +} diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index ea9b8158c20d..4b5ff9508e18 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -59,6 +59,8 @@ #define BPF_FS_MAGIC 0xcafe4a11 #endif +#define BPF_FS_DEFAULT_PATH "/sys/fs/bpf" + #define BPF_INSN_SZ (sizeof(struct bpf_insn)) /* vsprintf() in __base_pr() uses nonliteral format string. It may break @@ -693,6 +695,10 @@ struct bpf_object { struct usdt_manager *usdt_man; + struct kern_feature_cache *feat_cache; + char *token_path; + int token_fd; + char path[]; }; @@ -2192,7 +2198,7 @@ static int build_map_pin_path(struct bpf_map *map, const char *path) int err; if (!path) - path = "/sys/fs/bpf"; + path = BPF_FS_DEFAULT_PATH; err = pathname_concat(buf, sizeof(buf), path, bpf_map__name(map)); if (err) @@ -3054,9 +3060,15 @@ static bool prog_needs_vmlinux_btf(struct bpf_program *prog) return false; } +static bool map_needs_vmlinux_btf(struct bpf_map *map) +{ + return bpf_map__is_struct_ops(map); +} + static bool obj_needs_vmlinux_btf(const struct bpf_object *obj) { struct bpf_program *prog; + struct bpf_map *map; int i; /* CO-RE relocations need kernel BTF, only when btf_custom_path @@ -3081,6 +3093,11 @@ static bool obj_needs_vmlinux_btf(const struct bpf_object *obj) return true; } + bpf_object__for_each_map(map, obj) { + if (map_needs_vmlinux_btf(map)) + return true; + } + return false; } @@ -3268,7 +3285,7 @@ skip_exception_cb: } else { /* currently BPF_BTF_LOAD only supports log_level 1 */ err = btf_load_into_kernel(kern_btf, obj->log_buf, obj->log_size, - obj->log_level ? 1 : 0); + obj->log_level ? 1 : 0, obj->token_fd); } if (sanitize) { if (!err) { @@ -4591,6 +4608,63 @@ int bpf_map__set_max_entries(struct bpf_map *map, __u32 max_entries) return 0; } +static int bpf_object_prepare_token(struct bpf_object *obj) +{ + const char *bpffs_path; + int bpffs_fd = -1, token_fd, err; + bool mandatory; + enum libbpf_print_level level; + + /* token is already set up */ + if (obj->token_fd > 0) + return 0; + /* token is explicitly prevented */ + if (obj->token_fd < 0) { + pr_debug("object '%s': token is prevented, skipping...\n", obj->name); + /* reset to zero to avoid extra checks during map_create and prog_load steps */ + obj->token_fd = 0; + return 0; + } + + mandatory = obj->token_path != NULL; + level = mandatory ? LIBBPF_WARN : LIBBPF_DEBUG; + + bpffs_path = obj->token_path ?: BPF_FS_DEFAULT_PATH; + bpffs_fd = open(bpffs_path, O_DIRECTORY, O_RDWR); + if (bpffs_fd < 0) { + err = -errno; + __pr(level, "object '%s': failed (%d) to open BPF FS mount at '%s'%s\n", + obj->name, err, bpffs_path, + mandatory ? "" : ", skipping optional step..."); + return mandatory ? err : 0; + } + + token_fd = bpf_token_create(bpffs_fd, 0); + close(bpffs_fd); + if (token_fd < 0) { + if (!mandatory && token_fd == -ENOENT) { + pr_debug("object '%s': BPF FS at '%s' doesn't have BPF token delegation set up, skipping...\n", + obj->name, bpffs_path); + return 0; + } + __pr(level, "object '%s': failed (%d) to create BPF token from '%s'%s\n", + obj->name, token_fd, bpffs_path, + mandatory ? "" : ", skipping optional step..."); + return mandatory ? token_fd : 0; + } + + obj->feat_cache = calloc(1, sizeof(*obj->feat_cache)); + if (!obj->feat_cache) { + close(token_fd); + return -ENOMEM; + } + + obj->token_fd = token_fd; + obj->feat_cache->token_fd = token_fd; + + return 0; +} + static int bpf_object__probe_loading(struct bpf_object *obj) { @@ -4600,6 +4674,7 @@ bpf_object__probe_loading(struct bpf_object *obj) BPF_EXIT_INSN(), }; int ret, insn_cnt = ARRAY_SIZE(insns); + LIBBPF_OPTS(bpf_prog_load_opts, opts, .token_fd = obj->token_fd); if (obj->gen_loader) return 0; @@ -4609,9 +4684,9 @@ bpf_object__probe_loading(struct bpf_object *obj) pr_warn("Failed to bump RLIMIT_MEMLOCK (err = %d), you might need to do it explicitly!\n", ret); /* make sure basic loading works */ - ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL); + ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, &opts); if (ret < 0) - ret = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, NULL); + ret = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, &opts); if (ret < 0) { ret = errno; cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); @@ -4626,462 +4701,18 @@ bpf_object__probe_loading(struct bpf_object *obj) return 0; } -static int probe_fd(int fd) -{ - if (fd >= 0) - close(fd); - return fd >= 0; -} - -static int probe_kern_prog_name(void) -{ - const size_t attr_sz = offsetofend(union bpf_attr, prog_name); - struct bpf_insn insns[] = { - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - }; - union bpf_attr attr; - int ret; - - memset(&attr, 0, attr_sz); - attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; - attr.license = ptr_to_u64("GPL"); - attr.insns = ptr_to_u64(insns); - attr.insn_cnt = (__u32)ARRAY_SIZE(insns); - libbpf_strlcpy(attr.prog_name, "libbpf_nametest", sizeof(attr.prog_name)); - - /* make sure loading with name works */ - ret = sys_bpf_prog_load(&attr, attr_sz, PROG_LOAD_ATTEMPTS); - return probe_fd(ret); -} - -static int probe_kern_global_data(void) -{ - char *cp, errmsg[STRERR_BUFSIZE]; - struct bpf_insn insns[] = { - BPF_LD_MAP_VALUE(BPF_REG_1, 0, 16), - BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 42), - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - }; - int ret, map, insn_cnt = ARRAY_SIZE(insns); - - map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_global", sizeof(int), 32, 1, NULL); - if (map < 0) { - ret = -errno; - cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); - pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n", - __func__, cp, -ret); - return ret; - } - - insns[0].imm = map; - - ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL); - close(map); - return probe_fd(ret); -} - -static int probe_kern_btf(void) -{ - static const char strs[] = "\0int"; - __u32 types[] = { - /* int */ - BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); -} - -static int probe_kern_btf_func(void) -{ - static const char strs[] = "\0int\0x\0a"; - /* void x(int a) {} */ - __u32 types[] = { - /* int */ - BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ - /* FUNC_PROTO */ /* [2] */ - BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0), - BTF_PARAM_ENC(7, 1), - /* FUNC x */ /* [3] */ - BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0), 2), - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); -} - -static int probe_kern_btf_func_global(void) -{ - static const char strs[] = "\0int\0x\0a"; - /* static void x(int a) {} */ - __u32 types[] = { - /* int */ - BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ - /* FUNC_PROTO */ /* [2] */ - BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, 1), 0), - BTF_PARAM_ENC(7, 1), - /* FUNC x BTF_FUNC_GLOBAL */ /* [3] */ - BTF_TYPE_ENC(5, BTF_INFO_ENC(BTF_KIND_FUNC, 0, BTF_FUNC_GLOBAL), 2), - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); -} - -static int probe_kern_btf_datasec(void) -{ - static const char strs[] = "\0x\0.data"; - /* static int a; */ - __u32 types[] = { - /* int */ - BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ - /* VAR x */ /* [2] */ - BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1), - BTF_VAR_STATIC, - /* DATASEC val */ /* [3] */ - BTF_TYPE_ENC(3, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4), - BTF_VAR_SECINFO_ENC(2, 0, 4), - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); -} - -static int probe_kern_btf_float(void) -{ - static const char strs[] = "\0float"; - __u32 types[] = { - /* float */ - BTF_TYPE_FLOAT_ENC(1, 4), - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); -} - -static int probe_kern_btf_decl_tag(void) -{ - static const char strs[] = "\0tag"; - __u32 types[] = { - /* int */ - BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ - /* VAR x */ /* [2] */ - BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1), - BTF_VAR_STATIC, - /* attr */ - BTF_TYPE_DECL_TAG_ENC(1, 2, -1), - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); -} - -static int probe_kern_btf_type_tag(void) -{ - static const char strs[] = "\0tag"; - __u32 types[] = { - /* int */ - BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ - /* attr */ - BTF_TYPE_TYPE_TAG_ENC(1, 1), /* [2] */ - /* ptr */ - BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 2), /* [3] */ - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); -} - -static int probe_kern_array_mmap(void) -{ - LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_MMAPABLE); - int fd; - - fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_mmap", sizeof(int), sizeof(int), 1, &opts); - return probe_fd(fd); -} - -static int probe_kern_exp_attach_type(void) -{ - LIBBPF_OPTS(bpf_prog_load_opts, opts, .expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE); - struct bpf_insn insns[] = { - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - }; - int fd, insn_cnt = ARRAY_SIZE(insns); - - /* use any valid combination of program type and (optional) - * non-zero expected attach type (i.e., not a BPF_CGROUP_INET_INGRESS) - * to see if kernel supports expected_attach_type field for - * BPF_PROG_LOAD command - */ - fd = bpf_prog_load(BPF_PROG_TYPE_CGROUP_SOCK, NULL, "GPL", insns, insn_cnt, &opts); - return probe_fd(fd); -} - -static int probe_kern_probe_read_kernel(void) -{ - struct bpf_insn insns[] = { - BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), /* r1 = r10 (fp) */ - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8), /* r1 += -8 */ - BPF_MOV64_IMM(BPF_REG_2, 8), /* r2 = 8 */ - BPF_MOV64_IMM(BPF_REG_3, 0), /* r3 = 0 */ - BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_probe_read_kernel), - BPF_EXIT_INSN(), - }; - int fd, insn_cnt = ARRAY_SIZE(insns); - - fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, NULL); - return probe_fd(fd); -} - -static int probe_prog_bind_map(void) -{ - char *cp, errmsg[STRERR_BUFSIZE]; - struct bpf_insn insns[] = { - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - }; - int ret, map, prog, insn_cnt = ARRAY_SIZE(insns); - - map = bpf_map_create(BPF_MAP_TYPE_ARRAY, "libbpf_det_bind", sizeof(int), 32, 1, NULL); - if (map < 0) { - ret = -errno; - cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); - pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n", - __func__, cp, -ret); - return ret; - } - - prog = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL); - if (prog < 0) { - close(map); - return 0; - } - - ret = bpf_prog_bind_map(prog, map, NULL); - - close(map); - close(prog); - - return ret >= 0; -} - -static int probe_module_btf(void) -{ - static const char strs[] = "\0int"; - __u32 types[] = { - /* int */ - BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), - }; - struct bpf_btf_info info; - __u32 len = sizeof(info); - char name[16]; - int fd, err; - - fd = libbpf__load_raw_btf((char *)types, sizeof(types), strs, sizeof(strs)); - if (fd < 0) - return 0; /* BTF not supported at all */ - - memset(&info, 0, sizeof(info)); - info.name = ptr_to_u64(name); - info.name_len = sizeof(name); - - /* check that BPF_OBJ_GET_INFO_BY_FD supports specifying name pointer; - * kernel's module BTF support coincides with support for - * name/name_len fields in struct bpf_btf_info. - */ - err = bpf_btf_get_info_by_fd(fd, &info, &len); - close(fd); - return !err; -} - -static int probe_perf_link(void) -{ - struct bpf_insn insns[] = { - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - }; - int prog_fd, link_fd, err; - - prog_fd = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", - insns, ARRAY_SIZE(insns), NULL); - if (prog_fd < 0) - return -errno; - - /* use invalid perf_event FD to get EBADF, if link is supported; - * otherwise EINVAL should be returned - */ - link_fd = bpf_link_create(prog_fd, -1, BPF_PERF_EVENT, NULL); - err = -errno; /* close() can clobber errno */ - - if (link_fd >= 0) - close(link_fd); - close(prog_fd); - - return link_fd < 0 && err == -EBADF; -} - -static int probe_uprobe_multi_link(void) -{ - LIBBPF_OPTS(bpf_prog_load_opts, load_opts, - .expected_attach_type = BPF_TRACE_UPROBE_MULTI, - ); - LIBBPF_OPTS(bpf_link_create_opts, link_opts); - struct bpf_insn insns[] = { - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - }; - int prog_fd, link_fd, err; - unsigned long offset = 0; - - prog_fd = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, "GPL", - insns, ARRAY_SIZE(insns), &load_opts); - if (prog_fd < 0) - return -errno; - - /* Creating uprobe in '/' binary should fail with -EBADF. */ - link_opts.uprobe_multi.path = "/"; - link_opts.uprobe_multi.offsets = &offset; - link_opts.uprobe_multi.cnt = 1; - - link_fd = bpf_link_create(prog_fd, -1, BPF_TRACE_UPROBE_MULTI, &link_opts); - err = -errno; /* close() can clobber errno */ - - if (link_fd >= 0) - close(link_fd); - close(prog_fd); - - return link_fd < 0 && err == -EBADF; -} - -static int probe_kern_bpf_cookie(void) -{ - struct bpf_insn insns[] = { - BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_attach_cookie), - BPF_EXIT_INSN(), - }; - int ret, insn_cnt = ARRAY_SIZE(insns); - - ret = bpf_prog_load(BPF_PROG_TYPE_KPROBE, NULL, "GPL", insns, insn_cnt, NULL); - return probe_fd(ret); -} - -static int probe_kern_btf_enum64(void) -{ - static const char strs[] = "\0enum64"; - __u32 types[] = { - BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_ENUM64, 0, 0), 8), - }; - - return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs))); -} - -static int probe_kern_syscall_wrapper(void); - -enum kern_feature_result { - FEAT_UNKNOWN = 0, - FEAT_SUPPORTED = 1, - FEAT_MISSING = 2, -}; - -typedef int (*feature_probe_fn)(void); - -static struct kern_feature_desc { - const char *desc; - feature_probe_fn probe; - enum kern_feature_result res; -} feature_probes[__FEAT_CNT] = { - [FEAT_PROG_NAME] = { - "BPF program name", probe_kern_prog_name, - }, - [FEAT_GLOBAL_DATA] = { - "global variables", probe_kern_global_data, - }, - [FEAT_BTF] = { - "minimal BTF", probe_kern_btf, - }, - [FEAT_BTF_FUNC] = { - "BTF functions", probe_kern_btf_func, - }, - [FEAT_BTF_GLOBAL_FUNC] = { - "BTF global function", probe_kern_btf_func_global, - }, - [FEAT_BTF_DATASEC] = { - "BTF data section and variable", probe_kern_btf_datasec, - }, - [FEAT_ARRAY_MMAP] = { - "ARRAY map mmap()", probe_kern_array_mmap, - }, - [FEAT_EXP_ATTACH_TYPE] = { - "BPF_PROG_LOAD expected_attach_type attribute", - probe_kern_exp_attach_type, - }, - [FEAT_PROBE_READ_KERN] = { - "bpf_probe_read_kernel() helper", probe_kern_probe_read_kernel, - }, - [FEAT_PROG_BIND_MAP] = { - "BPF_PROG_BIND_MAP support", probe_prog_bind_map, - }, - [FEAT_MODULE_BTF] = { - "module BTF support", probe_module_btf, - }, - [FEAT_BTF_FLOAT] = { - "BTF_KIND_FLOAT support", probe_kern_btf_float, - }, - [FEAT_PERF_LINK] = { - "BPF perf link support", probe_perf_link, - }, - [FEAT_BTF_DECL_TAG] = { - "BTF_KIND_DECL_TAG support", probe_kern_btf_decl_tag, - }, - [FEAT_BTF_TYPE_TAG] = { - "BTF_KIND_TYPE_TAG support", probe_kern_btf_type_tag, - }, - [FEAT_MEMCG_ACCOUNT] = { - "memcg-based memory accounting", probe_memcg_account, - }, - [FEAT_BPF_COOKIE] = { - "BPF cookie support", probe_kern_bpf_cookie, - }, - [FEAT_BTF_ENUM64] = { - "BTF_KIND_ENUM64 support", probe_kern_btf_enum64, - }, - [FEAT_SYSCALL_WRAPPER] = { - "Kernel using syscall wrapper", probe_kern_syscall_wrapper, - }, - [FEAT_UPROBE_MULTI_LINK] = { - "BPF multi-uprobe link support", probe_uprobe_multi_link, - }, -}; - bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id) { - struct kern_feature_desc *feat = &feature_probes[feat_id]; - int ret; - if (obj && obj->gen_loader) /* To generate loader program assume the latest kernel * to avoid doing extra prog_load, map_create syscalls. */ return true; - if (READ_ONCE(feat->res) == FEAT_UNKNOWN) { - ret = feat->probe(); - if (ret > 0) { - WRITE_ONCE(feat->res, FEAT_SUPPORTED); - } else if (ret == 0) { - WRITE_ONCE(feat->res, FEAT_MISSING); - } else { - pr_warn("Detection of kernel %s support failed: %d\n", feat->desc, ret); - WRITE_ONCE(feat->res, FEAT_MISSING); - } - } + if (obj->token_fd) + return feat_supported(obj->feat_cache, feat_id); - return READ_ONCE(feat->res) == FEAT_SUPPORTED; + return feat_supported(NULL, feat_id); } static bool map_is_reuse_compat(const struct bpf_map *map, int map_fd) @@ -5200,6 +4831,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b create_attr.map_flags = def->map_flags; create_attr.numa_node = map->numa_node; create_attr.map_extra = map->map_extra; + create_attr.token_fd = obj->token_fd; if (bpf_map__is_struct_ops(map)) create_attr.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id; @@ -7035,6 +6667,7 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog load_attr.attach_btf_id = prog->attach_btf_id; load_attr.kern_version = kern_version; load_attr.prog_ifindex = prog->prog_ifindex; + load_attr.token_fd = obj->token_fd; /* specify func_info/line_info only if kernel supports them */ btf_fd = bpf_object__btf_fd(obj); @@ -7496,10 +7129,10 @@ static int bpf_object_init_progs(struct bpf_object *obj, const struct bpf_object static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf, size_t obj_buf_sz, const struct bpf_object_open_opts *opts) { - const char *obj_name, *kconfig, *btf_tmp_path; + const char *obj_name, *kconfig, *btf_tmp_path, *token_path; struct bpf_object *obj; char tmp_name[64]; - int err; + int err, token_fd; char *log_buf; size_t log_size; __u32 log_level; @@ -7533,6 +7166,28 @@ static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf, if (log_size && !log_buf) return ERR_PTR(-EINVAL); + token_path = OPTS_GET(opts, bpf_token_path, NULL); + token_fd = OPTS_GET(opts, bpf_token_fd, -1); + /* non-empty token path can't be combined with invalid token FD */ + if (token_path && token_path[0] != '\0' && token_fd < 0) + return ERR_PTR(-EINVAL); + /* empty token path can't be combined with valid token FD */ + if (token_path && token_path[0] == '\0' && token_fd > 0) + return ERR_PTR(-EINVAL); + /* if user didn't specify bpf_token_path/bpf_token_fd explicitly, + * check if LIBBPF_BPF_TOKEN_PATH envvar was set and treat it as + * bpf_token_path option + */ + if (token_fd == 0 && !token_path) + token_path = getenv("LIBBPF_BPF_TOKEN_PATH"); + /* empty token_path is equivalent to invalid token_fd */ + if (token_path && token_path[0] == '\0') { + token_path = NULL; + token_fd = -1; + } + if (token_path && strlen(token_path) >= PATH_MAX) + return ERR_PTR(-ENAMETOOLONG); + obj = bpf_object__new(path, obj_buf, obj_buf_sz, obj_name); if (IS_ERR(obj)) return obj; @@ -7541,6 +7196,19 @@ static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf, obj->log_size = log_size; obj->log_level = log_level; + obj->token_fd = token_fd <= 0 ? token_fd : dup_good_fd(token_fd); + if (token_fd > 0 && obj->token_fd < 0) { + err = -errno; + goto out; + } + if (token_path) { + obj->token_path = strdup(token_path); + if (!obj->token_path) { + err = -ENOMEM; + goto out; + } + } + btf_tmp_path = OPTS_GET(opts, btf_custom_path, NULL); if (btf_tmp_path) { if (strlen(btf_tmp_path) >= PATH_MAX) { @@ -8051,7 +7719,8 @@ static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const ch if (obj->gen_loader) bpf_gen__init(obj->gen_loader, extra_log_level, obj->nr_programs, obj->nr_maps); - err = bpf_object__probe_loading(obj); + err = bpf_object_prepare_token(obj); + err = err ? : bpf_object__probe_loading(obj); err = err ? : bpf_object__load_vmlinux_btf(obj, false); err = err ? : bpf_object__resolve_externs(obj, obj->kconfig); err = err ? : bpf_object__sanitize_and_load_btf(obj); @@ -8588,6 +8257,11 @@ void bpf_object__close(struct bpf_object *obj) } zfree(&obj->programs); + zfree(&obj->feat_cache); + zfree(&obj->token_path); + if (obj->token_fd > 0) + close(obj->token_fd); + free(obj); } @@ -10601,7 +10275,7 @@ static const char *arch_specific_syscall_pfx(void) #endif } -static int probe_kern_syscall_wrapper(void) +int probe_kern_syscall_wrapper(int token_fd) { char syscall_name[64]; const char *ksys_pfx; diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 6cd9c501624f..916904bd2a7a 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -177,10 +177,45 @@ struct bpf_object_open_opts { * logs through its print callback. */ __u32 kernel_log_level; + /* FD of a BPF token instantiated by user through bpf_token_create() + * API. BPF object will keep dup()'ed FD internally, so passed token + * FD can be closed after BPF object/skeleton open step. + * + * Setting bpf_token_fd to negative value disables libbpf's automatic + * attempt to create BPF token from default BPF FS mount point + * (/sys/fs/bpf), in case this default behavior is undesirable. + * + * If bpf_token_path and bpf_token_fd are not specified, libbpf will + * consult LIBBPF_BPF_TOKEN_PATH environment variable. If set, it will + * be taken as a value of bpf_token_path option and will force libbpf + * to either create BPF token from provided custom BPF FS path, or + * will disable implicit BPF token creation, if envvar value is an + * empty string. + * + * bpf_token_path and bpf_token_fd are mutually exclusive and only one + * of those options should be set. Either of them overrides + * LIBBPF_BPF_TOKEN_PATH envvar. + */ + int bpf_token_fd; + /* Path to BPF FS mount point to derive BPF token from. + * + * Created BPF token will be used for all bpf() syscall operations + * that accept BPF token (e.g., map creation, BTF and program loads, + * etc) automatically within instantiated BPF object. + * + * Setting bpf_token_path option to empty string disables libbpf's + * automatic attempt to create BPF token from default BPF FS mount + * point (/sys/fs/bpf), in case this default behavior is undesirable. + * + * bpf_token_path and bpf_token_fd are mutually exclusive and only one + * of those options should be set. Either of them overrides + * LIBBPF_BPF_TOKEN_PATH envvar. + */ + const char *bpf_token_path; size_t :0; }; -#define bpf_object_open_opts__last_field kernel_log_level +#define bpf_object_open_opts__last_field bpf_token_path /** * @brief **bpf_object__open()** creates a bpf_object by opening diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 91c5aef7dae7..df7657b65c47 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -401,6 +401,7 @@ LIBBPF_1.3.0 { bpf_program__attach_netkit; bpf_program__attach_tcx; bpf_program__attach_uprobe_multi; + bpf_token_create; ring__avail_data_size; ring__consume; ring__consumer_pos; diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index b5d334754e5d..4cda32298c49 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -360,15 +360,32 @@ enum kern_feature_id { __FEAT_CNT, }; -int probe_memcg_account(void); +enum kern_feature_result { + FEAT_UNKNOWN = 0, + FEAT_SUPPORTED = 1, + FEAT_MISSING = 2, +}; + +struct kern_feature_cache { + enum kern_feature_result res[__FEAT_CNT]; + int token_fd; +}; + +bool feat_supported(struct kern_feature_cache *cache, enum kern_feature_id feat_id); bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id); + +int probe_kern_syscall_wrapper(int token_fd); +int probe_memcg_account(int token_fd); int bump_rlimit_memlock(void); int parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz); int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz); int libbpf__load_raw_btf(const char *raw_types, size_t types_len, - const char *str_sec, size_t str_len); -int btf_load_into_kernel(struct btf *btf, char *log_buf, size_t log_sz, __u32 log_level); + const char *str_sec, size_t str_len, + int token_fd); +int btf_load_into_kernel(struct btf *btf, + char *log_buf, size_t log_sz, __u32 log_level, + int token_fd); struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf); void btf_get_kernel_prefix_kind(enum bpf_attach_type attach_type, @@ -532,6 +549,17 @@ static inline bool is_ldimm64_insn(struct bpf_insn *insn) return insn->code == (BPF_LD | BPF_IMM | BPF_DW); } +/* Unconditionally dup FD, ensuring it doesn't use [0, 2] range. + * Original FD is not closed or altered in any other way. + * Preserves original FD value, if it's invalid (negative). + */ +static inline int dup_good_fd(int fd) +{ + if (fd < 0) + return fd; + return fcntl(fd, F_DUPFD_CLOEXEC, 3); +} + /* if fd is stdin, stdout, or stderr, dup to a fd greater than 2 * Takes ownership of the fd passed in, and closes it if calling * fcntl(fd, F_DUPFD_CLOEXEC, 3). @@ -543,7 +571,7 @@ static inline int ensure_good_fd(int fd) if (fd < 0) return fd; if (fd < 3) { - fd = fcntl(fd, F_DUPFD_CLOEXEC, 3); + fd = dup_good_fd(fd); saved_errno = errno; close(old_fd); errno = saved_errno; diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index 9c4db90b92b6..8e7437006639 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -219,7 +219,8 @@ int libbpf_probe_bpf_prog_type(enum bpf_prog_type prog_type, const void *opts) } int libbpf__load_raw_btf(const char *raw_types, size_t types_len, - const char *str_sec, size_t str_len) + const char *str_sec, size_t str_len, + int token_fd) { struct btf_header hdr = { .magic = BTF_MAGIC, @@ -229,6 +230,7 @@ int libbpf__load_raw_btf(const char *raw_types, size_t types_len, .str_off = types_len, .str_len = str_len, }; + LIBBPF_OPTS(bpf_btf_load_opts, opts, .token_fd = token_fd); int btf_fd, btf_len; __u8 *raw_btf; @@ -241,7 +243,7 @@ int libbpf__load_raw_btf(const char *raw_types, size_t types_len, memcpy(raw_btf + hdr.hdr_len, raw_types, hdr.type_len); memcpy(raw_btf + hdr.hdr_len + hdr.type_len, str_sec, hdr.str_len); - btf_fd = bpf_btf_load(raw_btf, btf_len, NULL); + btf_fd = bpf_btf_load(raw_btf, btf_len, &opts); free(raw_btf); return btf_fd; @@ -271,7 +273,7 @@ static int load_local_storage_btf(void) }; return libbpf__load_raw_btf((char *)types, sizeof(types), - strs, sizeof(strs)); + strs, sizeof(strs), 0); } static int probe_map_create(enum bpf_map_type map_type) diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c index 5ced96d99f8c..52a2901e8bd0 100644 --- a/tools/lib/bpf/linker.c +++ b/tools/lib/bpf/linker.c @@ -719,13 +719,25 @@ static int linker_sanity_check_elf(struct src_obj *obj) return -EINVAL; } - if (sec->shdr->sh_addralign && !is_pow_of_2(sec->shdr->sh_addralign)) + if (sec->shdr->sh_addralign && !is_pow_of_2(sec->shdr->sh_addralign)) { + pr_warn("ELF section #%zu alignment %llu is non pow-of-2 alignment in %s\n", + sec->sec_idx, (long long unsigned)sec->shdr->sh_addralign, + obj->filename); return -EINVAL; - if (sec->shdr->sh_addralign != sec->data->d_align) + } + if (sec->shdr->sh_addralign != sec->data->d_align) { + pr_warn("ELF section #%zu has inconsistent alignment addr=%llu != d=%llu in %s\n", + sec->sec_idx, (long long unsigned)sec->shdr->sh_addralign, + (long long unsigned)sec->data->d_align, obj->filename); return -EINVAL; + } - if (sec->shdr->sh_size != sec->data->d_size) + if (sec->shdr->sh_size != sec->data->d_size) { + pr_warn("ELF section #%zu has inconsistent section size sh=%llu != d=%llu in %s\n", + sec->sec_idx, (long long unsigned)sec->shdr->sh_size, + (long long unsigned)sec->data->d_size, obj->filename); return -EINVAL; + } switch (sec->shdr->sh_type) { case SHT_SYMTAB: @@ -737,8 +749,12 @@ static int linker_sanity_check_elf(struct src_obj *obj) break; case SHT_PROGBITS: if (sec->shdr->sh_flags & SHF_EXECINSTR) { - if (sec->shdr->sh_size % sizeof(struct bpf_insn) != 0) + if (sec->shdr->sh_size % sizeof(struct bpf_insn) != 0) { + pr_warn("ELF section #%zu has unexpected size alignment %llu in %s\n", + sec->sec_idx, (long long unsigned)sec->shdr->sh_size, + obj->filename); return -EINVAL; + } } break; case SHT_NOBITS: diff --git a/tools/lib/bpf/str_error.h b/tools/lib/bpf/str_error.h index a139334d57b6..626d7ffb03d6 100644 --- a/tools/lib/bpf/str_error.h +++ b/tools/lib/bpf/str_error.h @@ -2,5 +2,8 @@ #ifndef __LIBBPF_STR_ERROR_H #define __LIBBPF_STR_ERROR_H +#define STRERR_BUFSIZE 128 + char *libbpf_strerror_r(int err, char *dst, int len); + #endif /* __LIBBPF_STR_ERROR_H */ diff --git a/tools/testing/selftests/bpf/bpf_kfuncs.h b/tools/testing/selftests/bpf/bpf_kfuncs.h index 5ca68ff0b59f..b4e78c1eb37b 100644 --- a/tools/testing/selftests/bpf/bpf_kfuncs.h +++ b/tools/testing/selftests/bpf/bpf_kfuncs.h @@ -55,4 +55,14 @@ void *bpf_cast_to_kern_ctx(void *) __ksym; void *bpf_rdonly_cast(void *obj, __u32 btf_id) __ksym; +extern int bpf_get_file_xattr(struct file *file, const char *name, + struct bpf_dynptr *value_ptr) __ksym; +extern int bpf_get_fsverity_digest(struct file *file, struct bpf_dynptr *digest_ptr) __ksym; + +extern struct bpf_key *bpf_lookup_user_key(__u32 serial, __u64 flags) __ksym; +extern struct bpf_key *bpf_lookup_system_key(__u64 id) __ksym; +extern void bpf_key_put(struct bpf_key *key) __ksym; +extern int bpf_verify_pkcs7_signature(struct bpf_dynptr *data_ptr, + struct bpf_dynptr *sig_ptr, + struct bpf_key *trusted_keyring) __ksym; #endif diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c index 5aa133bf3688..19be9c63d5e8 100644 --- a/tools/testing/selftests/bpf/cgroup_helpers.c +++ b/tools/testing/selftests/bpf/cgroup_helpers.c @@ -689,3 +689,19 @@ int get_cgroup1_hierarchy_id(const char *subsys_name) fclose(file); return found ? id : -1; } + +/** + * open_classid() - Open a cgroupv1 net_cls classid + * + * This function expects the cgroup work dir to be already created, as we + * open it here. + * + * On success, it returns the file descriptor. On failure it returns -1. + */ +int open_classid(void) +{ + char cgroup_workdir[PATH_MAX + 1]; + + format_classid_path(cgroup_workdir); + return open(cgroup_workdir, O_RDONLY); +} diff --git a/tools/testing/selftests/bpf/cgroup_helpers.h b/tools/testing/selftests/bpf/cgroup_helpers.h index ee053641c026..502845160d88 100644 --- a/tools/testing/selftests/bpf/cgroup_helpers.h +++ b/tools/testing/selftests/bpf/cgroup_helpers.h @@ -33,6 +33,7 @@ void cleanup_cgroup_environment(void); int set_classid(void); int join_classid(void); unsigned long long get_classid_cgroup_id(void); +int open_classid(void); int setup_classid_environment(void); void cleanup_classid_environment(void); diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index 3ec5927ec3e5..c125c441abc7 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -23,6 +23,7 @@ CONFIG_FPROBE=y CONFIG_FTRACE_SYSCALLS=y CONFIG_FUNCTION_ERROR_INJECTION=y CONFIG_FUNCTION_TRACER=y +CONFIG_FS_VERITY=y CONFIG_GENEVE=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y @@ -82,7 +83,7 @@ CONFIG_SECURITY=y CONFIG_SECURITYFS=y CONFIG_TEST_BPF=m CONFIG_USERFAULTFD=y +CONFIG_VSOCKETS=y CONFIG_VXLAN=y CONFIG_XDP_SOCKETS=y CONFIG_XFRM_INTERFACE=y -CONFIG_VSOCKETS=y diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c index 8fb4a04fbbc0..816145bcb647 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf.c +++ b/tools/testing/selftests/bpf/prog_tests/btf.c @@ -4630,11 +4630,6 @@ static int test_btf_id(unsigned int test_num) /* The map holds the last ref to BTF and its btf_id */ close(map_fd); map_fd = -1; - btf_fd[0] = bpf_btf_get_fd_by_id(map_info.btf_id); - if (CHECK(btf_fd[0] >= 0, "BTF lingers")) { - err = -1; - goto done; - } fprintf(stderr, "OK"); diff --git a/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c b/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c index 63e776f4176e..747761572098 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c +++ b/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c @@ -19,6 +19,21 @@ struct socket_cookie { __u64 cookie_value; }; +static bool is_cgroup1; +static int target_hid; + +#define CGROUP_MODE_SET(skel) \ +{ \ + skel->bss->is_cgroup1 = is_cgroup1; \ + skel->bss->target_hid = target_hid; \ +} + +static void cgroup_mode_value_init(bool cgroup, int hid) +{ + is_cgroup1 = cgroup; + target_hid = hid; +} + static void test_tp_btf(int cgroup_fd) { struct cgrp_ls_tp_btf *skel; @@ -29,6 +44,8 @@ static void test_tp_btf(int cgroup_fd) if (!ASSERT_OK_PTR(skel, "skel_open_and_load")) return; + CGROUP_MODE_SET(skel); + /* populate a value in map_b */ err = bpf_map_update_elem(bpf_map__fd(skel->maps.map_b), &cgroup_fd, &val1, BPF_ANY); if (!ASSERT_OK(err, "map_update_elem")) @@ -130,6 +147,8 @@ static void test_recursion(int cgroup_fd) if (!ASSERT_OK_PTR(skel, "skel_open_and_load")) return; + CGROUP_MODE_SET(skel); + err = cgrp_ls_recursion__attach(skel); if (!ASSERT_OK(err, "skel_attach")) goto out; @@ -165,6 +184,8 @@ static void test_cgroup_iter_sleepable(int cgroup_fd, __u64 cgroup_id) if (!ASSERT_OK_PTR(skel, "skel_open")) return; + CGROUP_MODE_SET(skel); + bpf_program__set_autoload(skel->progs.cgroup_iter, true); err = cgrp_ls_sleepable__load(skel); if (!ASSERT_OK(err, "skel_load")) @@ -202,6 +223,7 @@ static void test_yes_rcu_lock(__u64 cgroup_id) if (!ASSERT_OK_PTR(skel, "skel_open")) return; + CGROUP_MODE_SET(skel); skel->bss->target_pid = syscall(SYS_gettid); bpf_program__set_autoload(skel->progs.yes_rcu_lock, true); @@ -229,6 +251,8 @@ static void test_no_rcu_lock(void) if (!ASSERT_OK_PTR(skel, "skel_open")) return; + CGROUP_MODE_SET(skel); + bpf_program__set_autoload(skel->progs.no_rcu_lock, true); err = cgrp_ls_sleepable__load(skel); ASSERT_ERR(err, "skel_load"); @@ -236,7 +260,25 @@ static void test_no_rcu_lock(void) cgrp_ls_sleepable__destroy(skel); } -void test_cgrp_local_storage(void) +static void test_cgrp1_no_rcu_lock(void) +{ + struct cgrp_ls_sleepable *skel; + int err; + + skel = cgrp_ls_sleepable__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + return; + + CGROUP_MODE_SET(skel); + + bpf_program__set_autoload(skel->progs.cgrp1_no_rcu_lock, true); + err = cgrp_ls_sleepable__load(skel); + ASSERT_OK(err, "skel_load"); + + cgrp_ls_sleepable__destroy(skel); +} + +static void cgrp2_local_storage(void) { __u64 cgroup_id; int cgroup_fd; @@ -245,6 +287,8 @@ void test_cgrp_local_storage(void) if (!ASSERT_GE(cgroup_fd, 0, "join_cgroup /cgrp_local_storage")) return; + cgroup_mode_value_init(0, -1); + cgroup_id = get_cgroup_id("/cgrp_local_storage"); if (test__start_subtest("tp_btf")) test_tp_btf(cgroup_fd); @@ -263,3 +307,55 @@ void test_cgrp_local_storage(void) close(cgroup_fd); } + +static void cgrp1_local_storage(void) +{ + int cgrp1_fd, cgrp1_hid, cgrp1_id, err; + + /* Setup cgroup1 hierarchy */ + err = setup_classid_environment(); + if (!ASSERT_OK(err, "setup_classid_environment")) + return; + + err = join_classid(); + if (!ASSERT_OK(err, "join_cgroup1")) + goto cleanup; + + cgrp1_fd = open_classid(); + if (!ASSERT_GE(cgrp1_fd, 0, "cgroup1 fd")) + goto cleanup; + + cgrp1_id = get_classid_cgroup_id(); + if (!ASSERT_GE(cgrp1_id, 0, "cgroup1 id")) + goto close_fd; + + cgrp1_hid = get_cgroup1_hierarchy_id("net_cls"); + if (!ASSERT_GE(cgrp1_hid, 0, "cgroup1 hid")) + goto close_fd; + + cgroup_mode_value_init(1, cgrp1_hid); + + if (test__start_subtest("cgrp1_tp_btf")) + test_tp_btf(cgrp1_fd); + if (test__start_subtest("cgrp1_recursion")) + test_recursion(cgrp1_fd); + if (test__start_subtest("cgrp1_negative")) + test_negative(); + if (test__start_subtest("cgrp1_iter_sleepable")) + test_cgroup_iter_sleepable(cgrp1_fd, cgrp1_id); + if (test__start_subtest("cgrp1_yes_rcu_lock")) + test_yes_rcu_lock(cgrp1_id); + if (test__start_subtest("cgrp1_no_rcu_lock")) + test_cgrp1_no_rcu_lock(); + +close_fd: + close(cgrp1_fd); +cleanup: + cleanup_classid_environment(); +} + +void test_cgrp_local_storage(void) +{ + cgrp2_local_storage(); + cgrp1_local_storage(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/cpumask.c b/tools/testing/selftests/bpf/prog_tests/cpumask.c index 756ea8b590b6..c2e886399e3c 100644 --- a/tools/testing/selftests/bpf/prog_tests/cpumask.c +++ b/tools/testing/selftests/bpf/prog_tests/cpumask.c @@ -18,6 +18,7 @@ static const char * const cpumask_success_testcases[] = { "test_insert_leave", "test_insert_remove_release", "test_global_mask_rcu", + "test_cpumask_weight", }; static void verify_success(const char *prog_name) diff --git a/tools/testing/selftests/bpf/prog_tests/fs_kfuncs.c b/tools/testing/selftests/bpf/prog_tests/fs_kfuncs.c new file mode 100644 index 000000000000..37056ba73847 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/fs_kfuncs.c @@ -0,0 +1,142 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include <stdlib.h> +#include <sys/types.h> +#include <sys/xattr.h> +#include <linux/fsverity.h> +#include <unistd.h> +#include <test_progs.h> +#include "test_get_xattr.skel.h" +#include "test_fsverity.skel.h" + +static const char testfile[] = "/tmp/test_progs_fs_kfuncs"; + +static void test_xattr(void) +{ + struct test_get_xattr *skel = NULL; + int fd = -1, err; + + fd = open(testfile, O_CREAT | O_RDONLY, 0644); + if (!ASSERT_GE(fd, 0, "create_file")) + return; + + close(fd); + fd = -1; + + err = setxattr(testfile, "user.kfuncs", "hello", sizeof("hello"), 0); + if (err && errno == EOPNOTSUPP) { + printf("%s:SKIP:local fs doesn't support xattr (%d)\n" + "To run this test, make sure /tmp filesystem supports xattr.\n", + __func__, errno); + test__skip(); + goto out; + } + + if (!ASSERT_OK(err, "setxattr")) + goto out; + + skel = test_get_xattr__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_get_xattr__open_and_load")) + goto out; + + skel->bss->monitored_pid = getpid(); + err = test_get_xattr__attach(skel); + + if (!ASSERT_OK(err, "test_get_xattr__attach")) + goto out; + + fd = open(testfile, O_RDONLY, 0644); + if (!ASSERT_GE(fd, 0, "open_file")) + goto out; + + ASSERT_EQ(skel->bss->found_xattr, 1, "found_xattr"); + +out: + close(fd); + test_get_xattr__destroy(skel); + remove(testfile); +} + +#ifndef SHA256_DIGEST_SIZE +#define SHA256_DIGEST_SIZE 32 +#endif + +static void test_fsverity(void) +{ + struct fsverity_enable_arg arg = {0}; + struct test_fsverity *skel = NULL; + struct fsverity_digest *d; + int fd, err; + char buffer[4096]; + + fd = open(testfile, O_CREAT | O_RDWR, 0644); + if (!ASSERT_GE(fd, 0, "create_file")) + return; + + /* Write random buffer, so the file is not empty */ + err = write(fd, buffer, 4096); + if (!ASSERT_EQ(err, 4096, "write_file")) + goto out; + close(fd); + + /* Reopen read-only, otherwise FS_IOC_ENABLE_VERITY will fail */ + fd = open(testfile, O_RDONLY, 0644); + if (!ASSERT_GE(fd, 0, "open_file1")) + return; + + /* Enable fsverity for the file. + * If the file system doesn't support verity, this will fail. Skip + * the test in such case. + */ + arg.version = 1; + arg.hash_algorithm = FS_VERITY_HASH_ALG_SHA256; + arg.block_size = 4096; + err = ioctl(fd, FS_IOC_ENABLE_VERITY, &arg); + if (err) { + printf("%s:SKIP:local fs doesn't support fsverity (%d)\n" + "To run this test, try enable CONFIG_FS_VERITY and enable FSVerity for the filesystem.\n", + __func__, errno); + test__skip(); + goto out; + } + + skel = test_fsverity__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_fsverity__open_and_load")) + goto out; + + /* Get fsverity_digest from ioctl */ + d = (struct fsverity_digest *)skel->bss->expected_digest; + d->digest_algorithm = FS_VERITY_HASH_ALG_SHA256; + d->digest_size = SHA256_DIGEST_SIZE; + err = ioctl(fd, FS_IOC_MEASURE_VERITY, skel->bss->expected_digest); + if (!ASSERT_OK(err, "ioctl_FS_IOC_MEASURE_VERITY")) + goto out; + + skel->bss->monitored_pid = getpid(); + err = test_fsverity__attach(skel); + if (!ASSERT_OK(err, "test_fsverity__attach")) + goto out; + + /* Reopen the file to trigger the program */ + close(fd); + fd = open(testfile, O_RDONLY); + if (!ASSERT_GE(fd, 0, "open_file2")) + goto out; + + ASSERT_EQ(skel->bss->got_fsverity, 1, "got_fsverity"); + ASSERT_EQ(skel->bss->digest_matches, 1, "digest_matches"); +out: + close(fd); + test_fsverity__destroy(skel); + remove(testfile); +} + +void test_fs_kfuncs(void) +{ + if (test__start_subtest("xattr")) + test_xattr(); + + if (test__start_subtest("fsverity")) + test_fsverity(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/global_func_dead_code.c b/tools/testing/selftests/bpf/prog_tests/global_func_dead_code.c new file mode 100644 index 000000000000..65309894b27a --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/global_func_dead_code.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include <test_progs.h> +#include "verifier_global_subprogs.skel.h" +#include "freplace_dead_global_func.skel.h" + +void test_global_func_dead_code(void) +{ + struct verifier_global_subprogs *tgt_skel = NULL; + struct freplace_dead_global_func *skel = NULL; + char log_buf[4096]; + int err, tgt_fd; + + /* first, try to load target with good global subprog */ + tgt_skel = verifier_global_subprogs__open(); + if (!ASSERT_OK_PTR(tgt_skel, "tgt_skel_good_open")) + return; + + bpf_program__set_autoload(tgt_skel->progs.chained_global_func_calls_success, true); + + err = verifier_global_subprogs__load(tgt_skel); + if (!ASSERT_OK(err, "tgt_skel_good_load")) + goto out; + + tgt_fd = bpf_program__fd(tgt_skel->progs.chained_global_func_calls_success); + + /* Attach to good non-eliminated subprog */ + skel = freplace_dead_global_func__open(); + if (!ASSERT_OK_PTR(skel, "skel_good_open")) + goto out; + + err = bpf_program__set_attach_target(skel->progs.freplace_prog, tgt_fd, "global_good"); + ASSERT_OK(err, "attach_target_good"); + + err = freplace_dead_global_func__load(skel); + if (!ASSERT_OK(err, "skel_good_load")) + goto out; + + freplace_dead_global_func__destroy(skel); + + /* Try attaching to dead code-eliminated subprog */ + skel = freplace_dead_global_func__open(); + if (!ASSERT_OK_PTR(skel, "skel_dead_open")) + goto out; + + bpf_program__set_log_buf(skel->progs.freplace_prog, log_buf, sizeof(log_buf)); + err = bpf_program__set_attach_target(skel->progs.freplace_prog, tgt_fd, "global_dead"); + ASSERT_OK(err, "attach_target_dead"); + + err = freplace_dead_global_func__load(skel); + if (!ASSERT_ERR(err, "skel_dead_load")) + goto out; + + ASSERT_HAS_SUBSTR(log_buf, "Subprog global_dead doesn't exist", "dead_subprog_missing_msg"); + +out: + verifier_global_subprogs__destroy(tgt_skel); + freplace_dead_global_func__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c index 4041cfa670eb..05000810e28e 100644 --- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c +++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c @@ -222,6 +222,7 @@ static void test_attach_api_fails(void) "bpf_fentry_test2", }; __u64 cookies[2]; + int saved_error; addrs[0] = ksym_get_addr("bpf_fentry_test1"); addrs[1] = ksym_get_addr("bpf_fentry_test2"); @@ -238,10 +239,11 @@ static void test_attach_api_fails(void) /* fail_1 - pattern and opts NULL */ link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe_manual, NULL, NULL); + saved_error = -errno; if (!ASSERT_ERR_PTR(link, "fail_1")) goto cleanup; - if (!ASSERT_EQ(libbpf_get_error(link), -EINVAL, "fail_1_error")) + if (!ASSERT_EQ(saved_error, -EINVAL, "fail_1_error")) goto cleanup; /* fail_2 - both addrs and syms set */ @@ -252,10 +254,11 @@ static void test_attach_api_fails(void) link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe_manual, NULL, &opts); + saved_error = -errno; if (!ASSERT_ERR_PTR(link, "fail_2")) goto cleanup; - if (!ASSERT_EQ(libbpf_get_error(link), -EINVAL, "fail_2_error")) + if (!ASSERT_EQ(saved_error, -EINVAL, "fail_2_error")) goto cleanup; /* fail_3 - pattern and addrs set */ @@ -266,10 +269,11 @@ static void test_attach_api_fails(void) link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe_manual, "ksys_*", &opts); + saved_error = -errno; if (!ASSERT_ERR_PTR(link, "fail_3")) goto cleanup; - if (!ASSERT_EQ(libbpf_get_error(link), -EINVAL, "fail_3_error")) + if (!ASSERT_EQ(saved_error, -EINVAL, "fail_3_error")) goto cleanup; /* fail_4 - pattern and cnt set */ @@ -280,10 +284,11 @@ static void test_attach_api_fails(void) link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe_manual, "ksys_*", &opts); + saved_error = -errno; if (!ASSERT_ERR_PTR(link, "fail_4")) goto cleanup; - if (!ASSERT_EQ(libbpf_get_error(link), -EINVAL, "fail_4_error")) + if (!ASSERT_EQ(saved_error, -EINVAL, "fail_4_error")) goto cleanup; /* fail_5 - pattern and cookies */ @@ -294,10 +299,26 @@ static void test_attach_api_fails(void) link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe_manual, "ksys_*", &opts); + saved_error = -errno; if (!ASSERT_ERR_PTR(link, "fail_5")) goto cleanup; - if (!ASSERT_EQ(libbpf_get_error(link), -EINVAL, "fail_5_error")) + if (!ASSERT_EQ(saved_error, -EINVAL, "fail_5_error")) + goto cleanup; + + /* fail_6 - abnormal cnt */ + opts.addrs = (const unsigned long *) addrs; + opts.syms = NULL; + opts.cnt = INT_MAX; + opts.cookies = NULL; + + link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe_manual, + NULL, &opts); + saved_error = -errno; + if (!ASSERT_ERR_PTR(link, "fail_6")) + goto cleanup; + + if (!ASSERT_EQ(saved_error, -E2BIG, "fail_6_error")) goto cleanup; cleanup: diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c index 9f766ddd946a..4ed46ed58a7b 100644 --- a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c +++ b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c @@ -30,6 +30,8 @@ void test_libbpf_probe_prog_types(void) if (prog_type == BPF_PROG_TYPE_UNSPEC) continue; + if (strcmp(prog_type_name, "__MAX_BPF_PROG_TYPE") == 0) + continue; if (!test__start_subtest(prog_type_name)) continue; @@ -68,6 +70,8 @@ void test_libbpf_probe_map_types(void) if (map_type == BPF_MAP_TYPE_UNSPEC) continue; + if (strcmp(map_type_name, "__MAX_BPF_MAP_TYPE") == 0) + continue; if (!test__start_subtest(map_type_name)) continue; diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c index c440ea3311ed..62ea855ec4d0 100644 --- a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c +++ b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c @@ -87,7 +87,7 @@ static void test_libbpf_bpf_link_type_str(void) const char *link_type_str; char buf[256]; - if (link_type == MAX_BPF_LINK_TYPE) + if (link_type == __MAX_BPF_LINK_TYPE) continue; link_type_name = btf__str_by_offset(btf, e->name_off); @@ -132,6 +132,9 @@ static void test_libbpf_bpf_map_type_str(void) const char *map_type_str; char buf[256]; + if (map_type == __MAX_BPF_MAP_TYPE) + continue; + map_type_name = btf__str_by_offset(btf, e->name_off); map_type_str = libbpf_bpf_map_type_str(map_type); ASSERT_OK_PTR(map_type_str, map_type_name); @@ -186,6 +189,9 @@ static void test_libbpf_bpf_prog_type_str(void) const char *prog_type_str; char buf[256]; + if (prog_type == __MAX_BPF_PROG_TYPE) + continue; + prog_type_name = btf__str_by_offset(btf, e->name_off); prog_type_str = libbpf_bpf_prog_type_str(prog_type); ASSERT_OK_PTR(prog_type_str, prog_type_name); diff --git a/tools/testing/selftests/bpf/prog_tests/local_kptr_stash.c b/tools/testing/selftests/bpf/prog_tests/local_kptr_stash.c index e6e50a394472..827e713f6cf1 100644 --- a/tools/testing/selftests/bpf/prog_tests/local_kptr_stash.c +++ b/tools/testing/selftests/bpf/prog_tests/local_kptr_stash.c @@ -48,6 +48,27 @@ static void test_local_kptr_stash_plain(void) local_kptr_stash__destroy(skel); } +static void test_local_kptr_stash_local_with_root(void) +{ + LIBBPF_OPTS(bpf_test_run_opts, opts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); + struct local_kptr_stash *skel; + int ret; + + skel = local_kptr_stash__open_and_load(); + if (!ASSERT_OK_PTR(skel, "local_kptr_stash__open_and_load")) + return; + + ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.stash_local_with_root), &opts); + ASSERT_OK(ret, "local_kptr_stash_add_local_with_root run"); + ASSERT_OK(opts.retval, "local_kptr_stash_add_local_with_root retval"); + + local_kptr_stash__destroy(skel); +} + static void test_local_kptr_stash_unstash(void) { LIBBPF_OPTS(bpf_test_run_opts, opts, @@ -115,6 +136,8 @@ void test_local_kptr_stash(void) test_local_kptr_stash_simple(); if (test__start_subtest("local_kptr_stash_plain")) test_local_kptr_stash_plain(); + if (test__start_subtest("local_kptr_stash_local_with_root")) + test_local_kptr_stash_local_with_root(); if (test__start_subtest("local_kptr_stash_unstash")) test_local_kptr_stash_unstash(); if (test__start_subtest("refcount_acquire_without_unstash")) diff --git a/tools/testing/selftests/bpf/prog_tests/map_btf.c b/tools/testing/selftests/bpf/prog_tests/map_btf.c new file mode 100644 index 000000000000..2c4ef6037573 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/map_btf.c @@ -0,0 +1,98 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023. Huawei Technologies Co., Ltd */ +#include <test_progs.h> + +#include "normal_map_btf.skel.h" +#include "map_in_map_btf.skel.h" + +static void do_test_normal_map_btf(void) +{ + struct normal_map_btf *skel; + int i, err, new_fd = -1; + int map_fd_arr[64]; + + skel = normal_map_btf__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_load")) + return; + + err = normal_map_btf__attach(skel); + if (!ASSERT_OK(err, "attach")) + goto out; + + skel->bss->pid = getpid(); + usleep(1); + ASSERT_TRUE(skel->bss->done, "done"); + + /* Use percpu_array to slow bpf_map_free_deferred() down. + * The memory allocation may fail, so doesn't check the returned fd. + */ + for (i = 0; i < ARRAY_SIZE(map_fd_arr); i++) + map_fd_arr[i] = bpf_map_create(BPF_MAP_TYPE_PERCPU_ARRAY, NULL, 4, 4, 256, NULL); + + /* Close array fd later */ + new_fd = dup(bpf_map__fd(skel->maps.array)); +out: + normal_map_btf__destroy(skel); + if (new_fd < 0) + return; + /* Use kern_sync_rcu() to wait for the start of the free of the bpf + * program and use an assumed delay to wait for the release of the map + * btf which is held by other maps (e.g, bss). After that, array map + * holds the last reference of map btf. + */ + kern_sync_rcu(); + usleep(4000); + /* Spawn multiple kworkers to delay the invocation of + * bpf_map_free_deferred() for array map. + */ + for (i = 0; i < ARRAY_SIZE(map_fd_arr); i++) { + if (map_fd_arr[i] < 0) + continue; + close(map_fd_arr[i]); + } + close(new_fd); +} + +static void do_test_map_in_map_btf(void) +{ + int err, zero = 0, new_fd = -1; + struct map_in_map_btf *skel; + + skel = map_in_map_btf__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_load")) + return; + + err = map_in_map_btf__attach(skel); + if (!ASSERT_OK(err, "attach")) + goto out; + + skel->bss->pid = getpid(); + usleep(1); + ASSERT_TRUE(skel->bss->done, "done"); + + /* Close inner_array fd later */ + new_fd = dup(bpf_map__fd(skel->maps.inner_array)); + /* Defer the free of inner_array */ + err = bpf_map__delete_elem(skel->maps.outer_array, &zero, sizeof(zero), 0); + ASSERT_OK(err, "delete inner map"); +out: + map_in_map_btf__destroy(skel); + if (new_fd < 0) + return; + /* Use kern_sync_rcu() to wait for the start of the free of the bpf + * program and use an assumed delay to wait for the free of the outer + * map and the release of map btf. After that, inner map holds the last + * reference of map btf. + */ + kern_sync_rcu(); + usleep(10000); + close(new_fd); +} + +void test_map_btf(void) +{ + if (test__start_subtest("array_btf")) + do_test_normal_map_btf(); + if (test__start_subtest("inner_array_btf")) + do_test_map_in_map_btf(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/map_in_map.c b/tools/testing/selftests/bpf/prog_tests/map_in_map.c new file mode 100644 index 000000000000..d2a10eb4e5b5 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/map_in_map.c @@ -0,0 +1,141 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023. Huawei Technologies Co., Ltd */ +#define _GNU_SOURCE +#include <unistd.h> +#include <sys/syscall.h> +#include <test_progs.h> +#include <bpf/btf.h> +#include "access_map_in_map.skel.h" + +struct thread_ctx { + pthread_barrier_t barrier; + int outer_map_fd; + int start, abort; + int loop, err; +}; + +static int wait_for_start_or_abort(struct thread_ctx *ctx) +{ + while (!ctx->start && !ctx->abort) + usleep(1); + return ctx->abort ? -1 : 0; +} + +static void *update_map_fn(void *data) +{ + struct thread_ctx *ctx = data; + int loop = ctx->loop, err = 0; + + if (wait_for_start_or_abort(ctx) < 0) + return NULL; + pthread_barrier_wait(&ctx->barrier); + + while (loop-- > 0) { + int fd, zero = 0; + + fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, 4, 4, 1, NULL); + if (fd < 0) { + err |= 1; + pthread_barrier_wait(&ctx->barrier); + continue; + } + + /* Remove the old inner map */ + if (bpf_map_update_elem(ctx->outer_map_fd, &zero, &fd, 0) < 0) + err |= 2; + close(fd); + pthread_barrier_wait(&ctx->barrier); + } + + ctx->err = err; + + return NULL; +} + +static void *access_map_fn(void *data) +{ + struct thread_ctx *ctx = data; + int loop = ctx->loop; + + if (wait_for_start_or_abort(ctx) < 0) + return NULL; + pthread_barrier_wait(&ctx->barrier); + + while (loop-- > 0) { + /* Access the old inner map */ + syscall(SYS_getpgid); + pthread_barrier_wait(&ctx->barrier); + } + + return NULL; +} + +static void test_map_in_map_access(const char *prog_name, const char *map_name) +{ + struct access_map_in_map *skel; + struct bpf_map *outer_map; + struct bpf_program *prog; + struct thread_ctx ctx; + pthread_t tid[2]; + int err; + + skel = access_map_in_map__open(); + if (!ASSERT_OK_PTR(skel, "access_map_in_map open")) + return; + + prog = bpf_object__find_program_by_name(skel->obj, prog_name); + if (!ASSERT_OK_PTR(prog, "find program")) + goto out; + bpf_program__set_autoload(prog, true); + + outer_map = bpf_object__find_map_by_name(skel->obj, map_name); + if (!ASSERT_OK_PTR(outer_map, "find map")) + goto out; + + err = access_map_in_map__load(skel); + if (!ASSERT_OK(err, "access_map_in_map load")) + goto out; + + err = access_map_in_map__attach(skel); + if (!ASSERT_OK(err, "access_map_in_map attach")) + goto out; + + skel->bss->tgid = getpid(); + + memset(&ctx, 0, sizeof(ctx)); + pthread_barrier_init(&ctx.barrier, NULL, 2); + ctx.outer_map_fd = bpf_map__fd(outer_map); + ctx.loop = 4; + + err = pthread_create(&tid[0], NULL, update_map_fn, &ctx); + if (!ASSERT_OK(err, "close_thread")) + goto out; + + err = pthread_create(&tid[1], NULL, access_map_fn, &ctx); + if (!ASSERT_OK(err, "read_thread")) { + ctx.abort = 1; + pthread_join(tid[0], NULL); + goto out; + } + + ctx.start = 1; + pthread_join(tid[0], NULL); + pthread_join(tid[1], NULL); + + ASSERT_OK(ctx.err, "err"); +out: + access_map_in_map__destroy(skel); +} + +void test_map_in_map(void) +{ + if (test__start_subtest("acc_map_in_array")) + test_map_in_map_access("access_map_in_array", "outer_array_map"); + if (test__start_subtest("sleepable_acc_map_in_array")) + test_map_in_map_access("sleepable_access_map_in_array", "outer_array_map"); + if (test__start_subtest("acc_map_in_htab")) + test_map_in_map_access("access_map_in_htab", "outer_htab_map"); + if (test__start_subtest("sleepable_acc_map_in_htab")) + test_map_in_map_access("sleepable_access_map_in_htab", "outer_htab_map"); +} + diff --git a/tools/testing/selftests/bpf/prog_tests/syscall.c b/tools/testing/selftests/bpf/prog_tests/syscall.c index f4d40001155a..0be8301c0ffd 100644 --- a/tools/testing/selftests/bpf/prog_tests/syscall.c +++ b/tools/testing/selftests/bpf/prog_tests/syscall.c @@ -12,7 +12,7 @@ struct args { int btf_fd; }; -void test_syscall(void) +static void test_syscall_load_prog(void) { static char verifier_log[8192]; struct args ctx = { @@ -32,7 +32,7 @@ void test_syscall(void) if (!ASSERT_OK_PTR(skel, "skel_load")) goto cleanup; - prog_fd = bpf_program__fd(skel->progs.bpf_prog); + prog_fd = bpf_program__fd(skel->progs.load_prog); err = bpf_prog_test_run_opts(prog_fd, &tattr); ASSERT_EQ(err, 0, "err"); ASSERT_EQ(tattr.retval, 1, "retval"); @@ -53,3 +53,29 @@ cleanup: if (ctx.btf_fd > 0) close(ctx.btf_fd); } + +static void test_syscall_update_outer_map(void) +{ + LIBBPF_OPTS(bpf_test_run_opts, opts); + struct syscall *skel; + int err, prog_fd; + + skel = syscall__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_load")) + goto cleanup; + + prog_fd = bpf_program__fd(skel->progs.update_outer_map); + err = bpf_prog_test_run_opts(prog_fd, &opts); + ASSERT_EQ(err, 0, "err"); + ASSERT_EQ(opts.retval, 1, "retval"); +cleanup: + syscall__destroy(skel); +} + +void test_syscall(void) +{ + if (test__start_subtest("load_prog")) + test_syscall_load_prog(); + if (test__start_subtest("update_outer_map")) + test_syscall_update_outer_map(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/test_tunnel.c b/tools/testing/selftests/bpf/prog_tests/test_tunnel.c index d149ab98798d..2b3c6dd66259 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_tunnel.c +++ b/tools/testing/selftests/bpf/prog_tests/test_tunnel.c @@ -50,6 +50,7 @@ */ #include <arpa/inet.h> +#include <linux/if_link.h> #include <linux/if_tun.h> #include <linux/limits.h> #include <linux/sysctl.h> @@ -92,6 +93,11 @@ #define IPIP_TUNL_DEV0 "ipip00" #define IPIP_TUNL_DEV1 "ipip11" +#define XFRM_AUTH "0x1111111111111111111111111111111111111111" +#define XFRM_ENC "0x22222222222222222222222222222222" +#define XFRM_SPI_IN_TO_OUT 0x1 +#define XFRM_SPI_OUT_TO_IN 0x2 + #define PING_ARGS "-i 0.01 -c 3 -w 10 -q" static int config_device(void) @@ -264,6 +270,92 @@ static void delete_ipip_tunnel(void) SYS_NOFAIL("ip fou del port 5555 2> /dev/null"); } +static int add_xfrm_tunnel(void) +{ + /* at_ns0 namespace + * at_ns0 -> root + */ + SYS(fail, + "ip netns exec at_ns0 " + "ip xfrm state add src %s dst %s proto esp " + "spi %d reqid 1 mode tunnel replay-window 42 " + "auth-trunc 'hmac(sha1)' %s 96 enc 'cbc(aes)' %s", + IP4_ADDR_VETH0, IP4_ADDR1_VETH1, XFRM_SPI_IN_TO_OUT, XFRM_AUTH, XFRM_ENC); + SYS(fail, + "ip netns exec at_ns0 " + "ip xfrm policy add src %s/32 dst %s/32 dir out " + "tmpl src %s dst %s proto esp reqid 1 " + "mode tunnel", + IP4_ADDR_TUNL_DEV0, IP4_ADDR_TUNL_DEV1, IP4_ADDR_VETH0, IP4_ADDR1_VETH1); + + /* root -> at_ns0 */ + SYS(fail, + "ip netns exec at_ns0 " + "ip xfrm state add src %s dst %s proto esp " + "spi %d reqid 2 mode tunnel " + "auth-trunc 'hmac(sha1)' %s 96 enc 'cbc(aes)' %s", + IP4_ADDR1_VETH1, IP4_ADDR_VETH0, XFRM_SPI_OUT_TO_IN, XFRM_AUTH, XFRM_ENC); + SYS(fail, + "ip netns exec at_ns0 " + "ip xfrm policy add src %s/32 dst %s/32 dir in " + "tmpl src %s dst %s proto esp reqid 2 " + "mode tunnel", + IP4_ADDR_TUNL_DEV1, IP4_ADDR_TUNL_DEV0, IP4_ADDR1_VETH1, IP4_ADDR_VETH0); + + /* address & route */ + SYS(fail, "ip netns exec at_ns0 ip addr add dev veth0 %s/32", + IP4_ADDR_TUNL_DEV0); + SYS(fail, "ip netns exec at_ns0 ip route add %s dev veth0 via %s src %s", + IP4_ADDR_TUNL_DEV1, IP4_ADDR1_VETH1, IP4_ADDR_TUNL_DEV0); + + /* root namespace + * at_ns0 -> root + */ + SYS(fail, + "ip xfrm state add src %s dst %s proto esp " + "spi %d reqid 1 mode tunnel replay-window 42 " + "auth-trunc 'hmac(sha1)' %s 96 enc 'cbc(aes)' %s", + IP4_ADDR_VETH0, IP4_ADDR1_VETH1, XFRM_SPI_IN_TO_OUT, XFRM_AUTH, XFRM_ENC); + SYS(fail, + "ip xfrm policy add src %s/32 dst %s/32 dir in " + "tmpl src %s dst %s proto esp reqid 1 " + "mode tunnel", + IP4_ADDR_TUNL_DEV0, IP4_ADDR_TUNL_DEV1, IP4_ADDR_VETH0, IP4_ADDR1_VETH1); + + /* root -> at_ns0 */ + SYS(fail, + "ip xfrm state add src %s dst %s proto esp " + "spi %d reqid 2 mode tunnel " + "auth-trunc 'hmac(sha1)' %s 96 enc 'cbc(aes)' %s", + IP4_ADDR1_VETH1, IP4_ADDR_VETH0, XFRM_SPI_OUT_TO_IN, XFRM_AUTH, XFRM_ENC); + SYS(fail, + "ip xfrm policy add src %s/32 dst %s/32 dir out " + "tmpl src %s dst %s proto esp reqid 2 " + "mode tunnel", + IP4_ADDR_TUNL_DEV1, IP4_ADDR_TUNL_DEV0, IP4_ADDR1_VETH1, IP4_ADDR_VETH0); + + /* address & route */ + SYS(fail, "ip addr add dev veth1 %s/32", IP4_ADDR_TUNL_DEV1); + SYS(fail, "ip route add %s dev veth1 via %s src %s", + IP4_ADDR_TUNL_DEV0, IP4_ADDR_VETH0, IP4_ADDR_TUNL_DEV1); + + return 0; +fail: + return -1; +} + +static void delete_xfrm_tunnel(void) +{ + SYS_NOFAIL("ip xfrm policy delete dir out src %s/32 dst %s/32 2> /dev/null", + IP4_ADDR_TUNL_DEV1, IP4_ADDR_TUNL_DEV0); + SYS_NOFAIL("ip xfrm policy delete dir in src %s/32 dst %s/32 2> /dev/null", + IP4_ADDR_TUNL_DEV0, IP4_ADDR_TUNL_DEV1); + SYS_NOFAIL("ip xfrm state delete src %s dst %s proto esp spi %d 2> /dev/null", + IP4_ADDR_VETH0, IP4_ADDR1_VETH1, XFRM_SPI_IN_TO_OUT); + SYS_NOFAIL("ip xfrm state delete src %s dst %s proto esp spi %d 2> /dev/null", + IP4_ADDR1_VETH1, IP4_ADDR_VETH0, XFRM_SPI_OUT_TO_IN); +} + static int test_ping(int family, const char *addr) { SYS(fail, "%s %s %s > /dev/null", ping_command(family), PING_ARGS, addr); @@ -532,25 +624,85 @@ done: test_tunnel_kern__destroy(skel); } +static void test_xfrm_tunnel(void) +{ + DECLARE_LIBBPF_OPTS(bpf_tc_hook, tc_hook, + .attach_point = BPF_TC_INGRESS); + LIBBPF_OPTS(bpf_xdp_attach_opts, opts); + struct test_tunnel_kern *skel = NULL; + struct nstoken *nstoken; + int xdp_prog_fd; + int tc_prog_fd; + int ifindex; + int err; + + err = add_xfrm_tunnel(); + if (!ASSERT_OK(err, "add_xfrm_tunnel")) + return; + + skel = test_tunnel_kern__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load")) + goto done; + + ifindex = if_nametoindex("veth1"); + if (!ASSERT_NEQ(ifindex, 0, "veth1 ifindex")) + goto done; + + /* attach tc prog to tunnel dev */ + tc_hook.ifindex = ifindex; + tc_prog_fd = bpf_program__fd(skel->progs.xfrm_get_state); + if (!ASSERT_GE(tc_prog_fd, 0, "bpf_program__fd")) + goto done; + if (attach_tc_prog(&tc_hook, tc_prog_fd, -1)) + goto done; + + /* attach xdp prog to tunnel dev */ + xdp_prog_fd = bpf_program__fd(skel->progs.xfrm_get_state_xdp); + if (!ASSERT_GE(xdp_prog_fd, 0, "bpf_program__fd")) + goto done; + err = bpf_xdp_attach(ifindex, xdp_prog_fd, XDP_FLAGS_REPLACE, &opts); + if (!ASSERT_OK(err, "bpf_xdp_attach")) + goto done; + + /* ping from at_ns0 namespace test */ + nstoken = open_netns("at_ns0"); + err = test_ping(AF_INET, IP4_ADDR_TUNL_DEV1); + close_netns(nstoken); + if (!ASSERT_OK(err, "test_ping")) + goto done; + + if (!ASSERT_EQ(skel->bss->xfrm_reqid, 1, "req_id")) + goto done; + if (!ASSERT_EQ(skel->bss->xfrm_spi, XFRM_SPI_IN_TO_OUT, "spi")) + goto done; + if (!ASSERT_EQ(skel->bss->xfrm_remote_ip, 0xac100164, "remote_ip")) + goto done; + if (!ASSERT_EQ(skel->bss->xfrm_replay_window, 42, "replay_window")) + goto done; + +done: + delete_xfrm_tunnel(); + if (skel) + test_tunnel_kern__destroy(skel); +} + #define RUN_TEST(name, ...) \ ({ \ if (test__start_subtest(#name)) { \ + config_device(); \ test_ ## name(__VA_ARGS__); \ + cleanup(); \ } \ }) static void *test_tunnel_run_tests(void *arg) { - cleanup(); - config_device(); - RUN_TEST(vxlan_tunnel); RUN_TEST(ip6vxlan_tunnel); RUN_TEST(ipip_tunnel, NONE); RUN_TEST(ipip_tunnel, FOU); RUN_TEST(ipip_tunnel, GUE); - - cleanup(); + RUN_TEST(xfrm_tunnel); return NULL; } diff --git a/tools/testing/selftests/bpf/prog_tests/time_tai.c b/tools/testing/selftests/bpf/prog_tests/time_tai.c index a31119823666..f45af1b0ef2c 100644 --- a/tools/testing/selftests/bpf/prog_tests/time_tai.c +++ b/tools/testing/selftests/bpf/prog_tests/time_tai.c @@ -56,7 +56,7 @@ void test_time_tai(void) ASSERT_NEQ(ts2, 0, "tai_ts2"); /* TAI is moving forward only */ - ASSERT_GT(ts2, ts1, "tai_forward"); + ASSERT_GE(ts2, ts1, "tai_forward"); /* Check for future */ ret = clock_gettime(CLOCK_TAI, &now_tai); diff --git a/tools/testing/selftests/bpf/prog_tests/token.c b/tools/testing/selftests/bpf/prog_tests/token.c new file mode 100644 index 000000000000..b5dce630e0e1 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/token.c @@ -0,0 +1,1031 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ +#define _GNU_SOURCE +#include <test_progs.h> +#include <bpf/btf.h> +#include "cap_helpers.h" +#include <fcntl.h> +#include <sched.h> +#include <signal.h> +#include <unistd.h> +#include <linux/filter.h> +#include <linux/unistd.h> +#include <linux/mount.h> +#include <sys/socket.h> +#include <sys/stat.h> +#include <sys/syscall.h> +#include <sys/un.h> +#include "priv_map.skel.h" +#include "priv_prog.skel.h" +#include "dummy_st_ops_success.skel.h" + +static inline int sys_mount(const char *dev_name, const char *dir_name, + const char *type, unsigned long flags, + const void *data) +{ + return syscall(__NR_mount, dev_name, dir_name, type, flags, data); +} + +static inline int sys_fsopen(const char *fsname, unsigned flags) +{ + return syscall(__NR_fsopen, fsname, flags); +} + +static inline int sys_fspick(int dfd, const char *path, unsigned flags) +{ + return syscall(__NR_fspick, dfd, path, flags); +} + +static inline int sys_fsconfig(int fs_fd, unsigned cmd, const char *key, const void *val, int aux) +{ + return syscall(__NR_fsconfig, fs_fd, cmd, key, val, aux); +} + +static inline int sys_fsmount(int fs_fd, unsigned flags, unsigned ms_flags) +{ + return syscall(__NR_fsmount, fs_fd, flags, ms_flags); +} + +static inline int sys_move_mount(int from_dfd, const char *from_path, + int to_dfd, const char *to_path, + unsigned flags) +{ + return syscall(__NR_move_mount, from_dfd, from_path, to_dfd, to_path, flags); +} + +static int drop_priv_caps(__u64 *old_caps) +{ + return cap_disable_effective((1ULL << CAP_BPF) | + (1ULL << CAP_PERFMON) | + (1ULL << CAP_NET_ADMIN) | + (1ULL << CAP_SYS_ADMIN), old_caps); +} + +static int restore_priv_caps(__u64 old_caps) +{ + return cap_enable_effective(old_caps, NULL); +} + +static int set_delegate_mask(int fs_fd, const char *key, __u64 mask, const char *mask_str) +{ + char buf[32]; + int err; + + if (!mask_str) { + if (mask == ~0ULL) { + mask_str = "any"; + } else { + snprintf(buf, sizeof(buf), "0x%llx", (unsigned long long)mask); + mask_str = buf; + } + } + + err = sys_fsconfig(fs_fd, FSCONFIG_SET_STRING, key, + mask_str, 0); + if (err < 0) + err = -errno; + return err; +} + +#define zclose(fd) do { if (fd >= 0) close(fd); fd = -1; } while (0) + +struct bpffs_opts { + __u64 cmds; + __u64 maps; + __u64 progs; + __u64 attachs; + const char *cmds_str; + const char *maps_str; + const char *progs_str; + const char *attachs_str; +}; + +static int create_bpffs_fd(void) +{ + int fs_fd; + + /* create VFS context */ + fs_fd = sys_fsopen("bpf", 0); + ASSERT_GE(fs_fd, 0, "fs_fd"); + + return fs_fd; +} + +static int materialize_bpffs_fd(int fs_fd, struct bpffs_opts *opts) +{ + int mnt_fd, err; + + /* set up token delegation mount options */ + err = set_delegate_mask(fs_fd, "delegate_cmds", opts->cmds, opts->cmds_str); + if (!ASSERT_OK(err, "fs_cfg_cmds")) + return err; + err = set_delegate_mask(fs_fd, "delegate_maps", opts->maps, opts->maps_str); + if (!ASSERT_OK(err, "fs_cfg_maps")) + return err; + err = set_delegate_mask(fs_fd, "delegate_progs", opts->progs, opts->progs_str); + if (!ASSERT_OK(err, "fs_cfg_progs")) + return err; + err = set_delegate_mask(fs_fd, "delegate_attachs", opts->attachs, opts->attachs_str); + if (!ASSERT_OK(err, "fs_cfg_attachs")) + return err; + + /* instantiate FS object */ + err = sys_fsconfig(fs_fd, FSCONFIG_CMD_CREATE, NULL, NULL, 0); + if (err < 0) + return -errno; + + /* create O_PATH fd for detached mount */ + mnt_fd = sys_fsmount(fs_fd, 0, 0); + if (err < 0) + return -errno; + + return mnt_fd; +} + +/* send FD over Unix domain (AF_UNIX) socket */ +static int sendfd(int sockfd, int fd) +{ + struct msghdr msg = {}; + struct cmsghdr *cmsg; + int fds[1] = { fd }, err; + char iobuf[1]; + struct iovec io = { + .iov_base = iobuf, + .iov_len = sizeof(iobuf), + }; + union { + char buf[CMSG_SPACE(sizeof(fds))]; + struct cmsghdr align; + } u; + + msg.msg_iov = &io; + msg.msg_iovlen = 1; + msg.msg_control = u.buf; + msg.msg_controllen = sizeof(u.buf); + cmsg = CMSG_FIRSTHDR(&msg); + cmsg->cmsg_level = SOL_SOCKET; + cmsg->cmsg_type = SCM_RIGHTS; + cmsg->cmsg_len = CMSG_LEN(sizeof(fds)); + memcpy(CMSG_DATA(cmsg), fds, sizeof(fds)); + + err = sendmsg(sockfd, &msg, 0); + if (err < 0) + err = -errno; + if (!ASSERT_EQ(err, 1, "sendmsg")) + return -EINVAL; + + return 0; +} + +/* receive FD over Unix domain (AF_UNIX) socket */ +static int recvfd(int sockfd, int *fd) +{ + struct msghdr msg = {}; + struct cmsghdr *cmsg; + int fds[1], err; + char iobuf[1]; + struct iovec io = { + .iov_base = iobuf, + .iov_len = sizeof(iobuf), + }; + union { + char buf[CMSG_SPACE(sizeof(fds))]; + struct cmsghdr align; + } u; + + msg.msg_iov = &io; + msg.msg_iovlen = 1; + msg.msg_control = u.buf; + msg.msg_controllen = sizeof(u.buf); + + err = recvmsg(sockfd, &msg, 0); + if (err < 0) + err = -errno; + if (!ASSERT_EQ(err, 1, "recvmsg")) + return -EINVAL; + + cmsg = CMSG_FIRSTHDR(&msg); + if (!ASSERT_OK_PTR(cmsg, "cmsg_null") || + !ASSERT_EQ(cmsg->cmsg_len, CMSG_LEN(sizeof(fds)), "cmsg_len") || + !ASSERT_EQ(cmsg->cmsg_level, SOL_SOCKET, "cmsg_level") || + !ASSERT_EQ(cmsg->cmsg_type, SCM_RIGHTS, "cmsg_type")) + return -EINVAL; + + memcpy(fds, CMSG_DATA(cmsg), sizeof(fds)); + *fd = fds[0]; + + return 0; +} + +static ssize_t write_nointr(int fd, const void *buf, size_t count) +{ + ssize_t ret; + + do { + ret = write(fd, buf, count); + } while (ret < 0 && errno == EINTR); + + return ret; +} + +static int write_file(const char *path, const void *buf, size_t count) +{ + int fd; + ssize_t ret; + + fd = open(path, O_WRONLY | O_CLOEXEC | O_NOCTTY | O_NOFOLLOW); + if (fd < 0) + return -1; + + ret = write_nointr(fd, buf, count); + close(fd); + if (ret < 0 || (size_t)ret != count) + return -1; + + return 0; +} + +static int create_and_enter_userns(void) +{ + uid_t uid; + gid_t gid; + char map[100]; + + uid = getuid(); + gid = getgid(); + + if (unshare(CLONE_NEWUSER)) + return -1; + + if (write_file("/proc/self/setgroups", "deny", sizeof("deny") - 1) && + errno != ENOENT) + return -1; + + snprintf(map, sizeof(map), "0 %d 1", uid); + if (write_file("/proc/self/uid_map", map, strlen(map))) + return -1; + + + snprintf(map, sizeof(map), "0 %d 1", gid); + if (write_file("/proc/self/gid_map", map, strlen(map))) + return -1; + + if (setgid(0)) + return -1; + + if (setuid(0)) + return -1; + + return 0; +} + +typedef int (*child_callback_fn)(int); + +static void child(int sock_fd, struct bpffs_opts *opts, child_callback_fn callback) +{ + LIBBPF_OPTS(bpf_map_create_opts, map_opts); + int mnt_fd = -1, fs_fd = -1, err = 0, bpffs_fd = -1; + + /* setup userns with root mappings */ + err = create_and_enter_userns(); + if (!ASSERT_OK(err, "create_and_enter_userns")) + goto cleanup; + + /* setup mountns to allow creating BPF FS (fsopen("bpf")) from unpriv process */ + err = unshare(CLONE_NEWNS); + if (!ASSERT_OK(err, "create_mountns")) + goto cleanup; + + err = sys_mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, 0); + if (!ASSERT_OK(err, "remount_root")) + goto cleanup; + + fs_fd = create_bpffs_fd(); + if (!ASSERT_GE(fs_fd, 0, "create_bpffs_fd")) { + err = -EINVAL; + goto cleanup; + } + + /* ensure unprivileged child cannot set delegation options */ + err = set_delegate_mask(fs_fd, "delegate_cmds", 0x1, NULL); + ASSERT_EQ(err, -EPERM, "delegate_cmd_eperm"); + err = set_delegate_mask(fs_fd, "delegate_maps", 0x1, NULL); + ASSERT_EQ(err, -EPERM, "delegate_maps_eperm"); + err = set_delegate_mask(fs_fd, "delegate_progs", 0x1, NULL); + ASSERT_EQ(err, -EPERM, "delegate_progs_eperm"); + err = set_delegate_mask(fs_fd, "delegate_attachs", 0x1, NULL); + ASSERT_EQ(err, -EPERM, "delegate_attachs_eperm"); + + /* pass BPF FS context object to parent */ + err = sendfd(sock_fd, fs_fd); + if (!ASSERT_OK(err, "send_fs_fd")) + goto cleanup; + zclose(fs_fd); + + /* avoid mucking around with mount namespaces and mounting at + * well-known path, just get detach-mounted BPF FS fd back from parent + */ + err = recvfd(sock_fd, &mnt_fd); + if (!ASSERT_OK(err, "recv_mnt_fd")) + goto cleanup; + + /* try to fspick() BPF FS and try to add some delegation options */ + fs_fd = sys_fspick(mnt_fd, "", FSPICK_EMPTY_PATH); + if (!ASSERT_GE(fs_fd, 0, "bpffs_fspick")) { + err = -EINVAL; + goto cleanup; + } + + /* ensure unprivileged child cannot reconfigure to set delegation options */ + err = set_delegate_mask(fs_fd, "delegate_cmds", 0, "any"); + if (!ASSERT_EQ(err, -EPERM, "delegate_cmd_eperm_reconfig")) { + err = -EINVAL; + goto cleanup; + } + err = set_delegate_mask(fs_fd, "delegate_maps", 0, "any"); + if (!ASSERT_EQ(err, -EPERM, "delegate_maps_eperm_reconfig")) { + err = -EINVAL; + goto cleanup; + } + err = set_delegate_mask(fs_fd, "delegate_progs", 0, "any"); + if (!ASSERT_EQ(err, -EPERM, "delegate_progs_eperm_reconfig")) { + err = -EINVAL; + goto cleanup; + } + err = set_delegate_mask(fs_fd, "delegate_attachs", 0, "any"); + if (!ASSERT_EQ(err, -EPERM, "delegate_attachs_eperm_reconfig")) { + err = -EINVAL; + goto cleanup; + } + zclose(fs_fd); + + bpffs_fd = openat(mnt_fd, ".", 0, O_RDWR); + if (!ASSERT_GE(bpffs_fd, 0, "bpffs_open")) { + err = -EINVAL; + goto cleanup; + } + + /* do custom test logic with customly set up BPF FS instance */ + err = callback(bpffs_fd); + if (!ASSERT_OK(err, "test_callback")) + goto cleanup; + + err = 0; +cleanup: + zclose(sock_fd); + zclose(mnt_fd); + zclose(fs_fd); + zclose(bpffs_fd); + + exit(-err); +} + +static int wait_for_pid(pid_t pid) +{ + int status, ret; + +again: + ret = waitpid(pid, &status, 0); + if (ret == -1) { + if (errno == EINTR) + goto again; + + return -1; + } + + if (!WIFEXITED(status)) + return -1; + + return WEXITSTATUS(status); +} + +static void parent(int child_pid, struct bpffs_opts *bpffs_opts, int sock_fd) +{ + int fs_fd = -1, mnt_fd = -1, err; + + err = recvfd(sock_fd, &fs_fd); + if (!ASSERT_OK(err, "recv_bpffs_fd")) + goto cleanup; + + mnt_fd = materialize_bpffs_fd(fs_fd, bpffs_opts); + if (!ASSERT_GE(mnt_fd, 0, "materialize_bpffs_fd")) { + err = -EINVAL; + goto cleanup; + } + zclose(fs_fd); + + /* pass BPF FS context object to parent */ + err = sendfd(sock_fd, mnt_fd); + if (!ASSERT_OK(err, "send_mnt_fd")) + goto cleanup; + zclose(mnt_fd); + + err = wait_for_pid(child_pid); + ASSERT_OK(err, "waitpid_child"); + +cleanup: + zclose(sock_fd); + zclose(fs_fd); + zclose(mnt_fd); + + if (child_pid > 0) + (void)kill(child_pid, SIGKILL); +} + +static void subtest_userns(struct bpffs_opts *bpffs_opts, child_callback_fn cb) +{ + int sock_fds[2] = { -1, -1 }; + int child_pid = 0, err; + + err = socketpair(AF_UNIX, SOCK_STREAM, 0, sock_fds); + if (!ASSERT_OK(err, "socketpair")) + goto cleanup; + + child_pid = fork(); + if (!ASSERT_GE(child_pid, 0, "fork")) + goto cleanup; + + if (child_pid == 0) { + zclose(sock_fds[0]); + return child(sock_fds[1], bpffs_opts, cb); + + } else { + zclose(sock_fds[1]); + return parent(child_pid, bpffs_opts, sock_fds[0]); + } + +cleanup: + zclose(sock_fds[0]); + zclose(sock_fds[1]); + if (child_pid > 0) + (void)kill(child_pid, SIGKILL); +} + +static int userns_map_create(int mnt_fd) +{ + LIBBPF_OPTS(bpf_map_create_opts, map_opts); + int err, token_fd = -1, map_fd = -1; + __u64 old_caps = 0; + + /* create BPF token from BPF FS mount */ + token_fd = bpf_token_create(mnt_fd, NULL); + if (!ASSERT_GT(token_fd, 0, "token_create")) { + err = -EINVAL; + goto cleanup; + } + + /* while inside non-init userns, we need both a BPF token *and* + * CAP_BPF inside current userns to create privileged map; let's test + * that neither BPF token alone nor namespaced CAP_BPF is sufficient + */ + err = drop_priv_caps(&old_caps); + if (!ASSERT_OK(err, "drop_caps")) + goto cleanup; + + /* no token, no CAP_BPF -> fail */ + map_opts.token_fd = 0; + map_fd = bpf_map_create(BPF_MAP_TYPE_STACK, "wo_token_wo_bpf", 0, 8, 1, &map_opts); + if (!ASSERT_LT(map_fd, 0, "stack_map_wo_token_wo_cap_bpf_should_fail")) { + err = -EINVAL; + goto cleanup; + } + + /* token without CAP_BPF -> fail */ + map_opts.token_fd = token_fd; + map_fd = bpf_map_create(BPF_MAP_TYPE_STACK, "w_token_wo_bpf", 0, 8, 1, &map_opts); + if (!ASSERT_LT(map_fd, 0, "stack_map_w_token_wo_cap_bpf_should_fail")) { + err = -EINVAL; + goto cleanup; + } + + /* get back effective local CAP_BPF (and CAP_SYS_ADMIN) */ + err = restore_priv_caps(old_caps); + if (!ASSERT_OK(err, "restore_caps")) + goto cleanup; + + /* CAP_BPF without token -> fail */ + map_opts.token_fd = 0; + map_fd = bpf_map_create(BPF_MAP_TYPE_STACK, "wo_token_w_bpf", 0, 8, 1, &map_opts); + if (!ASSERT_LT(map_fd, 0, "stack_map_wo_token_w_cap_bpf_should_fail")) { + err = -EINVAL; + goto cleanup; + } + + /* finally, namespaced CAP_BPF + token -> success */ + map_opts.token_fd = token_fd; + map_fd = bpf_map_create(BPF_MAP_TYPE_STACK, "w_token_w_bpf", 0, 8, 1, &map_opts); + if (!ASSERT_GT(map_fd, 0, "stack_map_w_token_w_cap_bpf")) { + err = -EINVAL; + goto cleanup; + } + +cleanup: + zclose(token_fd); + zclose(map_fd); + return err; +} + +static int userns_btf_load(int mnt_fd) +{ + LIBBPF_OPTS(bpf_btf_load_opts, btf_opts); + int err, token_fd = -1, btf_fd = -1; + const void *raw_btf_data; + struct btf *btf = NULL; + __u32 raw_btf_size; + __u64 old_caps = 0; + + /* create BPF token from BPF FS mount */ + token_fd = bpf_token_create(mnt_fd, NULL); + if (!ASSERT_GT(token_fd, 0, "token_create")) { + err = -EINVAL; + goto cleanup; + } + + /* while inside non-init userns, we need both a BPF token *and* + * CAP_BPF inside current userns to create privileged map; let's test + * that neither BPF token alone nor namespaced CAP_BPF is sufficient + */ + err = drop_priv_caps(&old_caps); + if (!ASSERT_OK(err, "drop_caps")) + goto cleanup; + + /* setup a trivial BTF data to load to the kernel */ + btf = btf__new_empty(); + if (!ASSERT_OK_PTR(btf, "empty_btf")) + goto cleanup; + + ASSERT_GT(btf__add_int(btf, "int", 4, 0), 0, "int_type"); + + raw_btf_data = btf__raw_data(btf, &raw_btf_size); + if (!ASSERT_OK_PTR(raw_btf_data, "raw_btf_data")) + goto cleanup; + + /* no token + no CAP_BPF -> failure */ + btf_opts.token_fd = 0; + btf_fd = bpf_btf_load(raw_btf_data, raw_btf_size, &btf_opts); + if (!ASSERT_LT(btf_fd, 0, "no_token_no_cap_should_fail")) + goto cleanup; + + /* token + no CAP_BPF -> failure */ + btf_opts.token_fd = token_fd; + btf_fd = bpf_btf_load(raw_btf_data, raw_btf_size, &btf_opts); + if (!ASSERT_LT(btf_fd, 0, "token_no_cap_should_fail")) + goto cleanup; + + /* get back effective local CAP_BPF (and CAP_SYS_ADMIN) */ + err = restore_priv_caps(old_caps); + if (!ASSERT_OK(err, "restore_caps")) + goto cleanup; + + /* token + CAP_BPF -> success */ + btf_opts.token_fd = token_fd; + btf_fd = bpf_btf_load(raw_btf_data, raw_btf_size, &btf_opts); + if (!ASSERT_GT(btf_fd, 0, "token_and_cap_success")) + goto cleanup; + + err = 0; +cleanup: + btf__free(btf); + zclose(btf_fd); + zclose(token_fd); + return err; +} + +static int userns_prog_load(int mnt_fd) +{ + LIBBPF_OPTS(bpf_prog_load_opts, prog_opts); + int err, token_fd = -1, prog_fd = -1; + struct bpf_insn insns[] = { + /* bpf_jiffies64() requires CAP_BPF */ + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_jiffies64), + /* bpf_get_current_task() requires CAP_PERFMON */ + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_current_task), + /* r0 = 0; exit; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + size_t insn_cnt = ARRAY_SIZE(insns); + __u64 old_caps = 0; + + /* create BPF token from BPF FS mount */ + token_fd = bpf_token_create(mnt_fd, NULL); + if (!ASSERT_GT(token_fd, 0, "token_create")) { + err = -EINVAL; + goto cleanup; + } + + /* validate we can successfully load BPF program with token; this + * being XDP program (CAP_NET_ADMIN) using bpf_jiffies64() (CAP_BPF) + * and bpf_get_current_task() (CAP_PERFMON) helpers validates we have + * BPF token wired properly in a bunch of places in the kernel + */ + prog_opts.token_fd = token_fd; + prog_opts.expected_attach_type = BPF_XDP; + prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, "token_prog", "GPL", + insns, insn_cnt, &prog_opts); + if (!ASSERT_GT(prog_fd, 0, "prog_fd")) { + err = -EPERM; + goto cleanup; + } + + /* no token + caps -> failure */ + prog_opts.token_fd = 0; + prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, "token_prog", "GPL", + insns, insn_cnt, &prog_opts); + if (!ASSERT_EQ(prog_fd, -EPERM, "prog_fd_eperm")) { + err = -EPERM; + goto cleanup; + } + + err = drop_priv_caps(&old_caps); + if (!ASSERT_OK(err, "drop_caps")) + goto cleanup; + + /* no caps + token -> failure */ + prog_opts.token_fd = token_fd; + prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, "token_prog", "GPL", + insns, insn_cnt, &prog_opts); + if (!ASSERT_EQ(prog_fd, -EPERM, "prog_fd_eperm")) { + err = -EPERM; + goto cleanup; + } + + /* no caps + no token -> definitely a failure */ + prog_opts.token_fd = 0; + prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, "token_prog", "GPL", + insns, insn_cnt, &prog_opts); + if (!ASSERT_EQ(prog_fd, -EPERM, "prog_fd_eperm")) { + err = -EPERM; + goto cleanup; + } + + err = 0; +cleanup: + zclose(prog_fd); + zclose(token_fd); + return err; +} + +static int userns_obj_priv_map(int mnt_fd) +{ + LIBBPF_OPTS(bpf_object_open_opts, opts); + char buf[256]; + struct priv_map *skel; + int err, token_fd; + + skel = priv_map__open_and_load(); + if (!ASSERT_ERR_PTR(skel, "obj_tokenless_load")) { + priv_map__destroy(skel); + return -EINVAL; + } + + /* use bpf_token_path to provide BPF FS path */ + snprintf(buf, sizeof(buf), "/proc/self/fd/%d", mnt_fd); + opts.bpf_token_path = buf; + skel = priv_map__open_opts(&opts); + if (!ASSERT_OK_PTR(skel, "obj_token_path_open")) + return -EINVAL; + + err = priv_map__load(skel); + priv_map__destroy(skel); + if (!ASSERT_OK(err, "obj_token_path_load")) + return -EINVAL; + + /* create token and pass it through bpf_token_fd */ + token_fd = bpf_token_create(mnt_fd, NULL); + if (!ASSERT_GT(token_fd, 0, "create_token")) + return -EINVAL; + + opts.bpf_token_path = NULL; + opts.bpf_token_fd = token_fd; + skel = priv_map__open_opts(&opts); + if (!ASSERT_OK_PTR(skel, "obj_token_fd_open")) + return -EINVAL; + + /* we can close our token FD, bpf_object owns dup()'ed FD now */ + close(token_fd); + + err = priv_map__load(skel); + priv_map__destroy(skel); + if (!ASSERT_OK(err, "obj_token_fd_load")) + return -EINVAL; + + return 0; +} + +static int userns_obj_priv_prog(int mnt_fd) +{ + LIBBPF_OPTS(bpf_object_open_opts, opts); + char buf[256]; + struct priv_prog *skel; + int err; + + skel = priv_prog__open_and_load(); + if (!ASSERT_ERR_PTR(skel, "obj_tokenless_load")) { + priv_prog__destroy(skel); + return -EINVAL; + } + + /* use bpf_token_path to provide BPF FS path */ + snprintf(buf, sizeof(buf), "/proc/self/fd/%d", mnt_fd); + opts.bpf_token_path = buf; + skel = priv_prog__open_opts(&opts); + if (!ASSERT_OK_PTR(skel, "obj_token_path_open")) + return -EINVAL; + + err = priv_prog__load(skel); + priv_prog__destroy(skel); + if (!ASSERT_OK(err, "obj_token_path_load")) + return -EINVAL; + + return 0; +} + +/* this test is called with BPF FS that doesn't delegate BPF_BTF_LOAD command, + * which should cause struct_ops application to fail, as BTF won't be uploaded + * into the kernel, even if STRUCT_OPS programs themselves are allowed + */ +static int validate_struct_ops_load(int mnt_fd, bool expect_success) +{ + LIBBPF_OPTS(bpf_object_open_opts, opts); + char buf[256]; + struct dummy_st_ops_success *skel; + int err; + + snprintf(buf, sizeof(buf), "/proc/self/fd/%d", mnt_fd); + opts.bpf_token_path = buf; + skel = dummy_st_ops_success__open_opts(&opts); + if (!ASSERT_OK_PTR(skel, "obj_token_path_open")) + return -EINVAL; + + err = dummy_st_ops_success__load(skel); + dummy_st_ops_success__destroy(skel); + if (expect_success) { + if (!ASSERT_OK(err, "obj_token_path_load")) + return -EINVAL; + } else /* expect failure */ { + if (!ASSERT_ERR(err, "obj_token_path_load")) + return -EINVAL; + } + + return 0; +} + +static int userns_obj_priv_btf_fail(int mnt_fd) +{ + return validate_struct_ops_load(mnt_fd, false /* should fail */); +} + +static int userns_obj_priv_btf_success(int mnt_fd) +{ + return validate_struct_ops_load(mnt_fd, true /* should succeed */); +} + +#define TOKEN_ENVVAR "LIBBPF_BPF_TOKEN_PATH" +#define TOKEN_BPFFS_CUSTOM "/bpf-token-fs" + +static int userns_obj_priv_implicit_token(int mnt_fd) +{ + LIBBPF_OPTS(bpf_object_open_opts, opts); + struct dummy_st_ops_success *skel; + int err; + + /* before we mount BPF FS with token delegation, struct_ops skeleton + * should fail to load + */ + skel = dummy_st_ops_success__open_and_load(); + if (!ASSERT_ERR_PTR(skel, "obj_tokenless_load")) { + dummy_st_ops_success__destroy(skel); + return -EINVAL; + } + + /* mount custom BPF FS over /sys/fs/bpf so that libbpf can create BPF + * token automatically and implicitly + */ + err = sys_move_mount(mnt_fd, "", AT_FDCWD, "/sys/fs/bpf", MOVE_MOUNT_F_EMPTY_PATH); + if (!ASSERT_OK(err, "move_mount_bpffs")) + return -EINVAL; + + /* disable implicit BPF token creation by setting + * LIBBPF_BPF_TOKEN_PATH envvar to empty value, load should fail + */ + err = setenv(TOKEN_ENVVAR, "", 1 /*overwrite*/); + if (!ASSERT_OK(err, "setenv_token_path")) + return -EINVAL; + skel = dummy_st_ops_success__open_and_load(); + if (!ASSERT_ERR_PTR(skel, "obj_token_envvar_disabled_load")) { + unsetenv(TOKEN_ENVVAR); + dummy_st_ops_success__destroy(skel); + return -EINVAL; + } + unsetenv(TOKEN_ENVVAR); + + /* now the same struct_ops skeleton should succeed thanks to libppf + * creating BPF token from /sys/fs/bpf mount point + */ + skel = dummy_st_ops_success__open_and_load(); + if (!ASSERT_OK_PTR(skel, "obj_implicit_token_load")) + return -EINVAL; + + dummy_st_ops_success__destroy(skel); + + /* now disable implicit token through empty bpf_token_path, should fail */ + opts.bpf_token_path = ""; + skel = dummy_st_ops_success__open_opts(&opts); + if (!ASSERT_OK_PTR(skel, "obj_empty_token_path_open")) + return -EINVAL; + + err = dummy_st_ops_success__load(skel); + dummy_st_ops_success__destroy(skel); + if (!ASSERT_ERR(err, "obj_empty_token_path_load")) + return -EINVAL; + + /* now disable implicit token through negative bpf_token_fd, should fail */ + opts.bpf_token_path = NULL; + opts.bpf_token_fd = -1; + skel = dummy_st_ops_success__open_opts(&opts); + if (!ASSERT_OK_PTR(skel, "obj_neg_token_fd_open")) + return -EINVAL; + + err = dummy_st_ops_success__load(skel); + dummy_st_ops_success__destroy(skel); + if (!ASSERT_ERR(err, "obj_neg_token_fd_load")) + return -EINVAL; + + return 0; +} + +static int userns_obj_priv_implicit_token_envvar(int mnt_fd) +{ + LIBBPF_OPTS(bpf_object_open_opts, opts); + struct dummy_st_ops_success *skel; + int err; + + /* before we mount BPF FS with token delegation, struct_ops skeleton + * should fail to load + */ + skel = dummy_st_ops_success__open_and_load(); + if (!ASSERT_ERR_PTR(skel, "obj_tokenless_load")) { + dummy_st_ops_success__destroy(skel); + return -EINVAL; + } + + /* mount custom BPF FS over custom location, so libbpf can't create + * BPF token implicitly, unless pointed to it through + * LIBBPF_BPF_TOKEN_PATH envvar + */ + rmdir(TOKEN_BPFFS_CUSTOM); + if (!ASSERT_OK(mkdir(TOKEN_BPFFS_CUSTOM, 0777), "mkdir_bpffs_custom")) + goto err_out; + err = sys_move_mount(mnt_fd, "", AT_FDCWD, TOKEN_BPFFS_CUSTOM, MOVE_MOUNT_F_EMPTY_PATH); + if (!ASSERT_OK(err, "move_mount_bpffs")) + goto err_out; + + /* even though we have BPF FS with delegation, it's not at default + * /sys/fs/bpf location, so we still fail to load until envvar is set up + */ + skel = dummy_st_ops_success__open_and_load(); + if (!ASSERT_ERR_PTR(skel, "obj_tokenless_load2")) { + dummy_st_ops_success__destroy(skel); + goto err_out; + } + + err = setenv(TOKEN_ENVVAR, TOKEN_BPFFS_CUSTOM, 1 /*overwrite*/); + if (!ASSERT_OK(err, "setenv_token_path")) + goto err_out; + + /* now the same struct_ops skeleton should succeed thanks to libppf + * creating BPF token from custom mount point + */ + skel = dummy_st_ops_success__open_and_load(); + if (!ASSERT_OK_PTR(skel, "obj_implicit_token_load")) + goto err_out; + + dummy_st_ops_success__destroy(skel); + + /* now disable implicit token through empty bpf_token_path, envvar + * will be ignored, should fail + */ + opts.bpf_token_path = ""; + skel = dummy_st_ops_success__open_opts(&opts); + if (!ASSERT_OK_PTR(skel, "obj_empty_token_path_open")) + goto err_out; + + err = dummy_st_ops_success__load(skel); + dummy_st_ops_success__destroy(skel); + if (!ASSERT_ERR(err, "obj_empty_token_path_load")) + goto err_out; + + /* now disable implicit token through negative bpf_token_fd, envvar + * will be ignored, should fail + */ + opts.bpf_token_path = NULL; + opts.bpf_token_fd = -1; + skel = dummy_st_ops_success__open_opts(&opts); + if (!ASSERT_OK_PTR(skel, "obj_neg_token_fd_open")) + goto err_out; + + err = dummy_st_ops_success__load(skel); + dummy_st_ops_success__destroy(skel); + if (!ASSERT_ERR(err, "obj_neg_token_fd_load")) + goto err_out; + + rmdir(TOKEN_BPFFS_CUSTOM); + unsetenv(TOKEN_ENVVAR); + return 0; +err_out: + rmdir(TOKEN_BPFFS_CUSTOM); + unsetenv(TOKEN_ENVVAR); + return -EINVAL; +} + +#define bit(n) (1ULL << (n)) + +void test_token(void) +{ + if (test__start_subtest("map_token")) { + struct bpffs_opts opts = { + .cmds_str = "map_create", + .maps_str = "stack", + }; + + subtest_userns(&opts, userns_map_create); + } + if (test__start_subtest("btf_token")) { + struct bpffs_opts opts = { + .cmds = 1ULL << BPF_BTF_LOAD, + }; + + subtest_userns(&opts, userns_btf_load); + } + if (test__start_subtest("prog_token")) { + struct bpffs_opts opts = { + .cmds_str = "PROG_LOAD", + .progs_str = "XDP", + .attachs_str = "xdp", + }; + + subtest_userns(&opts, userns_prog_load); + } + if (test__start_subtest("obj_priv_map")) { + struct bpffs_opts opts = { + .cmds = bit(BPF_MAP_CREATE), + .maps = bit(BPF_MAP_TYPE_QUEUE), + }; + + subtest_userns(&opts, userns_obj_priv_map); + } + if (test__start_subtest("obj_priv_prog")) { + struct bpffs_opts opts = { + .cmds = bit(BPF_PROG_LOAD), + .progs = bit(BPF_PROG_TYPE_KPROBE), + .attachs = ~0ULL, + }; + + subtest_userns(&opts, userns_obj_priv_prog); + } + if (test__start_subtest("obj_priv_btf_fail")) { + struct bpffs_opts opts = { + /* disallow BTF loading */ + .cmds = bit(BPF_MAP_CREATE) | bit(BPF_PROG_LOAD), + .maps = bit(BPF_MAP_TYPE_STRUCT_OPS), + .progs = bit(BPF_PROG_TYPE_STRUCT_OPS), + .attachs = ~0ULL, + }; + + subtest_userns(&opts, userns_obj_priv_btf_fail); + } + if (test__start_subtest("obj_priv_btf_success")) { + struct bpffs_opts opts = { + /* allow BTF loading */ + .cmds = bit(BPF_BTF_LOAD) | bit(BPF_MAP_CREATE) | bit(BPF_PROG_LOAD), + .maps = bit(BPF_MAP_TYPE_STRUCT_OPS), + .progs = bit(BPF_PROG_TYPE_STRUCT_OPS), + .attachs = ~0ULL, + }; + + subtest_userns(&opts, userns_obj_priv_btf_success); + } + if (test__start_subtest("obj_priv_implicit_token")) { + struct bpffs_opts opts = { + /* allow BTF loading */ + .cmds = bit(BPF_BTF_LOAD) | bit(BPF_MAP_CREATE) | bit(BPF_PROG_LOAD), + .maps = bit(BPF_MAP_TYPE_STRUCT_OPS), + .progs = bit(BPF_PROG_TYPE_STRUCT_OPS), + .attachs = ~0ULL, + }; + + subtest_userns(&opts, userns_obj_priv_implicit_token); + } + if (test__start_subtest("obj_priv_implicit_token_envvar")) { + struct bpffs_opts opts = { + /* allow BTF loading */ + .cmds = bit(BPF_BTF_LOAD) | bit(BPF_MAP_CREATE) | bit(BPF_PROG_LOAD), + .maps = bit(BPF_MAP_TYPE_STRUCT_OPS), + .progs = bit(BPF_PROG_TYPE_STRUCT_OPS), + .attachs = ~0ULL, + }; + + subtest_userns(&opts, userns_obj_priv_implicit_token_envvar); + } +} diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c index ece260cf2c0b..8269cdee33ae 100644 --- a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c +++ b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c @@ -234,6 +234,177 @@ static void test_attach_api_syms(void) test_attach_api("/proc/self/exe", NULL, &opts); } +static void test_attach_api_fails(void) +{ + LIBBPF_OPTS(bpf_link_create_opts, opts); + const char *path = "/proc/self/exe"; + struct uprobe_multi *skel = NULL; + int prog_fd, link_fd = -1; + unsigned long offset = 0; + + skel = uprobe_multi__open_and_load(); + if (!ASSERT_OK_PTR(skel, "uprobe_multi__open_and_load")) + goto cleanup; + + prog_fd = bpf_program__fd(skel->progs.uprobe_extra); + + /* abnormal cnt */ + opts.uprobe_multi.path = path; + opts.uprobe_multi.offsets = &offset; + opts.uprobe_multi.cnt = INT_MAX; + link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts); + if (!ASSERT_ERR(link_fd, "link_fd")) + goto cleanup; + if (!ASSERT_EQ(link_fd, -E2BIG, "big cnt")) + goto cleanup; + + /* cnt is 0 */ + LIBBPF_OPTS_RESET(opts, + .uprobe_multi.path = path, + .uprobe_multi.offsets = (unsigned long *) &offset, + ); + + link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts); + if (!ASSERT_ERR(link_fd, "link_fd")) + goto cleanup; + if (!ASSERT_EQ(link_fd, -EINVAL, "cnt_is_zero")) + goto cleanup; + + /* negative offset */ + offset = -1; + opts.uprobe_multi.path = path; + opts.uprobe_multi.offsets = (unsigned long *) &offset; + opts.uprobe_multi.cnt = 1; + + link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts); + if (!ASSERT_ERR(link_fd, "link_fd")) + goto cleanup; + if (!ASSERT_EQ(link_fd, -EINVAL, "offset_is_negative")) + goto cleanup; + + /* offsets is NULL */ + LIBBPF_OPTS_RESET(opts, + .uprobe_multi.path = path, + .uprobe_multi.cnt = 1, + ); + + link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts); + if (!ASSERT_ERR(link_fd, "link_fd")) + goto cleanup; + if (!ASSERT_EQ(link_fd, -EINVAL, "offsets_is_null")) + goto cleanup; + + /* wrong offsets pointer */ + LIBBPF_OPTS_RESET(opts, + .uprobe_multi.path = path, + .uprobe_multi.offsets = (unsigned long *) 1, + .uprobe_multi.cnt = 1, + ); + + link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts); + if (!ASSERT_ERR(link_fd, "link_fd")) + goto cleanup; + if (!ASSERT_EQ(link_fd, -EFAULT, "offsets_is_wrong")) + goto cleanup; + + /* path is NULL */ + offset = 1; + LIBBPF_OPTS_RESET(opts, + .uprobe_multi.offsets = (unsigned long *) &offset, + .uprobe_multi.cnt = 1, + ); + + link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts); + if (!ASSERT_ERR(link_fd, "link_fd")) + goto cleanup; + if (!ASSERT_EQ(link_fd, -EINVAL, "path_is_null")) + goto cleanup; + + /* wrong path pointer */ + LIBBPF_OPTS_RESET(opts, + .uprobe_multi.path = (const char *) 1, + .uprobe_multi.offsets = (unsigned long *) &offset, + .uprobe_multi.cnt = 1, + ); + + link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts); + if (!ASSERT_ERR(link_fd, "link_fd")) + goto cleanup; + if (!ASSERT_EQ(link_fd, -EFAULT, "path_is_wrong")) + goto cleanup; + + /* wrong path type */ + LIBBPF_OPTS_RESET(opts, + .uprobe_multi.path = "/", + .uprobe_multi.offsets = (unsigned long *) &offset, + .uprobe_multi.cnt = 1, + ); + + link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts); + if (!ASSERT_ERR(link_fd, "link_fd")) + goto cleanup; + if (!ASSERT_EQ(link_fd, -EBADF, "path_is_wrong_type")) + goto cleanup; + + /* wrong cookies pointer */ + LIBBPF_OPTS_RESET(opts, + .uprobe_multi.path = path, + .uprobe_multi.offsets = (unsigned long *) &offset, + .uprobe_multi.cookies = (__u64 *) 1ULL, + .uprobe_multi.cnt = 1, + ); + + link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts); + if (!ASSERT_ERR(link_fd, "link_fd")) + goto cleanup; + if (!ASSERT_EQ(link_fd, -EFAULT, "cookies_is_wrong")) + goto cleanup; + + /* wrong ref_ctr_offsets pointer */ + LIBBPF_OPTS_RESET(opts, + .uprobe_multi.path = path, + .uprobe_multi.offsets = (unsigned long *) &offset, + .uprobe_multi.cookies = (__u64 *) &offset, + .uprobe_multi.ref_ctr_offsets = (unsigned long *) 1, + .uprobe_multi.cnt = 1, + ); + + link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts); + if (!ASSERT_ERR(link_fd, "link_fd")) + goto cleanup; + if (!ASSERT_EQ(link_fd, -EFAULT, "ref_ctr_offsets_is_wrong")) + goto cleanup; + + /* wrong flags */ + LIBBPF_OPTS_RESET(opts, + .uprobe_multi.flags = 1 << 31, + ); + + link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts); + if (!ASSERT_ERR(link_fd, "link_fd")) + goto cleanup; + if (!ASSERT_EQ(link_fd, -EINVAL, "wrong_flags")) + goto cleanup; + + /* wrong pid */ + LIBBPF_OPTS_RESET(opts, + .uprobe_multi.path = path, + .uprobe_multi.offsets = (unsigned long *) &offset, + .uprobe_multi.cnt = 1, + .uprobe_multi.pid = -2, + ); + + link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts); + if (!ASSERT_ERR(link_fd, "link_fd")) + goto cleanup; + ASSERT_EQ(link_fd, -ESRCH, "pid_is_wrong"); + +cleanup: + if (link_fd >= 0) + close(link_fd); + uprobe_multi__destroy(skel); +} + static void __test_link_api(struct child *child) { int prog_fd, link1_fd = -1, link2_fd = -1, link3_fd = -1, link4_fd = -1; @@ -311,7 +482,7 @@ cleanup: free(offsets); } -void test_link_api(void) +static void test_link_api(void) { struct child *child; @@ -412,4 +583,6 @@ void test_uprobe_multi_test(void) test_bench_attach_uprobe(); if (test__start_subtest("bench_usdt")) test_bench_attach_usdt(); + if (test__start_subtest("attach_api_fails")) + test_attach_api_fails(); } diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c index 8d746642cbd7..ac49ec25211d 100644 --- a/tools/testing/selftests/bpf/prog_tests/verifier.c +++ b/tools/testing/selftests/bpf/prog_tests/verifier.c @@ -6,6 +6,7 @@ #include "verifier_and.skel.h" #include "verifier_array_access.skel.h" #include "verifier_basic_stack.skel.h" +#include "verifier_bitfield_write.skel.h" #include "verifier_bounds.skel.h" #include "verifier_bounds_deduction.skel.h" #include "verifier_bounds_deduction_non_const.skel.h" @@ -116,6 +117,7 @@ static void run_tests_aux(const char *skel_name, void test_verifier_and(void) { RUN(verifier_and); } void test_verifier_basic_stack(void) { RUN(verifier_basic_stack); } +void test_verifier_bitfield_write(void) { RUN(verifier_bitfield_write); } void test_verifier_bounds(void) { RUN(verifier_bounds); } void test_verifier_bounds_deduction(void) { RUN(verifier_bounds_deduction); } void test_verifier_bounds_deduction_non_const(void) { RUN(verifier_bounds_deduction_non_const); } diff --git a/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c b/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c index dd7f2bc70048..ab0f02faa80c 100644 --- a/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c +++ b/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c @@ -16,9 +16,12 @@ #include <sys/wait.h> #include <sys/mman.h> #include <linux/keyctl.h> +#include <sys/xattr.h> +#include <linux/fsverity.h> #include <test_progs.h> #include "test_verify_pkcs7_sig.skel.h" +#include "test_sig_in_xattr.skel.h" #define MAX_DATA_SIZE (1024 * 1024) #define MAX_SIG_SIZE 1024 @@ -26,6 +29,10 @@ #define VERIFY_USE_SECONDARY_KEYRING (1UL) #define VERIFY_USE_PLATFORM_KEYRING (2UL) +#ifndef SHA256_DIGEST_SIZE +#define SHA256_DIGEST_SIZE 32 +#endif + /* In stripped ARM and x86-64 modules, ~ is surprisingly rare. */ #define MODULE_SIG_STRING "~Module signature appended~\n" @@ -254,7 +261,7 @@ out: return ret; } -void test_verify_pkcs7_sig(void) +static void test_verify_pkcs7_sig_from_map(void) { libbpf_print_fn_t old_print_cb; char tmp_dir_template[] = "/tmp/verify_sigXXXXXX"; @@ -400,3 +407,159 @@ close_prog: skel->bss->monitored_pid = 0; test_verify_pkcs7_sig__destroy(skel); } + +static int get_signature_size(const char *sig_path) +{ + struct stat st; + + if (stat(sig_path, &st) == -1) + return -1; + + return st.st_size; +} + +static int add_signature_to_xattr(const char *data_path, const char *sig_path) +{ + char sig[MAX_SIG_SIZE] = {0}; + int fd, size, ret; + + if (sig_path) { + fd = open(sig_path, O_RDONLY); + if (fd < 0) + return -1; + + size = read(fd, sig, MAX_SIG_SIZE); + close(fd); + if (size <= 0) + return -1; + } else { + /* no sig_path, just write 32 bytes of zeros */ + size = 32; + } + ret = setxattr(data_path, "user.sig", sig, size, 0); + if (!ASSERT_OK(ret, "setxattr")) + return -1; + + return 0; +} + +static int test_open_file(struct test_sig_in_xattr *skel, char *data_path, + pid_t pid, bool should_success, char *name) +{ + int ret; + + skel->bss->monitored_pid = pid; + ret = open(data_path, O_RDONLY); + close(ret); + skel->bss->monitored_pid = 0; + + if (should_success) { + if (!ASSERT_GE(ret, 0, name)) + return -1; + } else { + if (!ASSERT_LT(ret, 0, name)) + return -1; + } + return 0; +} + +static void test_pkcs7_sig_fsverity(void) +{ + char data_path[PATH_MAX]; + char sig_path[PATH_MAX]; + char tmp_dir_template[] = "/tmp/verify_sigXXXXXX"; + char *tmp_dir; + struct test_sig_in_xattr *skel = NULL; + pid_t pid; + int ret; + + tmp_dir = mkdtemp(tmp_dir_template); + if (!ASSERT_OK_PTR(tmp_dir, "mkdtemp")) + return; + + snprintf(data_path, PATH_MAX, "%s/data-file", tmp_dir); + snprintf(sig_path, PATH_MAX, "%s/sig-file", tmp_dir); + + ret = _run_setup_process(tmp_dir, "setup"); + if (!ASSERT_OK(ret, "_run_setup_process")) + goto out; + + ret = _run_setup_process(tmp_dir, "fsverity-create-sign"); + + if (ret) { + printf("%s: SKIP: fsverity [sign|enable] doesn't work.\n" + "To run this test, try enable CONFIG_FS_VERITY and enable FSVerity for the filesystem.\n", + __func__); + test__skip(); + goto out; + } + + skel = test_sig_in_xattr__open(); + if (!ASSERT_OK_PTR(skel, "test_sig_in_xattr__open")) + goto out; + ret = get_signature_size(sig_path); + if (!ASSERT_GT(ret, 0, "get_signature_size")) + goto out; + skel->bss->sig_size = ret; + skel->bss->user_keyring_serial = syscall(__NR_request_key, "keyring", + "ebpf_testing_keyring", NULL, + KEY_SPEC_SESSION_KEYRING); + memcpy(skel->bss->digest, "FSVerity", 8); + + ret = test_sig_in_xattr__load(skel); + if (!ASSERT_OK(ret, "test_sig_in_xattr__load")) + goto out; + + ret = test_sig_in_xattr__attach(skel); + if (!ASSERT_OK(ret, "test_sig_in_xattr__attach")) + goto out; + + pid = getpid(); + + /* Case 1: fsverity is not enabled, open should succeed */ + if (test_open_file(skel, data_path, pid, true, "open_1")) + goto out; + + /* Case 2: fsverity is enabled, xattr is missing, open should + * fail + */ + ret = _run_setup_process(tmp_dir, "fsverity-enable"); + if (!ASSERT_OK(ret, "fsverity-enable")) + goto out; + if (test_open_file(skel, data_path, pid, false, "open_2")) + goto out; + + /* Case 3: fsverity is enabled, xattr has valid signature, open + * should succeed + */ + ret = add_signature_to_xattr(data_path, sig_path); + if (!ASSERT_OK(ret, "add_signature_to_xattr_1")) + goto out; + + if (test_open_file(skel, data_path, pid, true, "open_3")) + goto out; + + /* Case 4: fsverity is enabled, xattr has invalid signature, open + * should fail + */ + ret = add_signature_to_xattr(data_path, NULL); + if (!ASSERT_OK(ret, "add_signature_to_xattr_2")) + goto out; + test_open_file(skel, data_path, pid, false, "open_4"); + +out: + _run_setup_process(tmp_dir, "cleanup"); + if (!skel) + return; + + skel->bss->monitored_pid = 0; + test_sig_in_xattr__destroy(skel); +} + +void test_verify_pkcs7_sig(void) +{ + if (test__start_subtest("pkcs7_sig_from_map")) + test_verify_pkcs7_sig_from_map(); + if (test__start_subtest("pkcs7_sig_fsverity")) + test_pkcs7_sig_fsverity(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c index ab4952b9fb1d..e6a783c7f5db 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c @@ -77,8 +77,8 @@ void test_xdp_context_test_run(void) test_xdp_context_error(prog_fd, opts, 4, sizeof(__u32), sizeof(data), 0, 0, 0); - /* Meta data must be 32 bytes or smaller */ - test_xdp_context_error(prog_fd, opts, 0, 36, sizeof(data), 0, 0, 0); + /* Meta data must be 255 bytes or smaller */ + test_xdp_context_error(prog_fd, opts, 0, 256, sizeof(data), 0, 0, 0); /* Total size of data must match data_end - data_meta */ test_xdp_context_error(prog_fd, opts, 0, sizeof(__u32), diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c index 33cdf88efa6b..05edcf32f528 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c @@ -20,7 +20,7 @@ #define UDP_PAYLOAD_BYTES 4 -#define AF_XDP_SOURCE_PORT 1234 +#define UDP_SOURCE_PORT 1234 #define AF_XDP_CONSUMER_PORT 8080 #define UMEM_NUM 16 @@ -33,6 +33,18 @@ #define RX_ADDR "10.0.0.2" #define PREFIX_LEN "8" #define FAMILY AF_INET +#define TX_NETNS_NAME "xdp_metadata_tx" +#define RX_NETNS_NAME "xdp_metadata_rx" +#define TX_MAC "00:00:00:00:00:01" +#define RX_MAC "00:00:00:00:00:02" + +#define VLAN_ID 59 +#define VLAN_PROTO "802.1Q" +#define VLAN_PID htons(ETH_P_8021Q) +#define TX_NAME_VLAN TX_NAME "." TO_STR(VLAN_ID) + +#define XDP_RSS_TYPE_L4 BIT(3) +#define VLAN_VID_MASK 0xfff struct xsk { void *umem_area; @@ -181,7 +193,7 @@ static int generate_packet(struct xsk *xsk, __u16 dst_port) ASSERT_EQ(inet_pton(FAMILY, RX_ADDR, &iph->daddr), 1, "inet_pton(RX_ADDR)"); ip_csum(iph); - udph->source = htons(AF_XDP_SOURCE_PORT); + udph->source = htons(UDP_SOURCE_PORT); udph->dest = htons(dst_port); udph->len = htons(sizeof(*udph) + UDP_PAYLOAD_BYTES); udph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, @@ -204,6 +216,30 @@ static int generate_packet(struct xsk *xsk, __u16 dst_port) return 0; } +static int generate_packet_inet(void) +{ + char udp_payload[UDP_PAYLOAD_BYTES]; + struct sockaddr_in rx_addr; + int sock_fd, err = 0; + + /* Build a packet */ + memset(udp_payload, 0xAA, UDP_PAYLOAD_BYTES); + rx_addr.sin_addr.s_addr = inet_addr(RX_ADDR); + rx_addr.sin_family = AF_INET; + rx_addr.sin_port = htons(AF_XDP_CONSUMER_PORT); + + sock_fd = socket(AF_INET, SOCK_DGRAM, IPPROTO_UDP); + if (!ASSERT_GE(sock_fd, 0, "socket(AF_INET, SOCK_DGRAM, IPPROTO_UDP)")) + return sock_fd; + + err = sendto(sock_fd, udp_payload, UDP_PAYLOAD_BYTES, MSG_DONTWAIT, + (void *)&rx_addr, sizeof(rx_addr)); + ASSERT_GE(err, 0, "sendto"); + + close(sock_fd); + return err; +} + static void complete_tx(struct xsk *xsk) { struct xsk_tx_metadata *meta; @@ -236,7 +272,7 @@ static void refill_rx(struct xsk *xsk, __u64 addr) } } -static int verify_xsk_metadata(struct xsk *xsk) +static int verify_xsk_metadata(struct xsk *xsk, bool sent_from_af_xdp) { const struct xdp_desc *rx_desc; struct pollfd fds = {}; @@ -290,17 +326,42 @@ static int verify_xsk_metadata(struct xsk *xsk) if (!ASSERT_NEQ(meta->rx_hash, 0, "rx_hash")) return -1; + if (!sent_from_af_xdp) { + if (!ASSERT_NEQ(meta->rx_hash_type & XDP_RSS_TYPE_L4, 0, "rx_hash_type")) + return -1; + + if (!ASSERT_EQ(meta->rx_vlan_tci & VLAN_VID_MASK, VLAN_ID, "rx_vlan_tci")) + return -1; + + if (!ASSERT_EQ(meta->rx_vlan_proto, VLAN_PID, "rx_vlan_proto")) + return -1; + goto done; + } + ASSERT_EQ(meta->rx_hash_type, 0, "rx_hash_type"); /* checksum offload */ ASSERT_EQ(udph->check, htons(0x721c), "csum"); +done: xsk_ring_cons__release(&xsk->rx, 1); refill_rx(xsk, comp_addr); return 0; } +static void switch_ns_to_rx(struct nstoken **tok) +{ + close_netns(*tok); + *tok = open_netns(RX_NETNS_NAME); +} + +static void switch_ns_to_tx(struct nstoken **tok) +{ + close_netns(*tok); + *tok = open_netns(TX_NETNS_NAME); +} + void test_xdp_metadata(void) { struct xdp_metadata2 *bpf_obj2 = NULL; @@ -318,27 +379,35 @@ void test_xdp_metadata(void) int sock_fd; int ret; - /* Setup new networking namespace, with a veth pair. */ + /* Setup new networking namespaces, with a veth pair. */ + SYS(out, "ip netns add " TX_NETNS_NAME); + SYS(out, "ip netns add " RX_NETNS_NAME); - SYS(out, "ip netns add xdp_metadata"); - tok = open_netns("xdp_metadata"); + tok = open_netns(TX_NETNS_NAME); SYS(out, "ip link add numtxqueues 1 numrxqueues 1 " TX_NAME " type veth peer " RX_NAME " numtxqueues 1 numrxqueues 1"); - SYS(out, "ip link set dev " TX_NAME " address 00:00:00:00:00:01"); - SYS(out, "ip link set dev " RX_NAME " address 00:00:00:00:00:02"); + SYS(out, "ip link set " RX_NAME " netns " RX_NETNS_NAME); + + SYS(out, "ip link set dev " TX_NAME " address " TX_MAC); SYS(out, "ip link set dev " TX_NAME " up"); + + SYS(out, "ip link add link " TX_NAME " " TX_NAME_VLAN + " type vlan proto " VLAN_PROTO " id " TO_STR(VLAN_ID)); + SYS(out, "ip link set dev " TX_NAME_VLAN " up"); + SYS(out, "ip addr add " TX_ADDR "/" PREFIX_LEN " dev " TX_NAME_VLAN); + + /* Avoid ARP calls */ + SYS(out, "ip -4 neigh add " RX_ADDR " lladdr " RX_MAC " dev " TX_NAME_VLAN); + + switch_ns_to_rx(&tok); + + SYS(out, "ip link set dev " RX_NAME " address " RX_MAC); SYS(out, "ip link set dev " RX_NAME " up"); - SYS(out, "ip addr add " TX_ADDR "/" PREFIX_LEN " dev " TX_NAME); SYS(out, "ip addr add " RX_ADDR "/" PREFIX_LEN " dev " RX_NAME); rx_ifindex = if_nametoindex(RX_NAME); - tx_ifindex = if_nametoindex(TX_NAME); - - /* Setup separate AF_XDP for TX and RX interfaces. */ - ret = open_xsk(tx_ifindex, &tx_xsk); - if (!ASSERT_OK(ret, "open_xsk(TX_NAME)")) - goto out; + /* Setup separate AF_XDP for RX interface. */ ret = open_xsk(rx_ifindex, &rx_xsk); if (!ASSERT_OK(ret, "open_xsk(RX_NAME)")) @@ -379,18 +448,38 @@ void test_xdp_metadata(void) if (!ASSERT_GE(ret, 0, "bpf_map_update_elem")) goto out; - /* Send packet destined to RX AF_XDP socket. */ + switch_ns_to_tx(&tok); + + /* Setup separate AF_XDP for TX interface nad send packet to the RX socket. */ + tx_ifindex = if_nametoindex(TX_NAME); + ret = open_xsk(tx_ifindex, &tx_xsk); + if (!ASSERT_OK(ret, "open_xsk(TX_NAME)")) + goto out; + if (!ASSERT_GE(generate_packet(&tx_xsk, AF_XDP_CONSUMER_PORT), 0, "generate AF_XDP_CONSUMER_PORT")) goto out; - /* Verify AF_XDP RX packet has proper metadata. */ - if (!ASSERT_GE(verify_xsk_metadata(&rx_xsk), 0, + switch_ns_to_rx(&tok); + + /* Verify packet sent from AF_XDP has proper metadata. */ + if (!ASSERT_GE(verify_xsk_metadata(&rx_xsk, true), 0, "verify_xsk_metadata")) goto out; + switch_ns_to_tx(&tok); complete_tx(&tx_xsk); + /* Now check metadata of packet, generated with network stack */ + if (!ASSERT_GE(generate_packet_inet(), 0, "generate UDP packet")) + goto out; + + switch_ns_to_rx(&tok); + + if (!ASSERT_GE(verify_xsk_metadata(&rx_xsk, false), 0, + "verify_xsk_metadata")) + goto out; + /* Make sure freplace correctly picks up original bound device * and doesn't crash. */ @@ -408,11 +497,15 @@ void test_xdp_metadata(void) if (!ASSERT_OK(xdp_metadata2__attach(bpf_obj2), "attach freplace")) goto out; + switch_ns_to_tx(&tok); + /* Send packet to trigger . */ if (!ASSERT_GE(generate_packet(&tx_xsk, AF_XDP_CONSUMER_PORT), 0, "generate freplace packet")) goto out; + switch_ns_to_rx(&tok); + while (!retries--) { if (bpf_obj2->bss->called) break; @@ -427,5 +520,6 @@ out: xdp_metadata__destroy(bpf_obj); if (tok) close_netns(tok); - SYS_NOFAIL("ip netns del xdp_metadata"); + SYS_NOFAIL("ip netns del " RX_NETNS_NAME); + SYS_NOFAIL("ip netns del " TX_NETNS_NAME); } diff --git a/tools/testing/selftests/bpf/progs/access_map_in_map.c b/tools/testing/selftests/bpf/progs/access_map_in_map.c new file mode 100644 index 000000000000..1126871c2ebd --- /dev/null +++ b/tools/testing/selftests/bpf/progs/access_map_in_map.c @@ -0,0 +1,93 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023. Huawei Technologies Co., Ltd */ +#include <linux/bpf.h> +#include <time.h> +#include <bpf/bpf_helpers.h> + +#include "bpf_misc.h" + +struct inner_map_type { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(key_size, 4); + __uint(value_size, 4); + __uint(max_entries, 1); +} inner_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __type(key, int); + __type(value, int); + __uint(max_entries, 1); + __array(values, struct inner_map_type); +} outer_array_map SEC(".maps") = { + .values = { + [0] = &inner_map, + }, +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH_OF_MAPS); + __type(key, int); + __type(value, int); + __uint(max_entries, 1); + __array(values, struct inner_map_type); +} outer_htab_map SEC(".maps") = { + .values = { + [0] = &inner_map, + }, +}; + +char _license[] SEC("license") = "GPL"; + +int tgid = 0; + +static int acc_map_in_map(void *outer_map) +{ + int i, key, value = 0xdeadbeef; + void *inner_map; + + if ((bpf_get_current_pid_tgid() >> 32) != tgid) + return 0; + + /* Find nonexistent inner map */ + key = 1; + inner_map = bpf_map_lookup_elem(outer_map, &key); + if (inner_map) + return 0; + + /* Find the old inner map */ + key = 0; + inner_map = bpf_map_lookup_elem(outer_map, &key); + if (!inner_map) + return 0; + + /* Wait for the old inner map to be replaced */ + for (i = 0; i < 2048; i++) + bpf_map_update_elem(inner_map, &key, &value, 0); + + return 0; +} + +SEC("?kprobe/" SYS_PREFIX "sys_getpgid") +int access_map_in_array(void *ctx) +{ + return acc_map_in_map(&outer_array_map); +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +int sleepable_access_map_in_array(void *ctx) +{ + return acc_map_in_map(&outer_array_map); +} + +SEC("?kprobe/" SYS_PREFIX "sys_getpgid") +int access_map_in_htab(void *ctx) +{ + return acc_map_in_map(&outer_htab_map); +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +int sleepable_access_map_in_htab(void *ctx) +{ + return acc_map_in_map(&outer_htab_map); +} diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h index 799fff4995d8..2fd59970c43a 100644 --- a/tools/testing/selftests/bpf/progs/bpf_misc.h +++ b/tools/testing/selftests/bpf/progs/bpf_misc.h @@ -71,6 +71,7 @@ #define __retval_unpriv(val) __attribute__((btf_decl_tag("comment:test_retval_unpriv="#val))) #define __auxiliary __attribute__((btf_decl_tag("comment:test_auxiliary"))) #define __auxiliary_unpriv __attribute__((btf_decl_tag("comment:test_auxiliary_unpriv"))) +#define __btf_path(path) __attribute__((btf_decl_tag("comment:test_btf_path=" path))) /* Convenience macro for use with 'asm volatile' blocks */ #define __naked __attribute__((naked)) diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h index 0b793a102791..1bdc680b0e0e 100644 --- a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h +++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h @@ -26,6 +26,7 @@ #define IPV6_AUTOFLOWLABEL 70 #define TC_ACT_UNSPEC (-1) +#define TC_ACT_OK 0 #define TC_ACT_SHOT 2 #define SOL_TCP 6 diff --git a/tools/testing/selftests/bpf/progs/cgrp_ls_recursion.c b/tools/testing/selftests/bpf/progs/cgrp_ls_recursion.c index a043d8fefdac..610c2427fd93 100644 --- a/tools/testing/selftests/bpf/progs/cgrp_ls_recursion.c +++ b/tools/testing/selftests/bpf/progs/cgrp_ls_recursion.c @@ -21,50 +21,100 @@ struct { __type(value, long); } map_b SEC(".maps"); +int target_hid = 0; +bool is_cgroup1 = 0; + +struct cgroup *bpf_task_get_cgroup1(struct task_struct *task, int hierarchy_id) __ksym; +void bpf_cgroup_release(struct cgroup *cgrp) __ksym; + +static void __on_lookup(struct cgroup *cgrp) +{ + bpf_cgrp_storage_delete(&map_a, cgrp); + bpf_cgrp_storage_delete(&map_b, cgrp); +} + SEC("fentry/bpf_local_storage_lookup") int BPF_PROG(on_lookup) { struct task_struct *task = bpf_get_current_task_btf(); + struct cgroup *cgrp; + + if (is_cgroup1) { + cgrp = bpf_task_get_cgroup1(task, target_hid); + if (!cgrp) + return 0; - bpf_cgrp_storage_delete(&map_a, task->cgroups->dfl_cgrp); - bpf_cgrp_storage_delete(&map_b, task->cgroups->dfl_cgrp); + __on_lookup(cgrp); + bpf_cgroup_release(cgrp); + return 0; + } + + __on_lookup(task->cgroups->dfl_cgrp); return 0; } -SEC("fentry/bpf_local_storage_update") -int BPF_PROG(on_update) +static void __on_update(struct cgroup *cgrp) { - struct task_struct *task = bpf_get_current_task_btf(); long *ptr; - ptr = bpf_cgrp_storage_get(&map_a, task->cgroups->dfl_cgrp, 0, - BPF_LOCAL_STORAGE_GET_F_CREATE); + ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0, BPF_LOCAL_STORAGE_GET_F_CREATE); if (ptr) *ptr += 1; - ptr = bpf_cgrp_storage_get(&map_b, task->cgroups->dfl_cgrp, 0, - BPF_LOCAL_STORAGE_GET_F_CREATE); + ptr = bpf_cgrp_storage_get(&map_b, cgrp, 0, BPF_LOCAL_STORAGE_GET_F_CREATE); if (ptr) *ptr += 1; +} +SEC("fentry/bpf_local_storage_update") +int BPF_PROG(on_update) +{ + struct task_struct *task = bpf_get_current_task_btf(); + struct cgroup *cgrp; + + if (is_cgroup1) { + cgrp = bpf_task_get_cgroup1(task, target_hid); + if (!cgrp) + return 0; + + __on_update(cgrp); + bpf_cgroup_release(cgrp); + return 0; + } + + __on_update(task->cgroups->dfl_cgrp); return 0; } -SEC("tp_btf/sys_enter") -int BPF_PROG(on_enter, struct pt_regs *regs, long id) +static void __on_enter(struct pt_regs *regs, long id, struct cgroup *cgrp) { - struct task_struct *task; long *ptr; - task = bpf_get_current_task_btf(); - ptr = bpf_cgrp_storage_get(&map_a, task->cgroups->dfl_cgrp, 0, - BPF_LOCAL_STORAGE_GET_F_CREATE); + ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0, BPF_LOCAL_STORAGE_GET_F_CREATE); if (ptr) *ptr = 200; - ptr = bpf_cgrp_storage_get(&map_b, task->cgroups->dfl_cgrp, 0, - BPF_LOCAL_STORAGE_GET_F_CREATE); + ptr = bpf_cgrp_storage_get(&map_b, cgrp, 0, BPF_LOCAL_STORAGE_GET_F_CREATE); if (ptr) *ptr = 100; +} + +SEC("tp_btf/sys_enter") +int BPF_PROG(on_enter, struct pt_regs *regs, long id) +{ + struct task_struct *task = bpf_get_current_task_btf(); + struct cgroup *cgrp; + + if (is_cgroup1) { + cgrp = bpf_task_get_cgroup1(task, target_hid); + if (!cgrp) + return 0; + + __on_enter(regs, id, cgrp); + bpf_cgroup_release(cgrp); + return 0; + } + + __on_enter(regs, id, task->cgroups->dfl_cgrp); return 0; } diff --git a/tools/testing/selftests/bpf/progs/cgrp_ls_sleepable.c b/tools/testing/selftests/bpf/progs/cgrp_ls_sleepable.c index 4c7844e1dbfa..facedd8b8250 100644 --- a/tools/testing/selftests/bpf/progs/cgrp_ls_sleepable.c +++ b/tools/testing/selftests/bpf/progs/cgrp_ls_sleepable.c @@ -17,7 +17,11 @@ struct { __u32 target_pid; __u64 cgroup_id; +int target_hid; +bool is_cgroup1; +struct cgroup *bpf_task_get_cgroup1(struct task_struct *task, int hierarchy_id) __ksym; +void bpf_cgroup_release(struct cgroup *cgrp) __ksym; void bpf_rcu_read_lock(void) __ksym; void bpf_rcu_read_unlock(void) __ksym; @@ -37,23 +41,50 @@ int cgroup_iter(struct bpf_iter__cgroup *ctx) return 0; } +static void __no_rcu_lock(struct cgroup *cgrp) +{ + long *ptr; + + /* Note that trace rcu is held in sleepable prog, so we can use + * bpf_cgrp_storage_get() in sleepable prog. + */ + ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (ptr) + cgroup_id = cgrp->kn->id; +} + SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") -int no_rcu_lock(void *ctx) +int cgrp1_no_rcu_lock(void *ctx) { struct task_struct *task; struct cgroup *cgrp; - long *ptr; + + task = bpf_get_current_task_btf(); + if (task->pid != target_pid) + return 0; + + /* bpf_task_get_cgroup1 can work in sleepable prog */ + cgrp = bpf_task_get_cgroup1(task, target_hid); + if (!cgrp) + return 0; + + __no_rcu_lock(cgrp); + bpf_cgroup_release(cgrp); + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +int no_rcu_lock(void *ctx) +{ + struct task_struct *task; task = bpf_get_current_task_btf(); if (task->pid != target_pid) return 0; /* task->cgroups is untrusted in sleepable prog outside of RCU CS */ - cgrp = task->cgroups->dfl_cgrp; - ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0, - BPF_LOCAL_STORAGE_GET_F_CREATE); - if (ptr) - cgroup_id = cgrp->kn->id; + __no_rcu_lock(task->cgroups->dfl_cgrp); return 0; } @@ -68,6 +99,22 @@ int yes_rcu_lock(void *ctx) if (task->pid != target_pid) return 0; + if (is_cgroup1) { + bpf_rcu_read_lock(); + cgrp = bpf_task_get_cgroup1(task, target_hid); + if (!cgrp) { + bpf_rcu_read_unlock(); + return 0; + } + + ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0, BPF_LOCAL_STORAGE_GET_F_CREATE); + if (ptr) + cgroup_id = cgrp->kn->id; + bpf_cgroup_release(cgrp); + bpf_rcu_read_unlock(); + return 0; + } + bpf_rcu_read_lock(); cgrp = task->cgroups->dfl_cgrp; /* cgrp is trusted under RCU CS */ diff --git a/tools/testing/selftests/bpf/progs/cgrp_ls_tp_btf.c b/tools/testing/selftests/bpf/progs/cgrp_ls_tp_btf.c index 9ebb8e2fe541..1c348f000f38 100644 --- a/tools/testing/selftests/bpf/progs/cgrp_ls_tp_btf.c +++ b/tools/testing/selftests/bpf/progs/cgrp_ls_tp_btf.c @@ -27,62 +27,100 @@ pid_t target_pid = 0; int mismatch_cnt = 0; int enter_cnt = 0; int exit_cnt = 0; +int target_hid = 0; +bool is_cgroup1 = 0; -SEC("tp_btf/sys_enter") -int BPF_PROG(on_enter, struct pt_regs *regs, long id) +struct cgroup *bpf_task_get_cgroup1(struct task_struct *task, int hierarchy_id) __ksym; +void bpf_cgroup_release(struct cgroup *cgrp) __ksym; + +static void __on_enter(struct pt_regs *regs, long id, struct cgroup *cgrp) { - struct task_struct *task; long *ptr; int err; - task = bpf_get_current_task_btf(); - if (task->pid != target_pid) - return 0; - /* populate value 0 */ - ptr = bpf_cgrp_storage_get(&map_a, task->cgroups->dfl_cgrp, 0, + ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0, BPF_LOCAL_STORAGE_GET_F_CREATE); if (!ptr) - return 0; + return; /* delete value 0 */ - err = bpf_cgrp_storage_delete(&map_a, task->cgroups->dfl_cgrp); + err = bpf_cgrp_storage_delete(&map_a, cgrp); if (err) - return 0; + return; /* value is not available */ - ptr = bpf_cgrp_storage_get(&map_a, task->cgroups->dfl_cgrp, 0, 0); + ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0, 0); if (ptr) - return 0; + return; /* re-populate the value */ - ptr = bpf_cgrp_storage_get(&map_a, task->cgroups->dfl_cgrp, 0, + ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0, BPF_LOCAL_STORAGE_GET_F_CREATE); if (!ptr) - return 0; + return; __sync_fetch_and_add(&enter_cnt, 1); *ptr = MAGIC_VALUE + enter_cnt; - - return 0; } -SEC("tp_btf/sys_exit") -int BPF_PROG(on_exit, struct pt_regs *regs, long id) +SEC("tp_btf/sys_enter") +int BPF_PROG(on_enter, struct pt_regs *regs, long id) { struct task_struct *task; - long *ptr; + struct cgroup *cgrp; task = bpf_get_current_task_btf(); if (task->pid != target_pid) return 0; - ptr = bpf_cgrp_storage_get(&map_a, task->cgroups->dfl_cgrp, 0, + if (is_cgroup1) { + cgrp = bpf_task_get_cgroup1(task, target_hid); + if (!cgrp) + return 0; + + __on_enter(regs, id, cgrp); + bpf_cgroup_release(cgrp); + return 0; + } + + __on_enter(regs, id, task->cgroups->dfl_cgrp); + return 0; +} + +static void __on_exit(struct pt_regs *regs, long id, struct cgroup *cgrp) +{ + long *ptr; + + ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0, BPF_LOCAL_STORAGE_GET_F_CREATE); if (!ptr) - return 0; + return; __sync_fetch_and_add(&exit_cnt, 1); if (*ptr != MAGIC_VALUE + exit_cnt) __sync_fetch_and_add(&mismatch_cnt, 1); +} + +SEC("tp_btf/sys_exit") +int BPF_PROG(on_exit, struct pt_regs *regs, long id) +{ + struct task_struct *task; + struct cgroup *cgrp; + + task = bpf_get_current_task_btf(); + if (task->pid != target_pid) + return 0; + + if (is_cgroup1) { + cgrp = bpf_task_get_cgroup1(task, target_hid); + if (!cgrp) + return 0; + + __on_exit(regs, id, cgrp); + bpf_cgroup_release(cgrp); + return 0; + } + + __on_exit(regs, id, task->cgroups->dfl_cgrp); return 0; } diff --git a/tools/testing/selftests/bpf/progs/cpumask_common.h b/tools/testing/selftests/bpf/progs/cpumask_common.h index b15c588ace15..0cd4aebb97cf 100644 --- a/tools/testing/selftests/bpf/progs/cpumask_common.h +++ b/tools/testing/selftests/bpf/progs/cpumask_common.h @@ -54,6 +54,7 @@ bool bpf_cpumask_full(const struct cpumask *cpumask) __ksym; void bpf_cpumask_copy(struct bpf_cpumask *dst, const struct cpumask *src) __ksym; u32 bpf_cpumask_any_distribute(const struct cpumask *src) __ksym; u32 bpf_cpumask_any_and_distribute(const struct cpumask *src1, const struct cpumask *src2) __ksym; +u32 bpf_cpumask_weight(const struct cpumask *cpumask) __ksym; void bpf_rcu_read_lock(void) __ksym; void bpf_rcu_read_unlock(void) __ksym; diff --git a/tools/testing/selftests/bpf/progs/cpumask_success.c b/tools/testing/selftests/bpf/progs/cpumask_success.c index 674a63424dee..fc3666edf456 100644 --- a/tools/testing/selftests/bpf/progs/cpumask_success.c +++ b/tools/testing/selftests/bpf/progs/cpumask_success.c @@ -461,6 +461,49 @@ int BPF_PROG(test_global_mask_rcu, struct task_struct *task, u64 clone_flags) } SEC("tp_btf/task_newtask") +int BPF_PROG(test_cpumask_weight, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *local; + + if (!is_test_task()) + return 0; + + local = create_cpumask(); + if (!local) + return 0; + + if (bpf_cpumask_weight(cast(local)) != 0) { + err = 3; + goto out; + } + + bpf_cpumask_set_cpu(0, local); + if (bpf_cpumask_weight(cast(local)) != 1) { + err = 4; + goto out; + } + + /* + * Make sure that adding additional CPUs changes the weight. Test to + * see whether the CPU was set to account for running on UP machines. + */ + bpf_cpumask_set_cpu(1, local); + if (bpf_cpumask_test_cpu(1, cast(local)) && bpf_cpumask_weight(cast(local)) != 2) { + err = 5; + goto out; + } + + bpf_cpumask_clear(local); + if (bpf_cpumask_weight(cast(local)) != 0) { + err = 6; + goto out; + } +out: + bpf_cpumask_release(local); + return 0; +} + +SEC("tp_btf/task_newtask") __success int BPF_PROG(test_refcount_null_tracking, struct task_struct *task, u64 clone_flags) { diff --git a/tools/testing/selftests/bpf/progs/exceptions_assert.c b/tools/testing/selftests/bpf/progs/exceptions_assert.c index 49efaed143fc..0ef81040da59 100644 --- a/tools/testing/selftests/bpf/progs/exceptions_assert.c +++ b/tools/testing/selftests/bpf/progs/exceptions_assert.c @@ -125,7 +125,7 @@ int check_assert_generic(struct __sk_buff *ctx) } SEC("?fentry/bpf_check") -__failure __msg("At program exit the register R0 has value (0x40; 0x0)") +__failure __msg("At program exit the register R1 has smin=64 smax=64") int check_assert_with_return(void *ctx) { bpf_assert_with(!ctx, 64); diff --git a/tools/testing/selftests/bpf/progs/exceptions_fail.c b/tools/testing/selftests/bpf/progs/exceptions_fail.c index 8c0ef2742208..9cceb6521143 100644 --- a/tools/testing/selftests/bpf/progs/exceptions_fail.c +++ b/tools/testing/selftests/bpf/progs/exceptions_fail.c @@ -308,7 +308,7 @@ int reject_set_exception_cb_bad_ret1(void *ctx) } SEC("?fentry/bpf_check") -__failure __msg("At program exit the register R0 has value (0x40; 0x0) should") +__failure __msg("At program exit the register R1 has smin=64 smax=64 should") int reject_set_exception_cb_bad_ret2(void *ctx) { bpf_throw(64); diff --git a/tools/testing/selftests/bpf/progs/freplace_dead_global_func.c b/tools/testing/selftests/bpf/progs/freplace_dead_global_func.c new file mode 100644 index 000000000000..e6a75f86cac6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/freplace_dead_global_func.c @@ -0,0 +1,11 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +SEC("freplace") +int freplace_prog(void) +{ + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c index b2181f850d3e..3aca3dc145b5 100644 --- a/tools/testing/selftests/bpf/progs/iters.c +++ b/tools/testing/selftests/bpf/progs/iters.c @@ -846,7 +846,7 @@ __naked int delayed_precision_mark(void) "call %[bpf_iter_num_next];" "if r0 == 0 goto 2f;" "if r6 != 42 goto 3f;" - "r7 = -32;" + "r7 = -33;" "call %[bpf_get_prandom_u32];" "r6 = r0;" "goto 1b;\n" diff --git a/tools/testing/selftests/bpf/progs/local_kptr_stash.c b/tools/testing/selftests/bpf/progs/local_kptr_stash.c index 1769fdff6aea..75043ffc5dad 100644 --- a/tools/testing/selftests/bpf/progs/local_kptr_stash.c +++ b/tools/testing/selftests/bpf/progs/local_kptr_stash.c @@ -37,11 +37,18 @@ struct plain_local { long data; }; +struct local_with_root { + long key; + struct bpf_spin_lock l; + struct bpf_rb_root r __contains(node_data, node); +}; + struct map_value { struct prog_test_ref_kfunc *not_kptr; struct prog_test_ref_kfunc __kptr *val; struct node_data __kptr *node; struct plain_local __kptr *plain; + struct local_with_root __kptr *local_root; }; /* This is necessary so that LLVM generates BTF for node_data struct @@ -65,6 +72,17 @@ struct { __uint(max_entries, 2); } some_nodes SEC(".maps"); +static bool less(struct bpf_rb_node *a, const struct bpf_rb_node *b) +{ + struct node_data *node_a; + struct node_data *node_b; + + node_a = container_of(a, struct node_data, node); + node_b = container_of(b, struct node_data, node); + + return node_a->key < node_b->key; +} + static int create_and_stash(int idx, int val) { struct map_value *mapval; @@ -114,6 +132,41 @@ long stash_plain(void *ctx) } SEC("tc") +long stash_local_with_root(void *ctx) +{ + struct local_with_root *res; + struct map_value *mapval; + struct node_data *n; + int idx = 0; + + mapval = bpf_map_lookup_elem(&some_nodes, &idx); + if (!mapval) + return 1; + + res = bpf_obj_new(typeof(*res)); + if (!res) + return 2; + res->key = 41; + + n = bpf_obj_new(typeof(*n)); + if (!n) { + bpf_obj_drop(res); + return 3; + } + + bpf_spin_lock(&res->l); + bpf_rbtree_add(&res->r, &n->node, less); + bpf_spin_unlock(&res->l); + + res = bpf_kptr_xchg(&mapval->local_root, res); + if (res) { + bpf_obj_drop(res); + return 4; + } + return 0; +} + +SEC("tc") long unstash_rb_node(void *ctx) { struct map_value *mapval; diff --git a/tools/testing/selftests/bpf/progs/map_in_map_btf.c b/tools/testing/selftests/bpf/progs/map_in_map_btf.c new file mode 100644 index 000000000000..7a1336d7b16a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/map_in_map_btf.c @@ -0,0 +1,73 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023. Huawei Technologies Co., Ltd */ +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +#include "bpf_misc.h" +#include "bpf_experimental.h" + +struct node_data { + __u64 data; + struct bpf_list_node node; +}; + +struct map_value { + struct bpf_list_head head __contains(node_data, node); + struct bpf_spin_lock lock; +}; + +struct inner_array_type { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, struct map_value); + __uint(max_entries, 1); +} inner_array SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __uint(key_size, 4); + __uint(value_size, 4); + __uint(max_entries, 1); + __array(values, struct inner_array_type); +} outer_array SEC(".maps") = { + .values = { + [0] = &inner_array, + }, +}; + +char _license[] SEC("license") = "GPL"; + +int pid = 0; +bool done = false; + +SEC("fentry/" SYS_PREFIX "sys_nanosleep") +int add_to_list_in_inner_array(void *ctx) +{ + struct map_value *value; + struct node_data *new; + struct bpf_map *map; + int zero = 0; + + if (done || (u32)bpf_get_current_pid_tgid() != pid) + return 0; + + map = bpf_map_lookup_elem(&outer_array, &zero); + if (!map) + return 0; + + value = bpf_map_lookup_elem(map, &zero); + if (!value) + return 0; + + new = bpf_obj_new(typeof(*new)); + if (!new) + return 0; + + bpf_spin_lock(&value->lock); + bpf_list_push_back(&value->head, &new->node); + bpf_spin_unlock(&value->lock); + done = true; + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/normal_map_btf.c b/tools/testing/selftests/bpf/progs/normal_map_btf.c new file mode 100644 index 000000000000..66cde82aa86d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/normal_map_btf.c @@ -0,0 +1,56 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023. Huawei Technologies Co., Ltd */ +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +#include "bpf_misc.h" +#include "bpf_experimental.h" + +struct node_data { + __u64 data; + struct bpf_list_node node; +}; + +struct map_value { + struct bpf_list_head head __contains(node_data, node); + struct bpf_spin_lock lock; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, struct map_value); + __uint(max_entries, 1); +} array SEC(".maps"); + +char _license[] SEC("license") = "GPL"; + +int pid = 0; +bool done = false; + +SEC("fentry/" SYS_PREFIX "sys_nanosleep") +int add_to_list_in_array(void *ctx) +{ + struct map_value *value; + struct node_data *new; + int zero = 0; + + if (done || (u32)bpf_get_current_pid_tgid() != pid) + return 0; + + value = bpf_map_lookup_elem(&array, &zero); + if (!value) + return 0; + + new = bpf_obj_new(typeof(*new)); + if (!new) + return 0; + + bpf_spin_lock(&value->lock); + bpf_list_push_back(&value->head, &new->node); + bpf_spin_unlock(&value->lock); + done = true; + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/priv_map.c b/tools/testing/selftests/bpf/progs/priv_map.c new file mode 100644 index 000000000000..9085be50f03b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/priv_map.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_QUEUE); + __uint(max_entries, 1); + __type(value, __u32); +} priv_map SEC(".maps"); diff --git a/tools/testing/selftests/bpf/progs/priv_prog.c b/tools/testing/selftests/bpf/progs/priv_prog.c new file mode 100644 index 000000000000..3c7b2b618c8a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/priv_prog.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +SEC("kprobe") +int kprobe_prog(void *ctx) +{ + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/syscall.c b/tools/testing/selftests/bpf/progs/syscall.c index e550f728962d..3d3cafdebe72 100644 --- a/tools/testing/selftests/bpf/progs/syscall.c +++ b/tools/testing/selftests/bpf/progs/syscall.c @@ -6,9 +6,15 @@ #include <bpf/bpf_tracing.h> #include <../../../tools/include/linux/filter.h> #include <linux/btf.h> +#include <string.h> +#include <errno.h> char _license[] SEC("license") = "GPL"; +struct bpf_map { + int id; +} __attribute__((preserve_access_index)); + struct args { __u64 log_buf; __u32 log_size; @@ -27,6 +33,37 @@ struct args { BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), sz), \ BTF_INT_ENC(encoding, bits_offset, bits) +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, union bpf_attr); + __uint(max_entries, 1); +} bpf_attr_array SEC(".maps"); + +struct inner_map_type { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(key_size, 4); + __uint(value_size, 4); + __uint(max_entries, 1); +} inner_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS); + __type(key, int); + __type(value, int); + __uint(max_entries, 1); + __array(values, struct inner_map_type); +} outer_array_map SEC(".maps") = { + .values = { + [0] = &inner_map, + }, +}; + +static inline __u64 ptr_to_u64(const void *ptr) +{ + return (__u64) (unsigned long) ptr; +} + static int btf_load(void) { struct btf_blob { @@ -58,7 +95,7 @@ static int btf_load(void) } SEC("syscall") -int bpf_prog(struct args *ctx) +int load_prog(struct args *ctx) { static char license[] = "GPL"; static struct bpf_insn insns[] = { @@ -94,8 +131,8 @@ int bpf_prog(struct args *ctx) map_create_attr.max_entries = ctx->max_entries; map_create_attr.btf_fd = ret; - prog_load_attr.license = (long) license; - prog_load_attr.insns = (long) insns; + prog_load_attr.license = ptr_to_u64(license); + prog_load_attr.insns = ptr_to_u64(insns); prog_load_attr.log_buf = ctx->log_buf; prog_load_attr.log_size = ctx->log_size; prog_load_attr.log_level = 1; @@ -107,8 +144,8 @@ int bpf_prog(struct args *ctx) insns[3].imm = ret; map_update_attr.map_fd = ret; - map_update_attr.key = (long) &key; - map_update_attr.value = (long) &value; + map_update_attr.key = ptr_to_u64(&key); + map_update_attr.value = ptr_to_u64(&value); ret = bpf_sys_bpf(BPF_MAP_UPDATE_ELEM, &map_update_attr, sizeof(map_update_attr)); if (ret < 0) return ret; @@ -119,3 +156,52 @@ int bpf_prog(struct args *ctx) ctx->prog_fd = ret; return 1; } + +SEC("syscall") +int update_outer_map(void *ctx) +{ + int zero = 0, ret = 0, outer_fd = -1, inner_fd = -1, err; + const int attr_sz = sizeof(union bpf_attr); + union bpf_attr *attr; + + attr = bpf_map_lookup_elem((struct bpf_map *)&bpf_attr_array, &zero); + if (!attr) + goto out; + + memset(attr, 0, attr_sz); + attr->map_id = ((struct bpf_map *)&outer_array_map)->id; + outer_fd = bpf_sys_bpf(BPF_MAP_GET_FD_BY_ID, attr, attr_sz); + if (outer_fd < 0) + goto out; + + memset(attr, 0, attr_sz); + attr->map_type = BPF_MAP_TYPE_ARRAY; + attr->key_size = 4; + attr->value_size = 4; + attr->max_entries = 1; + inner_fd = bpf_sys_bpf(BPF_MAP_CREATE, attr, attr_sz); + if (inner_fd < 0) + goto out; + + memset(attr, 0, attr_sz); + attr->map_fd = outer_fd; + attr->key = ptr_to_u64(&zero); + attr->value = ptr_to_u64(&inner_fd); + err = bpf_sys_bpf(BPF_MAP_UPDATE_ELEM, attr, attr_sz); + if (err) + goto out; + + memset(attr, 0, attr_sz); + attr->map_fd = outer_fd; + attr->key = ptr_to_u64(&zero); + err = bpf_sys_bpf(BPF_MAP_DELETE_ELEM, attr, attr_sz); + if (err) + goto out; + ret = 1; +out: + if (inner_fd >= 0) + bpf_sys_close(inner_fd); + if (outer_fd >= 0) + bpf_sys_close(outer_fd); + return ret; +} diff --git a/tools/testing/selftests/bpf/progs/test_fsverity.c b/tools/testing/selftests/bpf/progs/test_fsverity.c new file mode 100644 index 000000000000..3975495b75c8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_fsverity.c @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_kfuncs.h" + +char _license[] SEC("license") = "GPL"; + +#ifndef SHA256_DIGEST_SIZE +#define SHA256_DIGEST_SIZE 32 +#endif + +#define SIZEOF_STRUCT_FSVERITY_DIGEST 4 /* sizeof(struct fsverity_digest) */ + +char expected_digest[SIZEOF_STRUCT_FSVERITY_DIGEST + SHA256_DIGEST_SIZE]; +char digest[SIZEOF_STRUCT_FSVERITY_DIGEST + SHA256_DIGEST_SIZE]; +__u32 monitored_pid; +__u32 got_fsverity; +__u32 digest_matches; + +SEC("lsm.s/file_open") +int BPF_PROG(test_file_open, struct file *f) +{ + struct bpf_dynptr digest_ptr; + __u32 pid; + int ret; + int i; + + pid = bpf_get_current_pid_tgid() >> 32; + if (pid != monitored_pid) + return 0; + + bpf_dynptr_from_mem(digest, sizeof(digest), 0, &digest_ptr); + ret = bpf_get_fsverity_digest(f, &digest_ptr); + if (ret < 0) + return 0; + got_fsverity = 1; + + for (i = 0; i < sizeof(digest); i++) { + if (digest[i] != expected_digest[i]) + return 0; + } + + digest_matches = 1; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_get_xattr.c b/tools/testing/selftests/bpf/progs/test_get_xattr.c new file mode 100644 index 000000000000..7eb2a4e5a3e5 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_get_xattr.c @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_kfuncs.h" + +char _license[] SEC("license") = "GPL"; + +__u32 monitored_pid; +__u32 found_xattr; + +static const char expected_value[] = "hello"; +char value[32]; + +SEC("lsm.s/file_open") +int BPF_PROG(test_file_open, struct file *f) +{ + struct bpf_dynptr value_ptr; + __u32 pid; + int ret; + + pid = bpf_get_current_pid_tgid() >> 32; + if (pid != monitored_pid) + return 0; + + bpf_dynptr_from_mem(value, sizeof(value), 0, &value_ptr); + + ret = bpf_get_file_xattr(f, "user.kfuncs", &value_ptr); + if (ret != sizeof(expected_value)) + return 0; + if (bpf_strncmp(value, ret, expected_value)) + return 0; + found_xattr = 1; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_global_func15.c b/tools/testing/selftests/bpf/progs/test_global_func15.c index b512d6a6c75e..b4e089d6981d 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func15.c +++ b/tools/testing/selftests/bpf/progs/test_global_func15.c @@ -13,7 +13,7 @@ __noinline int foo(unsigned int *v) } SEC("cgroup_skb/ingress") -__failure __msg("At program exit the register R0 has value") +__failure __msg("At program exit the register R0 has ") int global_func15(struct __sk_buff *skb) { unsigned int v = 1; @@ -22,3 +22,35 @@ int global_func15(struct __sk_buff *skb) return v; } + +SEC("cgroup_skb/ingress") +__log_level(2) __flag(BPF_F_TEST_STATE_FREQ) +__failure +/* check that fallthrough code path marks r0 as precise */ +__msg("mark_precise: frame0: regs=r0 stack= before 2: (b7) r0 = 1") +/* check that branch code path marks r0 as precise */ +__msg("mark_precise: frame0: regs=r0 stack= before 0: (85) call bpf_get_prandom_u32#7") +__msg("At program exit the register R0 has ") +__naked int global_func15_tricky_pruning(void) +{ + asm volatile ( + "call %[bpf_get_prandom_u32];" + "if r0 s> 1000 goto 1f;" + "r0 = 1;" + "1:" + "goto +0;" /* checkpoint */ + /* cgroup_skb/ingress program is expected to return [0, 1] + * values, so branch above makes sure that in a fallthrough + * case we have a valid 1 stored in R0 register, but in + * a branch case we assign some random value to R0. So if + * there is something wrong with precision tracking for R0 at + * program exit, we might erronenously prune branch case, + * because R0 in fallthrough case is imprecise (and thus any + * value is valid from POV of verifier is_state_equal() logic) + */ + "exit;" + : + : __imm(bpf_get_prandom_u32) + : __clobber_common + ); +} diff --git a/tools/testing/selftests/bpf/progs/test_global_func16.c b/tools/testing/selftests/bpf/progs/test_global_func16.c index e7206304632e..e3e64bc472cd 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func16.c +++ b/tools/testing/selftests/bpf/progs/test_global_func16.c @@ -13,7 +13,7 @@ __noinline int foo(int (*arr)[10]) } SEC("cgroup_skb/ingress") -__failure __msg("invalid indirect read from stack") +__success int global_func16(struct __sk_buff *skb) { int array[10]; diff --git a/tools/testing/selftests/bpf/progs/test_sig_in_xattr.c b/tools/testing/selftests/bpf/progs/test_sig_in_xattr.c new file mode 100644 index 000000000000..2f0eb1334d65 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sig_in_xattr.c @@ -0,0 +1,83 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include <errno.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_kfuncs.h" + +char _license[] SEC("license") = "GPL"; + +#ifndef SHA256_DIGEST_SIZE +#define SHA256_DIGEST_SIZE 32 +#endif + +#define MAX_SIG_SIZE 1024 + +/* By default, "fsverity sign" signs a file with fsverity_formatted_digest + * of the file. fsverity_formatted_digest on the kernel side is only used + * with CONFIG_FS_VERITY_BUILTIN_SIGNATURES. However, BPF LSM doesn't not + * require CONFIG_FS_VERITY_BUILTIN_SIGNATURES, so vmlinux.h may not have + * fsverity_formatted_digest. In this test, we intentionally avoid using + * fsverity_formatted_digest. + * + * Luckily, fsverity_formatted_digest is simply 8-byte magic followed by + * fsverity_digest. We use a char array of size fsverity_formatted_digest + * plus SHA256_DIGEST_SIZE. The magic part of it is filled by user space, + * and the rest of it is filled by bpf_get_fsverity_digest. + * + * Note that, generating signatures based on fsverity_formatted_digest is + * the design choice of this selftest (and "fsverity sign"). With BPF + * LSM, we have the flexibility to generate signature based on other data + * sets, for example, fsverity_digest or only the digest[] part of it. + */ +#define MAGIC_SIZE 8 +#define SIZEOF_STRUCT_FSVERITY_DIGEST 4 /* sizeof(struct fsverity_digest) */ +char digest[MAGIC_SIZE + SIZEOF_STRUCT_FSVERITY_DIGEST + SHA256_DIGEST_SIZE]; + +__u32 monitored_pid; +char sig[MAX_SIG_SIZE]; +__u32 sig_size; +__u32 user_keyring_serial; + +SEC("lsm.s/file_open") +int BPF_PROG(test_file_open, struct file *f) +{ + struct bpf_dynptr digest_ptr, sig_ptr; + struct bpf_key *trusted_keyring; + __u32 pid; + int ret; + + pid = bpf_get_current_pid_tgid() >> 32; + if (pid != monitored_pid) + return 0; + + /* digest_ptr points to fsverity_digest */ + bpf_dynptr_from_mem(digest + MAGIC_SIZE, sizeof(digest) - MAGIC_SIZE, 0, &digest_ptr); + + ret = bpf_get_fsverity_digest(f, &digest_ptr); + /* No verity, allow access */ + if (ret < 0) + return 0; + + /* Move digest_ptr to fsverity_formatted_digest */ + bpf_dynptr_from_mem(digest, sizeof(digest), 0, &digest_ptr); + + /* Read signature from xattr */ + bpf_dynptr_from_mem(sig, sizeof(sig), 0, &sig_ptr); + ret = bpf_get_file_xattr(f, "user.sig", &sig_ptr); + /* No signature, reject access */ + if (ret < 0) + return -EPERM; + + trusted_keyring = bpf_lookup_user_key(user_keyring_serial, 0); + if (!trusted_keyring) + return -ENOENT; + + /* Verify signature */ + ret = bpf_verify_pkcs7_signature(&digest_ptr, &sig_ptr, trusted_keyring); + + bpf_key_put(trusted_keyring); + return ret; +} diff --git a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c index f66af753bbbb..3e436e6f7312 100644 --- a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c @@ -6,66 +6,34 @@ * modify it under the terms of version 2 of the GNU General Public * License as published by the Free Software Foundation. */ -#include <stddef.h> -#include <string.h> -#include <arpa/inet.h> -#include <linux/bpf.h> -#include <linux/if_ether.h> -#include <linux/if_packet.h> -#include <linux/if_tunnel.h> -#include <linux/ip.h> -#include <linux/ipv6.h> -#include <linux/icmp.h> -#include <linux/types.h> -#include <linux/socket.h> -#include <linux/pkt_cls.h> -#include <linux/erspan.h> -#include <linux/udp.h> +#include "vmlinux.h" +#include <bpf/bpf_core_read.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_endian.h> +#include "bpf_kfuncs.h" +#include "bpf_tracing_net.h" #define log_err(__ret) bpf_printk("ERROR line:%d ret:%d\n", __LINE__, __ret) -#define VXLAN_UDP_PORT 4789 +#define VXLAN_UDP_PORT 4789 +#define ETH_P_IP 0x0800 +#define PACKET_HOST 0 +#define TUNNEL_CSUM bpf_htons(0x01) +#define TUNNEL_KEY bpf_htons(0x04) /* Only IPv4 address assigned to veth1. * 172.16.1.200 */ #define ASSIGNED_ADDR_VETH1 0xac1001c8 -struct geneve_opt { - __be16 opt_class; - __u8 type; - __u8 length:5; - __u8 r3:1; - __u8 r2:1; - __u8 r1:1; - __u8 opt_data[8]; /* hard-coded to 8 byte */ -}; - -struct vxlanhdr { - __be32 vx_flags; - __be32 vx_vni; -} __attribute__((packed)); - -struct vxlan_metadata { - __u32 gbp; -}; - -struct bpf_fou_encap { - __be16 sport; - __be16 dport; -}; - -enum bpf_fou_encap_type { - FOU_BPF_ENCAP_FOU, - FOU_BPF_ENCAP_GUE, -}; - int bpf_skb_set_fou_encap(struct __sk_buff *skb_ctx, struct bpf_fou_encap *encap, int type) __ksym; int bpf_skb_get_fou_encap(struct __sk_buff *skb_ctx, struct bpf_fou_encap *encap) __ksym; +struct xfrm_state * +bpf_xdp_get_xfrm_state(struct xdp_md *ctx, struct bpf_xfrm_state_opts *opts, + u32 opts__sz) __ksym; +void bpf_xdp_xfrm_state_release(struct xfrm_state *x) __ksym; struct { __uint(type, BPF_MAP_TYPE_ARRAY); @@ -205,9 +173,9 @@ int erspan_set_tunnel(struct __sk_buff *skb) __u8 hwid = 7; md.version = 2; - md.u.md2.dir = direction; - md.u.md2.hwid = hwid & 0xf; - md.u.md2.hwid_upper = (hwid >> 4) & 0x3; + BPF_CORE_WRITE_BITFIELD(&md.u.md2, dir, direction); + BPF_CORE_WRITE_BITFIELD(&md.u.md2, hwid, (hwid & 0xf)); + BPF_CORE_WRITE_BITFIELD(&md.u.md2, hwid_upper, (hwid >> 4) & 0x3); #endif ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md)); @@ -246,8 +214,9 @@ int erspan_get_tunnel(struct __sk_buff *skb) bpf_printk("\tindex %x\n", index); #else bpf_printk("\tdirection %d hwid %x timestamp %u\n", - md.u.md2.dir, - (md.u.md2.hwid_upper << 4) + md.u.md2.hwid, + BPF_CORE_READ_BITFIELD(&md.u.md2, dir), + (BPF_CORE_READ_BITFIELD(&md.u.md2, hwid_upper) << 4) + + BPF_CORE_READ_BITFIELD(&md.u.md2, hwid), bpf_ntohl(md.u.md2.timestamp)); #endif @@ -284,9 +253,9 @@ int ip4ip6erspan_set_tunnel(struct __sk_buff *skb) __u8 hwid = 17; md.version = 2; - md.u.md2.dir = direction; - md.u.md2.hwid = hwid & 0xf; - md.u.md2.hwid_upper = (hwid >> 4) & 0x3; + BPF_CORE_WRITE_BITFIELD(&md.u.md2, dir, direction); + BPF_CORE_WRITE_BITFIELD(&md.u.md2, hwid, (hwid & 0xf)); + BPF_CORE_WRITE_BITFIELD(&md.u.md2, hwid_upper, (hwid >> 4) & 0x3); #endif ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md)); @@ -326,8 +295,9 @@ int ip4ip6erspan_get_tunnel(struct __sk_buff *skb) bpf_printk("\tindex %x\n", index); #else bpf_printk("\tdirection %d hwid %x timestamp %u\n", - md.u.md2.dir, - (md.u.md2.hwid_upper << 4) + md.u.md2.hwid, + BPF_CORE_READ_BITFIELD(&md.u.md2, dir), + (BPF_CORE_READ_BITFIELD(&md.u.md2, hwid_upper) << 4) + + BPF_CORE_READ_BITFIELD(&md.u.md2, hwid), bpf_ntohl(md.u.md2.timestamp)); #endif @@ -963,6 +933,10 @@ int ip6ip6_get_tunnel(struct __sk_buff *skb) return TC_ACT_OK; } +volatile int xfrm_reqid = 0; +volatile int xfrm_spi = 0; +volatile int xfrm_remote_ip = 0; + SEC("tc") int xfrm_get_state(struct __sk_buff *skb) { @@ -973,10 +947,58 @@ int xfrm_get_state(struct __sk_buff *skb) if (ret < 0) return TC_ACT_OK; - bpf_printk("reqid %d spi 0x%x remote ip 0x%x\n", - x.reqid, bpf_ntohl(x.spi), - bpf_ntohl(x.remote_ipv4)); + xfrm_reqid = x.reqid; + xfrm_spi = bpf_ntohl(x.spi); + xfrm_remote_ip = bpf_ntohl(x.remote_ipv4); + return TC_ACT_OK; } +volatile int xfrm_replay_window = 0; + +SEC("xdp") +int xfrm_get_state_xdp(struct xdp_md *xdp) +{ + struct bpf_xfrm_state_opts opts = {}; + struct xfrm_state *x = NULL; + struct ip_esp_hdr *esph; + struct bpf_dynptr ptr; + u8 esph_buf[8] = {}; + u8 iph_buf[20] = {}; + struct iphdr *iph; + u32 off; + + if (bpf_dynptr_from_xdp(xdp, 0, &ptr)) + goto out; + + off = sizeof(struct ethhdr); + iph = bpf_dynptr_slice(&ptr, off, iph_buf, sizeof(iph_buf)); + if (!iph || iph->protocol != IPPROTO_ESP) + goto out; + + off += sizeof(struct iphdr); + esph = bpf_dynptr_slice(&ptr, off, esph_buf, sizeof(esph_buf)); + if (!esph) + goto out; + + opts.netns_id = BPF_F_CURRENT_NETNS; + opts.daddr.a4 = iph->daddr; + opts.spi = esph->spi; + opts.proto = IPPROTO_ESP; + opts.family = AF_INET; + + x = bpf_xdp_get_xfrm_state(xdp, &opts, sizeof(opts)); + if (!x) + goto out; + + if (!x->replay_esn) + goto out; + + xfrm_replay_window = x->replay_esn->replay_window; +out: + if (x) + bpf_xdp_xfrm_state_release(x); + return XDP_PASS; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c b/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c index 7748cc23de8a..f42e9f3831a1 100644 --- a/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c +++ b/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c @@ -10,17 +10,11 @@ #include <errno.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> +#include "bpf_kfuncs.h" #define MAX_DATA_SIZE (1024 * 1024) #define MAX_SIG_SIZE 1024 -extern struct bpf_key *bpf_lookup_user_key(__u32 serial, __u64 flags) __ksym; -extern struct bpf_key *bpf_lookup_system_key(__u64 id) __ksym; -extern void bpf_key_put(struct bpf_key *key) __ksym; -extern int bpf_verify_pkcs7_signature(struct bpf_dynptr *data_ptr, - struct bpf_dynptr *sig_ptr, - struct bpf_key *trusted_keyring) __ksym; - __u32 monitored_pid; __u32 user_keyring_serial; __u64 system_keyring_id; diff --git a/tools/testing/selftests/bpf/progs/timer_failure.c b/tools/testing/selftests/bpf/progs/timer_failure.c index 226d33b5a05c..0996c2486f05 100644 --- a/tools/testing/selftests/bpf/progs/timer_failure.c +++ b/tools/testing/selftests/bpf/progs/timer_failure.c @@ -21,17 +21,38 @@ struct { __type(value, struct elem); } timer_map SEC(".maps"); -static int timer_cb_ret1(void *map, int *key, struct bpf_timer *timer) +__naked __noinline __used +static unsigned long timer_cb_ret_bad() { - if (bpf_get_smp_processor_id() % 2) - return 1; - else - return 0; + asm volatile ( + "call %[bpf_get_prandom_u32];" + "if r0 s> 1000 goto 1f;" + "r0 = 0;" + "1:" + "goto +0;" /* checkpoint */ + /* async callback is expected to return 0, so branch above + * skipping r0 = 0; should lead to a failure, but if exit + * instruction doesn't enforce r0's precision, this callback + * will be successfully verified + */ + "exit;" + : + : __imm(bpf_get_prandom_u32) + : __clobber_common + ); } SEC("fentry/bpf_fentry_test1") -__failure __msg("should have been in (0x0; 0x0)") -int BPF_PROG2(test_ret_1, int, a) +__log_level(2) +__flag(BPF_F_TEST_STATE_FREQ) +__failure +/* check that fallthrough code path marks r0 as precise */ +__msg("mark_precise: frame0: regs=r0 stack= before") +__msg(": (85) call bpf_get_prandom_u32#7") /* anchor message */ +/* check that branch code path marks r0 as precise */ +__msg("mark_precise: frame0: regs=r0 stack= before ") __msg(": (85) call bpf_get_prandom_u32#7") +__msg("should have been in [0, 0]") +long BPF_PROG2(test_bad_ret, int, a) { int key = 0; struct bpf_timer *timer; @@ -39,7 +60,7 @@ int BPF_PROG2(test_ret_1, int, a) timer = bpf_map_lookup_elem(&timer_map, &key); if (timer) { bpf_timer_init(timer, &timer_map, CLOCK_BOOTTIME); - bpf_timer_set_callback(timer, timer_cb_ret1); + bpf_timer_set_callback(timer, timer_cb_ret_bad); bpf_timer_start(timer, 1000, 0); } diff --git a/tools/testing/selftests/bpf/progs/user_ringbuf_fail.c b/tools/testing/selftests/bpf/progs/user_ringbuf_fail.c index 03ee946c6bf7..11ab25c42c36 100644 --- a/tools/testing/selftests/bpf/progs/user_ringbuf_fail.c +++ b/tools/testing/selftests/bpf/progs/user_ringbuf_fail.c @@ -184,7 +184,7 @@ invalid_drain_callback_return(struct bpf_dynptr *dynptr, void *context) * not be able to write to that pointer. */ SEC("?raw_tp") -__failure __msg("At callback return the register R0 has value") +__failure __msg("At callback return the register R0 has ") int user_ringbuf_callback_invalid_return(void *ctx) { bpf_user_ringbuf_drain(&user_ringbuf, invalid_drain_callback_return, NULL, 0); diff --git a/tools/testing/selftests/bpf/progs/verifier_basic_stack.c b/tools/testing/selftests/bpf/progs/verifier_basic_stack.c index 359df865a8f3..8d77cc5323d3 100644 --- a/tools/testing/selftests/bpf/progs/verifier_basic_stack.c +++ b/tools/testing/selftests/bpf/progs/verifier_basic_stack.c @@ -27,8 +27,8 @@ __naked void stack_out_of_bounds(void) SEC("socket") __description("uninitialized stack1") -__failure __msg("invalid indirect read from stack") -__failure_unpriv +__success __log_level(4) __msg("stack depth 8") +__failure_unpriv __msg_unpriv("invalid indirect read from stack") __naked void uninitialized_stack1(void) { asm volatile (" \ @@ -45,8 +45,8 @@ __naked void uninitialized_stack1(void) SEC("socket") __description("uninitialized stack2") -__failure __msg("invalid read from stack") -__failure_unpriv +__success __log_level(4) __msg("stack depth 8") +__failure_unpriv __msg_unpriv("invalid read from stack") __naked void uninitialized_stack2(void) { asm volatile (" \ diff --git a/tools/testing/selftests/bpf/progs/verifier_bitfield_write.c b/tools/testing/selftests/bpf/progs/verifier_bitfield_write.c new file mode 100644 index 000000000000..623f130a3198 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_bitfield_write.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <stdint.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> + +#include "bpf_misc.h" + +struct core_reloc_bitfields { + /* unsigned bitfields */ + uint8_t ub1: 1; + uint8_t ub2: 2; + uint32_t ub7: 7; + /* signed bitfields */ + int8_t sb4: 4; + int32_t sb20: 20; + /* non-bitfields */ + uint32_t u32; + int32_t s32; +} __attribute__((preserve_access_index)); + +SEC("tc") +__description("single CO-RE bitfield roundtrip") +__btf_path("btf__core_reloc_bitfields.bpf.o") +__success +__retval(3) +int single_field_roundtrip(struct __sk_buff *ctx) +{ + struct core_reloc_bitfields bitfields; + + __builtin_memset(&bitfields, 0, sizeof(bitfields)); + BPF_CORE_WRITE_BITFIELD(&bitfields, ub2, 3); + return BPF_CORE_READ_BITFIELD(&bitfields, ub2); +} + +SEC("tc") +__description("multiple CO-RE bitfield roundtrip") +__btf_path("btf__core_reloc_bitfields.bpf.o") +__success +__retval(0x3FD) +int multiple_field_roundtrip(struct __sk_buff *ctx) +{ + struct core_reloc_bitfields bitfields; + uint8_t ub2; + int8_t sb4; + + __builtin_memset(&bitfields, 0, sizeof(bitfields)); + BPF_CORE_WRITE_BITFIELD(&bitfields, ub2, 1); + BPF_CORE_WRITE_BITFIELD(&bitfields, sb4, -1); + + ub2 = BPF_CORE_READ_BITFIELD(&bitfields, ub2); + sb4 = BPF_CORE_READ_BITFIELD(&bitfields, sb4); + + return (((uint8_t)sb4) << 2) | ub2; +} + +SEC("tc") +__description("adjacent CO-RE bitfield roundtrip") +__btf_path("btf__core_reloc_bitfields.bpf.o") +__success +__retval(7) +int adjacent_field_roundtrip(struct __sk_buff *ctx) +{ + struct core_reloc_bitfields bitfields; + uint8_t ub1, ub2; + + __builtin_memset(&bitfields, 0, sizeof(bitfields)); + BPF_CORE_WRITE_BITFIELD(&bitfields, ub1, 1); + BPF_CORE_WRITE_BITFIELD(&bitfields, ub2, 3); + + ub1 = BPF_CORE_READ_BITFIELD(&bitfields, ub1); + ub2 = BPF_CORE_READ_BITFIELD(&bitfields, ub2); + + return (ub2 << 1) | ub1; +} + +SEC("tc") +__description("multibyte CO-RE bitfield roundtrip") +__btf_path("btf__core_reloc_bitfields.bpf.o") +__success +__retval(0x21) +int multibyte_field_roundtrip(struct __sk_buff *ctx) +{ + struct core_reloc_bitfields bitfields; + uint32_t ub7; + uint8_t ub1; + + __builtin_memset(&bitfields, 0, sizeof(bitfields)); + BPF_CORE_WRITE_BITFIELD(&bitfields, ub1, 1); + BPF_CORE_WRITE_BITFIELD(&bitfields, ub7, 16); + + ub1 = BPF_CORE_READ_BITFIELD(&bitfields, ub1); + ub7 = BPF_CORE_READ_BITFIELD(&bitfields, ub7); + + return (ub7 << 1) | ub1; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_cgroup_inv_retcode.c b/tools/testing/selftests/bpf/progs/verifier_cgroup_inv_retcode.c index d6c4a7f3f790..6e0f349f8f15 100644 --- a/tools/testing/selftests/bpf/progs/verifier_cgroup_inv_retcode.c +++ b/tools/testing/selftests/bpf/progs/verifier_cgroup_inv_retcode.c @@ -7,7 +7,7 @@ SEC("cgroup/sock") __description("bpf_exit with invalid return code. test1") -__failure __msg("R0 has value (0x0; 0xffffffff)") +__failure __msg("smin=0 smax=4294967295 should have been in [0, 1]") __naked void with_invalid_return_code_test1(void) { asm volatile (" \ @@ -30,7 +30,7 @@ __naked void with_invalid_return_code_test2(void) SEC("cgroup/sock") __description("bpf_exit with invalid return code. test3") -__failure __msg("R0 has value (0x0; 0x3)") +__failure __msg("smin=0 smax=3 should have been in [0, 1]") __naked void with_invalid_return_code_test3(void) { asm volatile (" \ @@ -53,7 +53,7 @@ __naked void with_invalid_return_code_test4(void) SEC("cgroup/sock") __description("bpf_exit with invalid return code. test5") -__failure __msg("R0 has value (0x2; 0x0)") +__failure __msg("smin=2 smax=2 should have been in [0, 1]") __naked void with_invalid_return_code_test5(void) { asm volatile (" \ @@ -75,7 +75,7 @@ __naked void with_invalid_return_code_test6(void) SEC("cgroup/sock") __description("bpf_exit with invalid return code. test7") -__failure __msg("R0 has unknown scalar value") +__failure __msg("R0 has unknown scalar value should have been in [0, 1]") __naked void with_invalid_return_code_test7(void) { asm volatile (" \ diff --git a/tools/testing/selftests/bpf/progs/verifier_direct_packet_access.c b/tools/testing/selftests/bpf/progs/verifier_direct_packet_access.c index 99a23dea8233..be95570ab382 100644 --- a/tools/testing/selftests/bpf/progs/verifier_direct_packet_access.c +++ b/tools/testing/selftests/bpf/progs/verifier_direct_packet_access.c @@ -411,7 +411,7 @@ l0_%=: r0 = 0; \ SEC("tc") __description("direct packet access: test17 (pruning, alignment)") -__failure __msg("misaligned packet access off 2+(0x0; 0x0)+15+-4 size 4") +__failure __msg("misaligned packet access off 2+0+15+-4 size 4") __flag(BPF_F_STRICT_ALIGNMENT) __naked void packet_access_test17_pruning_alignment(void) { diff --git a/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c b/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c index a0a5efd1caa1..bd696a431244 100644 --- a/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c +++ b/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c @@ -10,6 +10,7 @@ int arr[1]; int unkn_idx; +const volatile bool call_dead_subprog = false; __noinline long global_bad(void) { @@ -31,23 +32,31 @@ __noinline long global_calls_good_only(void) return global_good(); } +__noinline long global_dead(void) +{ + return arr[0] * 2; +} + SEC("?raw_tp") __success __log_level(2) /* main prog is validated completely first */ __msg("('global_calls_good_only') is global and assumed valid.") -__msg("1: (95) exit") /* eventually global_good() is transitively validated as well */ __msg("Validating global_good() func") __msg("('global_good') is safe for any args that match its prototype") int chained_global_func_calls_success(void) { - return global_calls_good_only(); + int sum = 0; + + if (call_dead_subprog) + sum += global_dead(); + return global_calls_good_only() + sum; } SEC("?raw_tp") __failure __log_level(2) /* main prog validated successfully first */ -__msg("1: (95) exit") +__msg("('global_calls_bad') is global and assumed valid.") /* eventually we validate global_bad() and fail */ __msg("Validating global_bad() func") __msg("math between map_value pointer and register") /* BOOM */ diff --git a/tools/testing/selftests/bpf/progs/verifier_int_ptr.c b/tools/testing/selftests/bpf/progs/verifier_int_ptr.c index b054f9c48143..9fc3fae5cd83 100644 --- a/tools/testing/selftests/bpf/progs/verifier_int_ptr.c +++ b/tools/testing/selftests/bpf/progs/verifier_int_ptr.c @@ -5,9 +5,10 @@ #include <bpf/bpf_helpers.h> #include "bpf_misc.h" -SEC("cgroup/sysctl") +SEC("socket") __description("ARG_PTR_TO_LONG uninitialized") -__failure __msg("invalid indirect read from stack R4 off -16+0 size 8") +__success +__failure_unpriv __msg_unpriv("invalid indirect read from stack R4 off -16+0 size 8") __naked void arg_ptr_to_long_uninitialized(void) { asm volatile (" \ @@ -67,7 +68,7 @@ __naked void ptr_to_long_half_uninitialized(void) SEC("cgroup/sysctl") __description("ARG_PTR_TO_LONG misaligned") -__failure __msg("misaligned stack access off (0x0; 0x0)+-20+0 size 8") +__failure __msg("misaligned stack access off 0+-20+0 size 8") __naked void arg_ptr_to_long_misaligned(void) { asm volatile (" \ diff --git a/tools/testing/selftests/bpf/progs/verifier_netfilter_retcode.c b/tools/testing/selftests/bpf/progs/verifier_netfilter_retcode.c index 353ae6da00e1..e1ffa5d32ff0 100644 --- a/tools/testing/selftests/bpf/progs/verifier_netfilter_retcode.c +++ b/tools/testing/selftests/bpf/progs/verifier_netfilter_retcode.c @@ -39,7 +39,7 @@ __naked void with_valid_return_code_test3(void) SEC("netfilter") __description("bpf_exit with invalid return code. test4") -__failure __msg("R0 has value (0x2; 0x0)") +__failure __msg("R0 has smin=2 smax=2 should have been in [0, 1]") __naked void with_invalid_return_code_test4(void) { asm volatile (" \ diff --git a/tools/testing/selftests/bpf/progs/verifier_raw_stack.c b/tools/testing/selftests/bpf/progs/verifier_raw_stack.c index efbfc3a4ad6a..f67390224a9c 100644 --- a/tools/testing/selftests/bpf/progs/verifier_raw_stack.c +++ b/tools/testing/selftests/bpf/progs/verifier_raw_stack.c @@ -5,9 +5,10 @@ #include <bpf/bpf_helpers.h> #include "bpf_misc.h" -SEC("tc") +SEC("socket") __description("raw_stack: no skb_load_bytes") -__failure __msg("invalid read from stack R6 off=-8 size=8") +__success +__failure_unpriv __msg_unpriv("invalid read from stack R6 off=-8 size=8") __naked void stack_no_skb_load_bytes(void) { asm volatile (" \ diff --git a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c index 6115520154e3..39fe3372e0e0 100644 --- a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c +++ b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c @@ -4,6 +4,7 @@ #include <linux/bpf.h> #include <bpf/bpf_helpers.h> #include "bpf_misc.h" +#include <../../../tools/include/linux/filter.h> struct { __uint(type, BPF_MAP_TYPE_RINGBUF); @@ -450,4 +451,290 @@ l0_%=: r1 >>= 16; \ : __clobber_all); } +SEC("raw_tp") +__log_level(2) +__success +__msg("fp-8=0m??mmmm") +__msg("fp-16=00mm??mm") +__msg("fp-24=00mm???m") +__naked void spill_subregs_preserve_stack_zero(void) +{ + asm volatile ( + "call %[bpf_get_prandom_u32];" + + /* 32-bit subreg spill with ZERO, MISC, and INVALID */ + ".8byte %[fp1_u8_st_zero];" /* ZERO, LLVM-18+: *(u8 *)(r10 -1) = 0; */ + "*(u8 *)(r10 -2) = r0;" /* MISC */ + /* fp-3 and fp-4 stay INVALID */ + "*(u32 *)(r10 -8) = r0;" + + /* 16-bit subreg spill with ZERO, MISC, and INVALID */ + ".8byte %[fp10_u16_st_zero];" /* ZERO, LLVM-18+: *(u16 *)(r10 -10) = 0; */ + "*(u16 *)(r10 -12) = r0;" /* MISC */ + /* fp-13 and fp-14 stay INVALID */ + "*(u16 *)(r10 -16) = r0;" + + /* 8-bit subreg spill with ZERO, MISC, and INVALID */ + ".8byte %[fp18_u16_st_zero];" /* ZERO, LLVM-18+: *(u16 *)(r18 -10) = 0; */ + "*(u16 *)(r10 -20) = r0;" /* MISC */ + /* fp-21, fp-22, and fp-23 stay INVALID */ + "*(u8 *)(r10 -24) = r0;" + + "r0 = 0;" + "exit;" + : + : __imm(bpf_get_prandom_u32), + __imm_insn(fp1_u8_st_zero, BPF_ST_MEM(BPF_B, BPF_REG_FP, -1, 0)), + __imm_insn(fp10_u16_st_zero, BPF_ST_MEM(BPF_H, BPF_REG_FP, -10, 0)), + __imm_insn(fp18_u16_st_zero, BPF_ST_MEM(BPF_H, BPF_REG_FP, -18, 0)) + : __clobber_all); +} + +char single_byte_buf[1] SEC(".data.single_byte_buf"); + +SEC("raw_tp") +__log_level(2) +__success +/* make sure fp-8 is all STACK_ZERO */ +__msg("2: (7a) *(u64 *)(r10 -8) = 0 ; R10=fp0 fp-8_w=00000000") +/* but fp-16 is spilled IMPRECISE zero const reg */ +__msg("4: (7b) *(u64 *)(r10 -16) = r0 ; R0_w=0 R10=fp0 fp-16_w=0") +/* validate that assigning R2 from STACK_ZERO doesn't mark register + * precise immediately; if necessary, it will be marked precise later + */ +__msg("6: (71) r2 = *(u8 *)(r10 -1) ; R2_w=0 R10=fp0 fp-8_w=00000000") +/* similarly, when R2 is assigned from spilled register, it is initially + * imprecise, but will be marked precise later once it is used in precise context + */ +__msg("10: (71) r2 = *(u8 *)(r10 -9) ; R2_w=0 R10=fp0 fp-16_w=0") +__msg("11: (0f) r1 += r2") +__msg("mark_precise: frame0: last_idx 11 first_idx 0 subseq_idx -1") +__msg("mark_precise: frame0: regs=r2 stack= before 10: (71) r2 = *(u8 *)(r10 -9)") +__msg("mark_precise: frame0: regs= stack=-16 before 9: (bf) r1 = r6") +__msg("mark_precise: frame0: regs= stack=-16 before 8: (73) *(u8 *)(r1 +0) = r2") +__msg("mark_precise: frame0: regs= stack=-16 before 7: (0f) r1 += r2") +__msg("mark_precise: frame0: regs= stack=-16 before 6: (71) r2 = *(u8 *)(r10 -1)") +__msg("mark_precise: frame0: regs= stack=-16 before 5: (bf) r1 = r6") +__msg("mark_precise: frame0: regs= stack=-16 before 4: (7b) *(u64 *)(r10 -16) = r0") +__msg("mark_precise: frame0: regs=r0 stack= before 3: (b7) r0 = 0") +__naked void partial_stack_load_preserves_zeros(void) +{ + asm volatile ( + /* fp-8 is all STACK_ZERO */ + ".8byte %[fp8_st_zero];" /* LLVM-18+: *(u64 *)(r10 -8) = 0; */ + + /* fp-16 is const zero register */ + "r0 = 0;" + "*(u64 *)(r10 -16) = r0;" + + /* load single U8 from non-aligned STACK_ZERO slot */ + "r1 = %[single_byte_buf];" + "r2 = *(u8 *)(r10 -1);" + "r1 += r2;" + "*(u8 *)(r1 + 0) = r2;" /* this should be fine */ + + /* load single U8 from non-aligned ZERO REG slot */ + "r1 = %[single_byte_buf];" + "r2 = *(u8 *)(r10 -9);" + "r1 += r2;" + "*(u8 *)(r1 + 0) = r2;" /* this should be fine */ + + /* load single U16 from non-aligned STACK_ZERO slot */ + "r1 = %[single_byte_buf];" + "r2 = *(u16 *)(r10 -2);" + "r1 += r2;" + "*(u8 *)(r1 + 0) = r2;" /* this should be fine */ + + /* load single U16 from non-aligned ZERO REG slot */ + "r1 = %[single_byte_buf];" + "r2 = *(u16 *)(r10 -10);" + "r1 += r2;" + "*(u8 *)(r1 + 0) = r2;" /* this should be fine */ + + /* load single U32 from non-aligned STACK_ZERO slot */ + "r1 = %[single_byte_buf];" + "r2 = *(u32 *)(r10 -4);" + "r1 += r2;" + "*(u8 *)(r1 + 0) = r2;" /* this should be fine */ + + /* load single U32 from non-aligned ZERO REG slot */ + "r1 = %[single_byte_buf];" + "r2 = *(u32 *)(r10 -12);" + "r1 += r2;" + "*(u8 *)(r1 + 0) = r2;" /* this should be fine */ + + /* for completeness, load U64 from STACK_ZERO slot */ + "r1 = %[single_byte_buf];" + "r2 = *(u64 *)(r10 -8);" + "r1 += r2;" + "*(u8 *)(r1 + 0) = r2;" /* this should be fine */ + + /* for completeness, load U64 from ZERO REG slot */ + "r1 = %[single_byte_buf];" + "r2 = *(u64 *)(r10 -16);" + "r1 += r2;" + "*(u8 *)(r1 + 0) = r2;" /* this should be fine */ + + "r0 = 0;" + "exit;" + : + : __imm_ptr(single_byte_buf), + __imm_insn(fp8_st_zero, BPF_ST_MEM(BPF_DW, BPF_REG_FP, -8, 0)) + : __clobber_common); +} + +char two_byte_buf[2] SEC(".data.two_byte_buf"); + +SEC("raw_tp") +__log_level(2) __flag(BPF_F_TEST_STATE_FREQ) +__success +/* make sure fp-8 is IMPRECISE fake register spill */ +__msg("3: (7a) *(u64 *)(r10 -8) = 1 ; R10=fp0 fp-8_w=1") +/* and fp-16 is spilled IMPRECISE const reg */ +__msg("5: (7b) *(u64 *)(r10 -16) = r0 ; R0_w=1 R10=fp0 fp-16_w=1") +/* validate load from fp-8, which was initialized using BPF_ST_MEM */ +__msg("8: (79) r2 = *(u64 *)(r10 -8) ; R2_w=1 R10=fp0 fp-8=1") +__msg("9: (0f) r1 += r2") +__msg("mark_precise: frame0: last_idx 9 first_idx 7 subseq_idx -1") +__msg("mark_precise: frame0: regs=r2 stack= before 8: (79) r2 = *(u64 *)(r10 -8)") +__msg("mark_precise: frame0: regs= stack=-8 before 7: (bf) r1 = r6") +/* note, fp-8 is precise, fp-16 is not yet precise, we'll get there */ +__msg("mark_precise: frame0: parent state regs= stack=-8: R0_w=1 R1=ctx() R6_r=map_value(map=.data.two_byte_,ks=4,vs=2) R10=fp0 fp-8_rw=P1 fp-16_w=1") +__msg("mark_precise: frame0: last_idx 6 first_idx 3 subseq_idx 7") +__msg("mark_precise: frame0: regs= stack=-8 before 6: (05) goto pc+0") +__msg("mark_precise: frame0: regs= stack=-8 before 5: (7b) *(u64 *)(r10 -16) = r0") +__msg("mark_precise: frame0: regs= stack=-8 before 4: (b7) r0 = 1") +__msg("mark_precise: frame0: regs= stack=-8 before 3: (7a) *(u64 *)(r10 -8) = 1") +__msg("10: R1_w=map_value(map=.data.two_byte_,ks=4,vs=2,off=1) R2_w=1") +/* validate load from fp-16, which was initialized using BPF_STX_MEM */ +__msg("12: (79) r2 = *(u64 *)(r10 -16) ; R2_w=1 R10=fp0 fp-16=1") +__msg("13: (0f) r1 += r2") +__msg("mark_precise: frame0: last_idx 13 first_idx 7 subseq_idx -1") +__msg("mark_precise: frame0: regs=r2 stack= before 12: (79) r2 = *(u64 *)(r10 -16)") +__msg("mark_precise: frame0: regs= stack=-16 before 11: (bf) r1 = r6") +__msg("mark_precise: frame0: regs= stack=-16 before 10: (73) *(u8 *)(r1 +0) = r2") +__msg("mark_precise: frame0: regs= stack=-16 before 9: (0f) r1 += r2") +__msg("mark_precise: frame0: regs= stack=-16 before 8: (79) r2 = *(u64 *)(r10 -8)") +__msg("mark_precise: frame0: regs= stack=-16 before 7: (bf) r1 = r6") +/* now both fp-8 and fp-16 are precise, very good */ +__msg("mark_precise: frame0: parent state regs= stack=-16: R0_w=1 R1=ctx() R6_r=map_value(map=.data.two_byte_,ks=4,vs=2) R10=fp0 fp-8_rw=P1 fp-16_rw=P1") +__msg("mark_precise: frame0: last_idx 6 first_idx 3 subseq_idx 7") +__msg("mark_precise: frame0: regs= stack=-16 before 6: (05) goto pc+0") +__msg("mark_precise: frame0: regs= stack=-16 before 5: (7b) *(u64 *)(r10 -16) = r0") +__msg("mark_precise: frame0: regs=r0 stack= before 4: (b7) r0 = 1") +__msg("14: R1_w=map_value(map=.data.two_byte_,ks=4,vs=2,off=1) R2_w=1") +__naked void stack_load_preserves_const_precision(void) +{ + asm volatile ( + /* establish checkpoint with state that has no stack slots; + * if we bubble up to this state without finding desired stack + * slot, then it's a bug and should be caught + */ + "goto +0;" + + /* fp-8 is const 1 *fake* register */ + ".8byte %[fp8_st_one];" /* LLVM-18+: *(u64 *)(r10 -8) = 1; */ + + /* fp-16 is const 1 register */ + "r0 = 1;" + "*(u64 *)(r10 -16) = r0;" + + /* force checkpoint to check precision marks preserved in parent states */ + "goto +0;" + + /* load single U64 from aligned FAKE_REG=1 slot */ + "r1 = %[two_byte_buf];" + "r2 = *(u64 *)(r10 -8);" + "r1 += r2;" + "*(u8 *)(r1 + 0) = r2;" /* this should be fine */ + + /* load single U64 from aligned REG=1 slot */ + "r1 = %[two_byte_buf];" + "r2 = *(u64 *)(r10 -16);" + "r1 += r2;" + "*(u8 *)(r1 + 0) = r2;" /* this should be fine */ + + "r0 = 0;" + "exit;" + : + : __imm_ptr(two_byte_buf), + __imm_insn(fp8_st_one, BPF_ST_MEM(BPF_DW, BPF_REG_FP, -8, 1)) + : __clobber_common); +} + +SEC("raw_tp") +__log_level(2) __flag(BPF_F_TEST_STATE_FREQ) +__success +/* make sure fp-8 is 32-bit FAKE subregister spill */ +__msg("3: (62) *(u32 *)(r10 -8) = 1 ; R10=fp0 fp-8=????1") +/* but fp-16 is spilled IMPRECISE zero const reg */ +__msg("5: (63) *(u32 *)(r10 -16) = r0 ; R0_w=1 R10=fp0 fp-16=????1") +/* validate load from fp-8, which was initialized using BPF_ST_MEM */ +__msg("8: (61) r2 = *(u32 *)(r10 -8) ; R2_w=1 R10=fp0 fp-8=????1") +__msg("9: (0f) r1 += r2") +__msg("mark_precise: frame0: last_idx 9 first_idx 7 subseq_idx -1") +__msg("mark_precise: frame0: regs=r2 stack= before 8: (61) r2 = *(u32 *)(r10 -8)") +__msg("mark_precise: frame0: regs= stack=-8 before 7: (bf) r1 = r6") +__msg("mark_precise: frame0: parent state regs= stack=-8: R0_w=1 R1=ctx() R6_r=map_value(map=.data.two_byte_,ks=4,vs=2) R10=fp0 fp-8_r=????P1 fp-16=????1") +__msg("mark_precise: frame0: last_idx 6 first_idx 3 subseq_idx 7") +__msg("mark_precise: frame0: regs= stack=-8 before 6: (05) goto pc+0") +__msg("mark_precise: frame0: regs= stack=-8 before 5: (63) *(u32 *)(r10 -16) = r0") +__msg("mark_precise: frame0: regs= stack=-8 before 4: (b7) r0 = 1") +__msg("mark_precise: frame0: regs= stack=-8 before 3: (62) *(u32 *)(r10 -8) = 1") +__msg("10: R1_w=map_value(map=.data.two_byte_,ks=4,vs=2,off=1) R2_w=1") +/* validate load from fp-16, which was initialized using BPF_STX_MEM */ +__msg("12: (61) r2 = *(u32 *)(r10 -16) ; R2_w=1 R10=fp0 fp-16=????1") +__msg("13: (0f) r1 += r2") +__msg("mark_precise: frame0: last_idx 13 first_idx 7 subseq_idx -1") +__msg("mark_precise: frame0: regs=r2 stack= before 12: (61) r2 = *(u32 *)(r10 -16)") +__msg("mark_precise: frame0: regs= stack=-16 before 11: (bf) r1 = r6") +__msg("mark_precise: frame0: regs= stack=-16 before 10: (73) *(u8 *)(r1 +0) = r2") +__msg("mark_precise: frame0: regs= stack=-16 before 9: (0f) r1 += r2") +__msg("mark_precise: frame0: regs= stack=-16 before 8: (61) r2 = *(u32 *)(r10 -8)") +__msg("mark_precise: frame0: regs= stack=-16 before 7: (bf) r1 = r6") +__msg("mark_precise: frame0: parent state regs= stack=-16: R0_w=1 R1=ctx() R6_r=map_value(map=.data.two_byte_,ks=4,vs=2) R10=fp0 fp-8_r=????P1 fp-16_r=????P1") +__msg("mark_precise: frame0: last_idx 6 first_idx 3 subseq_idx 7") +__msg("mark_precise: frame0: regs= stack=-16 before 6: (05) goto pc+0") +__msg("mark_precise: frame0: regs= stack=-16 before 5: (63) *(u32 *)(r10 -16) = r0") +__msg("mark_precise: frame0: regs=r0 stack= before 4: (b7) r0 = 1") +__msg("14: R1_w=map_value(map=.data.two_byte_,ks=4,vs=2,off=1) R2_w=1") +__naked void stack_load_preserves_const_precision_subreg(void) +{ + asm volatile ( + /* establish checkpoint with state that has no stack slots; + * if we bubble up to this state without finding desired stack + * slot, then it's a bug and should be caught + */ + "goto +0;" + + /* fp-8 is const 1 *fake* SUB-register */ + ".8byte %[fp8_st_one];" /* LLVM-18+: *(u32 *)(r10 -8) = 1; */ + + /* fp-16 is const 1 SUB-register */ + "r0 = 1;" + "*(u32 *)(r10 -16) = r0;" + + /* force checkpoint to check precision marks preserved in parent states */ + "goto +0;" + + /* load single U32 from aligned FAKE_REG=1 slot */ + "r1 = %[two_byte_buf];" + "r2 = *(u32 *)(r10 -8);" + "r1 += r2;" + "*(u8 *)(r1 + 0) = r2;" /* this should be fine */ + + /* load single U32 from aligned REG=1 slot */ + "r1 = %[two_byte_buf];" + "r2 = *(u32 *)(r10 -16);" + "r1 += r2;" + "*(u8 *)(r1 + 0) = r2;" /* this should be fine */ + + "r0 = 0;" + "exit;" + : + : __imm_ptr(two_byte_buf), + __imm_insn(fp8_st_one, BPF_ST_MEM(BPF_W, BPF_REG_FP, -8, 1)) /* 32-bit spill */ + : __clobber_common); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_stack_ptr.c b/tools/testing/selftests/bpf/progs/verifier_stack_ptr.c index e0f77e3e7869..417c61cd4b19 100644 --- a/tools/testing/selftests/bpf/progs/verifier_stack_ptr.c +++ b/tools/testing/selftests/bpf/progs/verifier_stack_ptr.c @@ -37,7 +37,7 @@ __naked void ptr_to_stack_store_load(void) SEC("socket") __description("PTR_TO_STACK store/load - bad alignment on off") -__failure __msg("misaligned stack access off (0x0; 0x0)+-8+2 size 8") +__failure __msg("misaligned stack access off 0+-8+2 size 8") __failure_unpriv __naked void load_bad_alignment_on_off(void) { @@ -53,7 +53,7 @@ __naked void load_bad_alignment_on_off(void) SEC("socket") __description("PTR_TO_STACK store/load - bad alignment on reg") -__failure __msg("misaligned stack access off (0x0; 0x0)+-10+8 size 8") +__failure __msg("misaligned stack access off 0+-10+8 size 8") __failure_unpriv __naked void load_bad_alignment_on_reg(void) { diff --git a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c index b5efcaeaa1ae..6f5d19665cf6 100644 --- a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c +++ b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c @@ -117,6 +117,56 @@ __naked int global_subprog_result_precise(void) ); } +__naked __noinline __used +static unsigned long loop_callback_bad() +{ + /* bpf_loop() callback that can return values outside of [0, 1] range */ + asm volatile ( + "call %[bpf_get_prandom_u32];" + "if r0 s> 1000 goto 1f;" + "r0 = 0;" + "1:" + "goto +0;" /* checkpoint */ + /* bpf_loop() expects [0, 1] values, so branch above skipping + * r0 = 0; should lead to a failure, but if exit instruction + * doesn't enforce r0's precision, this callback will be + * successfully verified + */ + "exit;" + : + : __imm(bpf_get_prandom_u32) + : __clobber_common + ); +} + +SEC("?raw_tp") +__failure __log_level(2) +__flag(BPF_F_TEST_STATE_FREQ) +/* check that fallthrough code path marks r0 as precise */ +__msg("mark_precise: frame1: regs=r0 stack= before 11: (b7) r0 = 0") +/* check that we have branch code path doing its own validation */ +__msg("from 10 to 12: frame1: R0=scalar(smin=umin=1001") +/* check that branch code path marks r0 as precise, before failing */ +__msg("mark_precise: frame1: regs=r0 stack= before 9: (85) call bpf_get_prandom_u32#7") +__msg("At callback return the register R0 has smin=1001 should have been in [0, 1]") +__naked int callback_precise_return_fail(void) +{ + asm volatile ( + "r1 = 1;" /* nr_loops */ + "r2 = %[loop_callback_bad];" /* callback_fn */ + "r3 = 0;" /* callback_ctx */ + "r4 = 0;" /* flags */ + "call %[bpf_loop];" + + "r0 = 0;" + "exit;" + : + : __imm_ptr(loop_callback_bad), + __imm(bpf_loop) + : __clobber_common + ); +} + SEC("?raw_tp") __success __log_level(2) /* First simulated path does not include callback body, @@ -539,11 +589,24 @@ static __u64 subprog_spill_reg_precise(void) SEC("?raw_tp") __success __log_level(2) -/* precision backtracking can't currently handle stack access not through r10, - * so we won't be able to mark stack slot fp-8 as precise, and so will - * fallback to forcing all as precise - */ -__msg("mark_precise: frame0: falling back to forcing all scalars precise") +__msg("10: (0f) r1 += r7") +__msg("mark_precise: frame0: last_idx 10 first_idx 7 subseq_idx -1") +__msg("mark_precise: frame0: regs=r7 stack= before 9: (bf) r1 = r8") +__msg("mark_precise: frame0: regs=r7 stack= before 8: (27) r7 *= 4") +__msg("mark_precise: frame0: regs=r7 stack= before 7: (79) r7 = *(u64 *)(r10 -8)") +__msg("mark_precise: frame0: parent state regs= stack=-8: R0_w=2 R6_w=1 R8_rw=map_value(map=.data.vals,ks=4,vs=16) R10=fp0 fp-8_rw=P1") +__msg("mark_precise: frame0: last_idx 18 first_idx 0 subseq_idx 7") +__msg("mark_precise: frame0: regs= stack=-8 before 18: (95) exit") +__msg("mark_precise: frame1: regs= stack= before 17: (0f) r0 += r2") +__msg("mark_precise: frame1: regs= stack= before 16: (79) r2 = *(u64 *)(r1 +0)") +__msg("mark_precise: frame1: regs= stack= before 15: (79) r0 = *(u64 *)(r10 -16)") +__msg("mark_precise: frame1: regs= stack= before 14: (7b) *(u64 *)(r10 -16) = r2") +__msg("mark_precise: frame1: regs= stack= before 13: (7b) *(u64 *)(r1 +0) = r2") +__msg("mark_precise: frame1: regs=r2 stack= before 6: (85) call pc+6") +__msg("mark_precise: frame0: regs=r2 stack= before 5: (bf) r2 = r6") +__msg("mark_precise: frame0: regs=r6 stack= before 4: (07) r1 += -8") +__msg("mark_precise: frame0: regs=r6 stack= before 3: (bf) r1 = r10") +__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 1") __naked int subprog_spill_into_parent_stack_slot_precise(void) { asm volatile ( @@ -578,14 +641,68 @@ __naked int subprog_spill_into_parent_stack_slot_precise(void) ); } -__naked __noinline __used -static __u64 subprog_with_checkpoint(void) +SEC("?raw_tp") +__success __log_level(2) +__msg("17: (0f) r1 += r0") +__msg("mark_precise: frame0: last_idx 17 first_idx 0 subseq_idx -1") +__msg("mark_precise: frame0: regs=r0 stack= before 16: (bf) r1 = r7") +__msg("mark_precise: frame0: regs=r0 stack= before 15: (27) r0 *= 4") +__msg("mark_precise: frame0: regs=r0 stack= before 14: (79) r0 = *(u64 *)(r10 -16)") +__msg("mark_precise: frame0: regs= stack=-16 before 13: (7b) *(u64 *)(r7 -8) = r0") +__msg("mark_precise: frame0: regs=r0 stack= before 12: (79) r0 = *(u64 *)(r8 +16)") +__msg("mark_precise: frame0: regs= stack=-16 before 11: (7b) *(u64 *)(r8 +16) = r0") +__msg("mark_precise: frame0: regs=r0 stack= before 10: (79) r0 = *(u64 *)(r7 -8)") +__msg("mark_precise: frame0: regs= stack=-16 before 9: (7b) *(u64 *)(r10 -16) = r0") +__msg("mark_precise: frame0: regs=r0 stack= before 8: (07) r8 += -32") +__msg("mark_precise: frame0: regs=r0 stack= before 7: (bf) r8 = r10") +__msg("mark_precise: frame0: regs=r0 stack= before 6: (07) r7 += -8") +__msg("mark_precise: frame0: regs=r0 stack= before 5: (bf) r7 = r10") +__msg("mark_precise: frame0: regs=r0 stack= before 21: (95) exit") +__msg("mark_precise: frame1: regs=r0 stack= before 20: (bf) r0 = r1") +__msg("mark_precise: frame1: regs=r1 stack= before 4: (85) call pc+15") +__msg("mark_precise: frame0: regs=r1 stack= before 3: (bf) r1 = r6") +__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 1") +__naked int stack_slot_aliases_precision(void) { asm volatile ( - "r0 = 0;" - /* guaranteed checkpoint if BPF_F_TEST_STATE_FREQ is used */ - "goto +0;" + "r6 = 1;" + /* pass r6 through r1 into subprog to get it back as r0; + * this whole chain will have to be marked as precise later + */ + "r1 = r6;" + "call identity_subprog;" + /* let's setup two registers that are aliased to r10 */ + "r7 = r10;" + "r7 += -8;" /* r7 = r10 - 8 */ + "r8 = r10;" + "r8 += -32;" /* r8 = r10 - 32 */ + /* now spill subprog's return value (a r6 -> r1 -> r0 chain) + * a few times through different stack pointer regs, making + * sure to use r10, r7, and r8 both in LDX and STX insns, and + * *importantly* also using a combination of const var_off and + * insn->off to validate that we record final stack slot + * correctly, instead of relying on just insn->off derivation, + * which is only valid for r10-based stack offset + */ + "*(u64 *)(r10 - 16) = r0;" + "r0 = *(u64 *)(r7 - 8);" /* r7 - 8 == r10 - 16 */ + "*(u64 *)(r8 + 16) = r0;" /* r8 + 16 = r10 - 16 */ + "r0 = *(u64 *)(r8 + 16);" + "*(u64 *)(r7 - 8) = r0;" + "r0 = *(u64 *)(r10 - 16);" + /* get ready to use r0 as an index into array to force precision */ + "r0 *= 4;" + "r1 = %[vals];" + /* here r0->r1->r6 chain is forced to be precise and has to be + * propagated back to the beginning, including through the + * subprog call and all the stack spills and loads + */ + "r1 += r0;" + "r0 = *(u32 *)(r1 + 0);" "exit;" + : + : __imm_ptr(vals) + : __clobber_common, "r6" ); } diff --git a/tools/testing/selftests/bpf/progs/verifier_var_off.c b/tools/testing/selftests/bpf/progs/verifier_var_off.c index 83a90afba785..c810f4f6f479 100644 --- a/tools/testing/selftests/bpf/progs/verifier_var_off.c +++ b/tools/testing/selftests/bpf/progs/verifier_var_off.c @@ -59,9 +59,10 @@ __naked void stack_read_priv_vs_unpriv(void) " ::: __clobber_all); } -SEC("lwt_in") +SEC("cgroup/skb") __description("variable-offset stack read, uninitialized") -__failure __msg("invalid variable-offset read from stack R2") +__success +__failure_unpriv __msg_unpriv("R2 variable stack access prohibited for !root") __naked void variable_offset_stack_read_uninitialized(void) { asm volatile (" \ @@ -83,13 +84,56 @@ __naked void variable_offset_stack_read_uninitialized(void) SEC("socket") __description("variable-offset stack write, priv vs unpriv") -__success __failure_unpriv +__success +/* Check that the maximum stack depth is correctly maintained according to the + * maximum possible variable offset. + */ +__log_level(4) __msg("stack depth 16") +__failure_unpriv /* Variable stack access is rejected for unprivileged. */ __msg_unpriv("R2 variable stack access prohibited for !root") __retval(0) __naked void stack_write_priv_vs_unpriv(void) { + asm volatile (" \ + /* Get an unknown value */ \ + r2 = *(u32*)(r1 + 0); \ + /* Make it small and 8-byte aligned */ \ + r2 &= 8; \ + r2 -= 16; \ + /* Add it to fp. We now have either fp-8 or \ + * fp-16, but we don't know which \ + */ \ + r2 += r10; \ + /* Dereference it for a stack write */ \ + r0 = 0; \ + *(u64*)(r2 + 0) = r0; \ + exit; \ +" ::: __clobber_all); +} + +/* Similar to the previous test, but this time also perform a read from the + * address written to with a variable offset. The read is allowed, showing that, + * after a variable-offset write, a priviledged program can read the slots that + * were in the range of that write (even if the verifier doesn't actually know if + * the slot being read was really written to or not. + * + * Despite this test being mostly a superset, the previous test is also kept for + * the sake of it checking the stack depth in the case where there is no read. + */ +SEC("socket") +__description("variable-offset stack write followed by read") +__success +/* Check that the maximum stack depth is correctly maintained according to the + * maximum possible variable offset. + */ +__log_level(4) __msg("stack depth 16") +__failure_unpriv +__msg_unpriv("R2 variable stack access prohibited for !root") +__retval(0) +__naked void stack_write_followed_by_read(void) +{ asm volatile (" \ /* Get an unknown value */ \ r2 = *(u32*)(r1 + 0); \ @@ -103,12 +147,7 @@ __naked void stack_write_priv_vs_unpriv(void) /* Dereference it for a stack write */ \ r0 = 0; \ *(u64*)(r2 + 0) = r0; \ - /* Now read from the address we just wrote. This shows\ - * that, after a variable-offset write, a priviledged\ - * program can read the slots that were in the range of\ - * that write (even if the verifier doesn't actually know\ - * if the slot being read was really written to or not.\ - */ \ + /* Now read from the address we just wrote. */ \ r3 = *(u64*)(r2 + 0); \ r0 = 0; \ exit; \ @@ -224,6 +263,35 @@ __naked void access_max_out_of_bound(void) : __clobber_all); } +/* Similar to the test above, but this time check the special case of a + * zero-sized stack access. We used to have a bug causing crashes for zero-sized + * out-of-bounds accesses. + */ +SEC("socket") +__description("indirect variable-offset stack access, zero-sized, max out of bound") +__failure __msg("invalid variable-offset indirect access to stack R1") +__naked void zero_sized_access_max_out_of_bound(void) +{ + asm volatile (" \ + r0 = 0; \ + /* Fill some stack */ \ + *(u64*)(r10 - 16) = r0; \ + *(u64*)(r10 - 8) = r0; \ + /* Get an unknown value */ \ + r1 = *(u32*)(r1 + 0); \ + r1 &= 63; \ + r1 += -16; \ + /* r1 is now anywhere in [-16,48) */ \ + r1 += r10; \ + r2 = 0; \ + r3 = 0; \ + call %[bpf_probe_read_kernel]; \ + exit; \ +" : + : __imm(bpf_probe_read_kernel) + : __clobber_all); +} + SEC("lwt_in") __description("indirect variable-offset stack access, min out of bound") __failure __msg("invalid variable-offset indirect access to stack R2") @@ -253,9 +321,10 @@ __naked void access_min_out_of_bound(void) : __clobber_all); } -SEC("lwt_in") +SEC("cgroup/skb") __description("indirect variable-offset stack access, min_off < min_initialized") -__failure __msg("invalid indirect read from stack R2 var_off") +__success +__failure_unpriv __msg_unpriv("R2 variable stack access prohibited for !root") __naked void access_min_off_min_initialized(void) { asm volatile (" \ diff --git a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c index f6d1cc9ad892..330ece2eabdb 100644 --- a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c @@ -20,21 +20,32 @@ extern int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, __u64 *timestamp) __ksym; extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash, enum xdp_rss_hash_type *rss_type) __ksym; +extern int bpf_xdp_metadata_rx_vlan_tag(const struct xdp_md *ctx, + __be16 *vlan_proto, + __u16 *vlan_tci) __ksym; SEC("xdp.frags") int rx(struct xdp_md *ctx) { void *data, *data_meta, *data_end; struct ipv6hdr *ip6h = NULL; - struct ethhdr *eth = NULL; struct udphdr *udp = NULL; struct iphdr *iph = NULL; struct xdp_meta *meta; + struct ethhdr *eth; int err; data = (void *)(long)ctx->data; data_end = (void *)(long)ctx->data_end; eth = data; + + if (eth + 1 < data_end && (eth->h_proto == bpf_htons(ETH_P_8021AD) || + eth->h_proto == bpf_htons(ETH_P_8021Q))) + eth = (void *)eth + sizeof(struct vlan_hdr); + + if (eth + 1 < data_end && eth->h_proto == bpf_htons(ETH_P_8021Q)) + eth = (void *)eth + sizeof(struct vlan_hdr); + if (eth + 1 < data_end) { if (eth->h_proto == bpf_htons(ETH_P_IP)) { iph = (void *)(eth + 1); @@ -76,15 +87,28 @@ int rx(struct xdp_md *ctx) return XDP_PASS; } + meta->hint_valid = 0; + + meta->xdp_timestamp = bpf_ktime_get_tai_ns(); err = bpf_xdp_metadata_rx_timestamp(ctx, &meta->rx_timestamp); - if (!err) - meta->xdp_timestamp = bpf_ktime_get_tai_ns(); + if (err) + meta->rx_timestamp_err = err; else - meta->rx_timestamp = 0; /* Used by AF_XDP as not avail signal */ + meta->hint_valid |= XDP_META_FIELD_TS; - err = bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash, &meta->rx_hash_type); - if (err < 0) - meta->rx_hash_err = err; /* Used by AF_XDP as no hash signal */ + err = bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash, + &meta->rx_hash_type); + if (err) + meta->rx_hash_err = err; + else + meta->hint_valid |= XDP_META_FIELD_RSS; + + err = bpf_xdp_metadata_rx_vlan_tag(ctx, &meta->rx_vlan_proto, + &meta->rx_vlan_tci); + if (err) + meta->rx_vlan_tag_err = err; + else + meta->hint_valid |= XDP_META_FIELD_VLAN_TAG; __sync_add_and_fetch(&pkts_redir, 1); return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS); diff --git a/tools/testing/selftests/bpf/progs/xdp_metadata.c b/tools/testing/selftests/bpf/progs/xdp_metadata.c index d151d406a123..31ca229bb3c0 100644 --- a/tools/testing/selftests/bpf/progs/xdp_metadata.c +++ b/tools/testing/selftests/bpf/progs/xdp_metadata.c @@ -23,15 +23,47 @@ extern int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, __u64 *timestamp) __ksym; extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash, enum xdp_rss_hash_type *rss_type) __ksym; +extern int bpf_xdp_metadata_rx_vlan_tag(const struct xdp_md *ctx, + __be16 *vlan_proto, + __u16 *vlan_tci) __ksym; SEC("xdp") int rx(struct xdp_md *ctx) { - void *data, *data_meta; + void *data, *data_meta, *data_end; + struct ipv6hdr *ip6h = NULL; + struct ethhdr *eth = NULL; + struct udphdr *udp = NULL; + struct iphdr *iph = NULL; struct xdp_meta *meta; u64 timestamp = -1; int ret; + data = (void *)(long)ctx->data; + data_end = (void *)(long)ctx->data_end; + eth = data; + if (eth + 1 < data_end) { + if (eth->h_proto == bpf_htons(ETH_P_IP)) { + iph = (void *)(eth + 1); + if (iph + 1 < data_end && iph->protocol == IPPROTO_UDP) + udp = (void *)(iph + 1); + } + if (eth->h_proto == bpf_htons(ETH_P_IPV6)) { + ip6h = (void *)(eth + 1); + if (ip6h + 1 < data_end && ip6h->nexthdr == IPPROTO_UDP) + udp = (void *)(ip6h + 1); + } + if (udp && udp + 1 > data_end) + udp = NULL; + } + + if (!udp) + return XDP_PASS; + + /* Forwarding UDP:8080 to AF_XDP */ + if (udp->dest != bpf_htons(8080)) + return XDP_PASS; + /* Reserve enough for all custom metadata. */ ret = bpf_xdp_adjust_meta(ctx, -(int)sizeof(struct xdp_meta)); @@ -57,6 +89,8 @@ int rx(struct xdp_md *ctx) meta->rx_timestamp = 1; bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash, &meta->rx_hash_type); + bpf_xdp_metadata_rx_vlan_tag(ctx, &meta->rx_vlan_proto, + &meta->rx_vlan_tci); return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS); } diff --git a/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c index 80f620602d50..518329c666e9 100644 --- a/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c +++ b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c @@ -467,13 +467,13 @@ static __always_inline int tcp_lookup(void *ctx, struct header_pointers *hdr, bo unsigned long status = ct->status; bpf_ct_release(ct); - if (status & IPS_CONFIRMED_BIT) + if (status & IPS_CONFIRMED) return XDP_PASS; } else if (ct_lookup_opts.error != -ENOENT) { return XDP_ABORTED; } - /* error == -ENOENT || !(status & IPS_CONFIRMED_BIT) */ + /* error == -ENOENT || !(status & IPS_CONFIRMED) */ return XDP_TX; } diff --git a/tools/testing/selftests/bpf/test_loader.c b/tools/testing/selftests/bpf/test_loader.c index a350ecdfba4a..74ceb7877ae2 100644 --- a/tools/testing/selftests/bpf/test_loader.c +++ b/tools/testing/selftests/bpf/test_loader.c @@ -27,6 +27,7 @@ #define TEST_TAG_RETVAL_PFX_UNPRIV "comment:test_retval_unpriv=" #define TEST_TAG_AUXILIARY "comment:test_auxiliary" #define TEST_TAG_AUXILIARY_UNPRIV "comment:test_auxiliary_unpriv" +#define TEST_BTF_PATH "comment:test_btf_path=" /* Warning: duplicated in bpf_misc.h */ #define POINTER_VALUE 0xcafe4all @@ -58,6 +59,7 @@ struct test_spec { const char *prog_name; struct test_subspec priv; struct test_subspec unpriv; + const char *btf_custom_path; int log_level; int prog_flags; int mode_mask; @@ -288,6 +290,8 @@ static int parse_test_spec(struct test_loader *tester, goto cleanup; update_flags(&spec->prog_flags, flags, clear); } + } else if (str_has_pfx(s, TEST_BTF_PATH)) { + spec->btf_custom_path = s + sizeof(TEST_BTF_PATH) - 1; } } @@ -578,6 +582,9 @@ void run_subtest(struct test_loader *tester, } } + /* Implicitly reset to NULL if next test case doesn't specify */ + open_opts->btf_custom_path = spec->btf_custom_path; + tobj = bpf_object__open_mem(obj_bytes, obj_byte_cnt, open_opts); if (!ASSERT_OK_PTR(tobj, "obj_open_mem")) /* shouldn't happen */ goto subtest_cleanup; diff --git a/tools/testing/selftests/bpf/test_tunnel.sh b/tools/testing/selftests/bpf/test_tunnel.sh index 2dec7dbf29a2..d9661b9988ba 100755 --- a/tools/testing/selftests/bpf/test_tunnel.sh +++ b/tools/testing/selftests/bpf/test_tunnel.sh @@ -517,90 +517,6 @@ test_ip6ip6() echo -e ${GREEN}"PASS: ip6$TYPE"${NC} } -setup_xfrm_tunnel() -{ - auth=0x$(printf '1%.0s' {1..40}) - enc=0x$(printf '2%.0s' {1..32}) - spi_in_to_out=0x1 - spi_out_to_in=0x2 - # at_ns0 namespace - # at_ns0 -> root - ip netns exec at_ns0 \ - ip xfrm state add src 172.16.1.100 dst 172.16.1.200 proto esp \ - spi $spi_in_to_out reqid 1 mode tunnel \ - auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc - ip netns exec at_ns0 \ - ip xfrm policy add src 10.1.1.100/32 dst 10.1.1.200/32 dir out \ - tmpl src 172.16.1.100 dst 172.16.1.200 proto esp reqid 1 \ - mode tunnel - # root -> at_ns0 - ip netns exec at_ns0 \ - ip xfrm state add src 172.16.1.200 dst 172.16.1.100 proto esp \ - spi $spi_out_to_in reqid 2 mode tunnel \ - auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc - ip netns exec at_ns0 \ - ip xfrm policy add src 10.1.1.200/32 dst 10.1.1.100/32 dir in \ - tmpl src 172.16.1.200 dst 172.16.1.100 proto esp reqid 2 \ - mode tunnel - # address & route - ip netns exec at_ns0 \ - ip addr add dev veth0 10.1.1.100/32 - ip netns exec at_ns0 \ - ip route add 10.1.1.200 dev veth0 via 172.16.1.200 \ - src 10.1.1.100 - - # root namespace - # at_ns0 -> root - ip xfrm state add src 172.16.1.100 dst 172.16.1.200 proto esp \ - spi $spi_in_to_out reqid 1 mode tunnel \ - auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc - ip xfrm policy add src 10.1.1.100/32 dst 10.1.1.200/32 dir in \ - tmpl src 172.16.1.100 dst 172.16.1.200 proto esp reqid 1 \ - mode tunnel - # root -> at_ns0 - ip xfrm state add src 172.16.1.200 dst 172.16.1.100 proto esp \ - spi $spi_out_to_in reqid 2 mode tunnel \ - auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc - ip xfrm policy add src 10.1.1.200/32 dst 10.1.1.100/32 dir out \ - tmpl src 172.16.1.200 dst 172.16.1.100 proto esp reqid 2 \ - mode tunnel - # address & route - ip addr add dev veth1 10.1.1.200/32 - ip route add 10.1.1.100 dev veth1 via 172.16.1.100 src 10.1.1.200 -} - -test_xfrm_tunnel() -{ - if [[ -e /sys/kernel/tracing/trace ]]; then - TRACE=/sys/kernel/tracing/trace - else - TRACE=/sys/kernel/debug/tracing/trace - fi - config_device - > ${TRACE} - setup_xfrm_tunnel - mkdir -p ${BPF_PIN_TUNNEL_DIR} - bpftool prog loadall ${BPF_FILE} ${BPF_PIN_TUNNEL_DIR} - tc qdisc add dev veth1 clsact - tc filter add dev veth1 proto ip ingress bpf da object-pinned \ - ${BPF_PIN_TUNNEL_DIR}/xfrm_get_state - ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 - sleep 1 - grep "reqid 1" ${TRACE} - check_err $? - grep "spi 0x1" ${TRACE} - check_err $? - grep "remote ip 0xac100164" ${TRACE} - check_err $? - cleanup - - if [ $ret -ne 0 ]; then - echo -e ${RED}"FAIL: xfrm tunnel"${NC} - return 1 - fi - echo -e ${GREEN}"PASS: xfrm tunnel"${NC} -} - attach_bpf() { DEV=$1 @@ -630,10 +546,6 @@ cleanup() ip link del ip6geneve11 2> /dev/null ip link del erspan11 2> /dev/null ip link del ip6erspan11 2> /dev/null - ip xfrm policy delete dir out src 10.1.1.200/32 dst 10.1.1.100/32 2> /dev/null - ip xfrm policy delete dir in src 10.1.1.100/32 dst 10.1.1.200/32 2> /dev/null - ip xfrm state delete src 172.16.1.100 dst 172.16.1.200 proto esp spi 0x1 2> /dev/null - ip xfrm state delete src 172.16.1.200 dst 172.16.1.100 proto esp spi 0x2 2> /dev/null } cleanup_exit() @@ -716,10 +628,6 @@ bpf_tunnel_test() test_ip6ip6 errors=$(( $errors + $? )) - echo "Testing IPSec tunnel..." - test_xfrm_tunnel - errors=$(( $errors + $? )) - return $errors } diff --git a/tools/testing/selftests/bpf/testing_helpers.h b/tools/testing/selftests/bpf/testing_helpers.h index 5b7a55136741..35284faff4f2 100644 --- a/tools/testing/selftests/bpf/testing_helpers.h +++ b/tools/testing/selftests/bpf/testing_helpers.h @@ -9,6 +9,9 @@ #include <bpf/libbpf.h> #include <time.h> +#define __TO_STR(x) #x +#define TO_STR(x) __TO_STR(x) + int parse_num_list(const char *s, bool **set, int *set_len); __u32 link_info_prog_id(const struct bpf_link *link, struct bpf_link_info *info); int bpf_prog_test_load(const char *file, enum bpf_prog_type type, diff --git a/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c b/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c index 319337bdcfc8..9a7b1106fda8 100644 --- a/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c +++ b/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c @@ -84,17 +84,6 @@ .errstr = "!read_ok", }, { - "Can't use cmpxchg on uninit memory", - .insns = { - BPF_MOV64_IMM(BPF_REG_0, 3), - BPF_MOV64_IMM(BPF_REG_2, 4), - BPF_ATOMIC_OP(BPF_DW, BPF_CMPXCHG, BPF_REG_10, BPF_REG_2, -8), - BPF_EXIT_INSN(), - }, - .result = REJECT, - .errstr = "invalid read from stack", -}, -{ "BPF_W cmpxchg should zero top 32 bits", .insns = { /* r0 = U64_MAX; */ diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c index 3d5cd51071f0..ab25a81fd3a1 100644 --- a/tools/testing/selftests/bpf/verifier/calls.c +++ b/tools/testing/selftests/bpf/verifier/calls.c @@ -1505,7 +1505,9 @@ .prog_type = BPF_PROG_TYPE_XDP, .fixup_map_hash_8b = { 23 }, .result = REJECT, - .errstr = "invalid read from stack R7 off=-16 size=8", + .errstr = "R0 invalid mem access 'scalar'", + .result_unpriv = REJECT, + .errstr_unpriv = "invalid read from stack R7 off=-16 size=8", }, { "calls: two calls that receive map_value via arg=ptr_stack_of_caller. test1", diff --git a/tools/testing/selftests/bpf/verifier/precise.c b/tools/testing/selftests/bpf/verifier/precise.c index 0d84dd1f38b6..8a2ff81d8350 100644 --- a/tools/testing/selftests/bpf/verifier/precise.c +++ b/tools/testing/selftests/bpf/verifier/precise.c @@ -140,10 +140,11 @@ .result = REJECT, }, { - "precise: ST insn causing spi > allocated_stack", + "precise: ST zero to stack insn is supported", .insns = { BPF_MOV64_REG(BPF_REG_3, BPF_REG_10), BPF_JMP_IMM(BPF_JNE, BPF_REG_3, 123, 0), + /* not a register spill, so we stop precision propagation for R4 here */ BPF_ST_MEM(BPF_DW, BPF_REG_3, -8, 0), BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8), BPF_MOV64_IMM(BPF_REG_0, -1), @@ -157,11 +158,11 @@ mark_precise: frame0: last_idx 4 first_idx 2\ mark_precise: frame0: regs=r4 stack= before 4\ mark_precise: frame0: regs=r4 stack= before 3\ - mark_precise: frame0: regs= stack=-8 before 2\ - mark_precise: frame0: falling back to forcing all scalars precise\ - force_precise: frame0: forcing r0 to be precise\ mark_precise: frame0: last_idx 5 first_idx 5\ - mark_precise: frame0: parent state regs= stack=:", + mark_precise: frame0: parent state regs=r0 stack=:\ + mark_precise: frame0: last_idx 4 first_idx 2\ + mark_precise: frame0: regs=r0 stack= before 4\ + 5: R0=-1 R4=0", .result = VERBOSE_ACCEPT, .retval = -1, }, @@ -169,6 +170,8 @@ "precise: STX insn causing spi > allocated_stack", .insns = { BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32), + /* make later reg spill more interesting by having somewhat known scalar */ + BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 0xff), BPF_MOV64_REG(BPF_REG_3, BPF_REG_10), BPF_JMP_IMM(BPF_JNE, BPF_REG_3, 123, 0), BPF_STX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, -8), @@ -179,18 +182,21 @@ }, .prog_type = BPF_PROG_TYPE_XDP, .flags = BPF_F_TEST_STATE_FREQ, - .errstr = "mark_precise: frame0: last_idx 6 first_idx 6\ + .errstr = "mark_precise: frame0: last_idx 7 first_idx 7\ mark_precise: frame0: parent state regs=r4 stack=:\ - mark_precise: frame0: last_idx 5 first_idx 3\ - mark_precise: frame0: regs=r4 stack= before 5\ - mark_precise: frame0: regs=r4 stack= before 4\ - mark_precise: frame0: regs= stack=-8 before 3\ - mark_precise: frame0: falling back to forcing all scalars precise\ - force_precise: frame0: forcing r0 to be precise\ - force_precise: frame0: forcing r0 to be precise\ - force_precise: frame0: forcing r0 to be precise\ - force_precise: frame0: forcing r0 to be precise\ - mark_precise: frame0: last_idx 6 first_idx 6\ + mark_precise: frame0: last_idx 6 first_idx 4\ + mark_precise: frame0: regs=r4 stack= before 6: (b7) r0 = -1\ + mark_precise: frame0: regs=r4 stack= before 5: (79) r4 = *(u64 *)(r10 -8)\ + mark_precise: frame0: regs= stack=-8 before 4: (7b) *(u64 *)(r3 -8) = r0\ + mark_precise: frame0: parent state regs=r0 stack=:\ + mark_precise: frame0: last_idx 3 first_idx 3\ + mark_precise: frame0: regs=r0 stack= before 3: (55) if r3 != 0x7b goto pc+0\ + mark_precise: frame0: regs=r0 stack= before 2: (bf) r3 = r10\ + mark_precise: frame0: regs=r0 stack= before 1: (57) r0 &= 255\ + mark_precise: frame0: parent state regs=r0 stack=:\ + mark_precise: frame0: last_idx 0 first_idx 0\ + mark_precise: frame0: regs=r0 stack= before 0: (85) call bpf_get_prandom_u32#7\ + mark_precise: frame0: last_idx 7 first_idx 7\ mark_precise: frame0: parent state regs= stack=:", .result = VERBOSE_ACCEPT, .retval = -1, diff --git a/tools/testing/selftests/bpf/verify_sig_setup.sh b/tools/testing/selftests/bpf/verify_sig_setup.sh index ba08922b4a27..f2cac42298ba 100755 --- a/tools/testing/selftests/bpf/verify_sig_setup.sh +++ b/tools/testing/selftests/bpf/verify_sig_setup.sh @@ -60,6 +60,27 @@ cleanup() { rm -rf ${tmp_dir} } +fsverity_create_sign_file() { + local tmp_dir="$1" + + data_file=${tmp_dir}/data-file + sig_file=${tmp_dir}/sig-file + dd if=/dev/urandom of=$data_file bs=1 count=12345 2> /dev/null + fsverity sign --key ${tmp_dir}/signing_key.pem $data_file $sig_file + + # We do not want to enable fsverity on $data_file yet. Try whether + # the file system support fsverity on a different file. + touch ${tmp_dir}/tmp-file + fsverity enable ${tmp_dir}/tmp-file +} + +fsverity_enable_file() { + local tmp_dir="$1" + + data_file=${tmp_dir}/data-file + fsverity enable $data_file +} + catch() { local exit_code="$1" @@ -86,6 +107,10 @@ main() setup "${tmp_dir}" elif [[ "${action}" == "cleanup" ]]; then cleanup "${tmp_dir}" + elif [[ "${action}" == "fsverity-create-sign" ]]; then + fsverity_create_sign_file "${tmp_dir}" + elif [[ "${action}" == "fsverity-enable" ]]; then + fsverity_enable_file "${tmp_dir}" else echo "Unknown action: ${action}" exit 1 diff --git a/tools/testing/selftests/bpf/veristat.c b/tools/testing/selftests/bpf/veristat.c index 1d418d66e375..244d4996e06e 100644 --- a/tools/testing/selftests/bpf/veristat.c +++ b/tools/testing/selftests/bpf/veristat.c @@ -1254,7 +1254,7 @@ static int cmp_join_stat(const struct verif_stats_join *s1, bool asc, bool abs) { const char *str1 = NULL, *str2 = NULL; - double v1, v2; + double v1 = 0.0, v2 = 0.0; int cmp = 0; fetch_join_stat_value(s1, id, var, &str1, &v1); diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c index 3291625ba4fb..878d68db0325 100644 --- a/tools/testing/selftests/bpf/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c @@ -21,6 +21,9 @@ #include "xsk.h" #include <error.h> +#include <linux/kernel.h> +#include <linux/bits.h> +#include <linux/bitfield.h> #include <linux/errqueue.h> #include <linux/if_link.h> #include <linux/net_tstamp.h> @@ -79,7 +82,7 @@ static int open_xsk(int ifindex, struct xsk *xsk, __u32 queue_id) .flags = XSK_UMEM__DEFAULT_FLAGS, .tx_metadata_len = sizeof(struct xsk_tx_metadata), }; - __u32 idx; + __u32 idx = 0; u64 addr; int ret; int i; @@ -182,19 +185,31 @@ static void print_tstamp_delta(const char *name, const char *refname, (double)delta / 1000); } +#define VLAN_PRIO_MASK GENMASK(15, 13) /* Priority Code Point */ +#define VLAN_DEI_MASK GENMASK(12, 12) /* Drop Eligible Indicator */ +#define VLAN_VID_MASK GENMASK(11, 0) /* VLAN Identifier */ +static void print_vlan_tci(__u16 tag) +{ + __u16 vlan_id = FIELD_GET(VLAN_VID_MASK, tag); + __u8 pcp = FIELD_GET(VLAN_PRIO_MASK, tag); + bool dei = FIELD_GET(VLAN_DEI_MASK, tag); + + printf("PCP=%u, DEI=%d, VID=0x%X\n", pcp, dei, vlan_id); +} + static void verify_xdp_metadata(void *data, clockid_t clock_id) { struct xdp_meta *meta; meta = data - sizeof(*meta); - if (meta->rx_hash_err < 0) - printf("No rx_hash err=%d\n", meta->rx_hash_err); - else + if (meta->hint_valid & XDP_META_FIELD_RSS) printf("rx_hash: 0x%X with RSS type:0x%X\n", meta->rx_hash, meta->rx_hash_type); + else + printf("No rx_hash, err=%d\n", meta->rx_hash_err); - if (meta->rx_timestamp) { + if (meta->hint_valid & XDP_META_FIELD_TS) { __u64 ref_tstamp = gettime(clock_id); /* store received timestamps to calculate a delta at tx */ @@ -206,7 +221,16 @@ static void verify_xdp_metadata(void *data, clockid_t clock_id) print_tstamp_delta("XDP RX-time", "User RX-time", meta->xdp_timestamp, ref_tstamp); } else { - printf("No rx_timestamp\n"); + printf("No rx_timestamp, err=%d\n", meta->rx_timestamp_err); + } + + if (meta->hint_valid & XDP_META_FIELD_VLAN_TAG) { + printf("rx_vlan_proto: 0x%X\n", ntohs(meta->rx_vlan_proto)); + printf("rx_vlan_tci: "); + print_vlan_tci(meta->rx_vlan_tci); + } else { + printf("No rx_vlan_tci or rx_vlan_proto, err=%d\n", + meta->rx_vlan_tag_err); } } diff --git a/tools/testing/selftests/bpf/xdp_metadata.h b/tools/testing/selftests/bpf/xdp_metadata.h index 938a729bd307..87318ad1117a 100644 --- a/tools/testing/selftests/bpf/xdp_metadata.h +++ b/tools/testing/selftests/bpf/xdp_metadata.h @@ -9,12 +9,44 @@ #define ETH_P_IPV6 0x86DD #endif +#ifndef ETH_P_8021Q +#define ETH_P_8021Q 0x8100 +#endif + +#ifndef ETH_P_8021AD +#define ETH_P_8021AD 0x88A8 +#endif + +#ifndef BIT +#define BIT(nr) (1 << (nr)) +#endif + +/* Non-existent checksum status */ +#define XDP_CHECKSUM_MAGIC BIT(2) + +enum xdp_meta_field { + XDP_META_FIELD_TS = BIT(0), + XDP_META_FIELD_RSS = BIT(1), + XDP_META_FIELD_VLAN_TAG = BIT(2), +}; + struct xdp_meta { - __u64 rx_timestamp; + union { + __u64 rx_timestamp; + __s32 rx_timestamp_err; + }; __u64 xdp_timestamp; __u32 rx_hash; union { __u32 rx_hash_type; __s32 rx_hash_err; }; + union { + struct { + __be16 rx_vlan_proto; + __u16 rx_vlan_tci; + }; + __s32 rx_vlan_tag_err; + }; + enum xdp_meta_field hint_valid; }; diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c index b604c570309a..b1102ee13faa 100644 --- a/tools/testing/selftests/bpf/xskxceiver.c +++ b/tools/testing/selftests/bpf/xskxceiver.c @@ -634,16 +634,24 @@ static u32 pkt_nb_frags(u32 frame_size, struct pkt_stream *pkt_stream, struct pk return nb_frags; } +static bool set_pkt_valid(int offset, u32 len) +{ + return len <= MAX_ETH_JUMBO_SIZE; +} + static void pkt_set(struct pkt_stream *pkt_stream, struct pkt *pkt, int offset, u32 len) { pkt->offset = offset; pkt->len = len; - if (len > MAX_ETH_JUMBO_SIZE) { - pkt->valid = false; - } else { - pkt->valid = true; - pkt_stream->nb_valid_entries++; - } + pkt->valid = set_pkt_valid(offset, len); +} + +static void pkt_stream_pkt_set(struct pkt_stream *pkt_stream, struct pkt *pkt, int offset, u32 len) +{ + bool prev_pkt_valid = pkt->valid; + + pkt_set(pkt_stream, pkt, offset, len); + pkt_stream->nb_valid_entries += pkt->valid - prev_pkt_valid; } static u32 pkt_get_buffer_len(struct xsk_umem_info *umem, u32 len) @@ -665,7 +673,7 @@ static struct pkt_stream *__pkt_stream_generate(u32 nb_pkts, u32 pkt_len, u32 nb for (i = 0; i < nb_pkts; i++) { struct pkt *pkt = &pkt_stream->pkts[i]; - pkt_set(pkt_stream, pkt, 0, pkt_len); + pkt_stream_pkt_set(pkt_stream, pkt, 0, pkt_len); pkt->pkt_nb = nb_start + i * nb_off; } @@ -700,10 +708,9 @@ static void __pkt_stream_replace_half(struct ifobject *ifobj, u32 pkt_len, pkt_stream = pkt_stream_clone(ifobj->xsk->pkt_stream); for (i = 1; i < ifobj->xsk->pkt_stream->nb_pkts; i += 2) - pkt_set(pkt_stream, &pkt_stream->pkts[i], offset, pkt_len); + pkt_stream_pkt_set(pkt_stream, &pkt_stream->pkts[i], offset, pkt_len); ifobj->xsk->pkt_stream = pkt_stream; - pkt_stream->nb_valid_entries /= 2; } static void pkt_stream_replace_half(struct test_spec *test, u32 pkt_len, int offset) |