diff --git a/.mailmap b/.mailmap index 16b704e1d5d3..9f41b3906b66 100644 --- a/.mailmap +++ b/.mailmap @@ -512,6 +512,7 @@ Praveen BP Pradeep Kumar Chitrapu Prasad Sodagudi Punit Agrawal +Puranjay Mohan Qais Yousef Qais Yousef Quentin Monnet diff --git a/MAINTAINERS b/MAINTAINERS index 62b1a16b791b..aff81a252865 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -553,7 +553,7 @@ F: Documentation/devicetree/bindings/iio/accel/adi,adxl345.yaml F: drivers/input/misc/adxl34x.c ADXL355 THREE-AXIS DIGITAL ACCELEROMETER DRIVER -M: Puranjay Mohan +M: Puranjay Mohan L: linux-iio@vger.kernel.org S: Supported F: Documentation/devicetree/bindings/iio/accel/adi,adxl355.yaml @@ -3714,7 +3714,7 @@ F: drivers/iio/imu/bmi323/ BPF JIT for ARM M: Russell King -M: Puranjay Mohan +M: Puranjay Mohan L: bpf@vger.kernel.org S: Maintained F: arch/arm/net/ @@ -3764,6 +3764,8 @@ X: arch/riscv/net/bpf_jit_comp64.c BPF JIT for RISC-V (64-bit) M: Björn Töpel +R: Pu Lehui +R: Puranjay Mohan L: bpf@vger.kernel.org S: Maintained F: arch/riscv/net/ @@ -21925,7 +21927,7 @@ F: include/linux/soc/ti/ti_sci_inta_msi.h F: include/linux/soc/ti/ti_sci_protocol.h TEXAS INSTRUMENTS' TMP117 TEMPERATURE SENSOR DRIVER -M: Puranjay Mohan +M: Puranjay Mohan L: linux-iio@vger.kernel.org S: Supported F: Documentation/devicetree/bindings/iio/temperature/ti,tmp117.yaml diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index 1d672457d02f..72b5cd697f5d 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -871,16 +871,11 @@ static inline void emit_a32_alu_r64(const bool is64, const s8 dst[], } /* dst = src (4 bytes)*/ -static inline void emit_a32_mov_r(const s8 dst, const s8 src, const u8 off, - struct jit_ctx *ctx) { +static inline void emit_a32_mov_r(const s8 dst, const s8 src, struct jit_ctx *ctx) { const s8 *tmp = bpf2a32[TMP_REG_1]; s8 rt; rt = arm_bpf_get_reg32(src, tmp[0], ctx); - if (off && off != 32) { - emit(ARM_LSL_I(rt, rt, 32 - off), ctx); - emit(ARM_ASR_I(rt, rt, 32 - off), ctx); - } arm_bpf_put_reg32(dst, rt, ctx); } @@ -889,15 +884,15 @@ static inline void emit_a32_mov_r64(const bool is64, const s8 dst[], const s8 src[], struct jit_ctx *ctx) { if (!is64) { - emit_a32_mov_r(dst_lo, src_lo, 0, ctx); + emit_a32_mov_r(dst_lo, src_lo, ctx); if (!ctx->prog->aux->verifier_zext) /* Zero out high 4 bytes */ emit_a32_mov_i(dst_hi, 0, ctx); } else if (__LINUX_ARM_ARCH__ < 6 && ctx->cpu_architecture < CPU_ARCH_ARMv5TE) { /* complete 8 byte move */ - emit_a32_mov_r(dst_lo, src_lo, 0, ctx); - emit_a32_mov_r(dst_hi, src_hi, 0, ctx); + emit_a32_mov_r(dst_lo, src_lo, ctx); + emit_a32_mov_r(dst_hi, src_hi, ctx); } else if (is_stacked(src_lo) && is_stacked(dst_lo)) { const u8 *tmp = bpf2a32[TMP_REG_1]; @@ -917,17 +912,52 @@ static inline void emit_a32_mov_r64(const bool is64, const s8 dst[], static inline void emit_a32_movsx_r64(const bool is64, const u8 off, const s8 dst[], const s8 src[], struct jit_ctx *ctx) { const s8 *tmp = bpf2a32[TMP_REG_1]; - const s8 *rt; + s8 rs; + s8 rd; - rt = arm_bpf_get_reg64(dst, tmp, ctx); + if (is_stacked(dst_lo)) + rd = tmp[1]; + else + rd = dst_lo; + rs = arm_bpf_get_reg32(src_lo, rd, ctx); + /* rs may be one of src[1], dst[1], or tmp[1] */ + + /* Sign extend rs if needed. If off == 32, lower 32-bits of src are moved to dst and sign + * extension only happens in the upper 64 bits. + */ + if (off != 32) { + /* Sign extend rs into rd */ + emit(ARM_LSL_I(rd, rs, 32 - off), ctx); + emit(ARM_ASR_I(rd, rd, 32 - off), ctx); + } else { + rd = rs; + } + + /* Write rd to dst_lo + * + * Optimization: + * Assume: + * 1. dst == src and stacked. + * 2. off == 32 + * + * In this case src_lo was loaded into rd(tmp[1]) but rd was not sign extended as off==32. + * So, we don't need to write rd back to dst_lo as they have the same value. + * This saves us one str instruction. + */ + if (dst_lo != src_lo || off != 32) + arm_bpf_put_reg32(dst_lo, rd, ctx); - emit_a32_mov_r(dst_lo, src_lo, off, ctx); if (!is64) { if (!ctx->prog->aux->verifier_zext) /* Zero out high 4 bytes */ emit_a32_mov_i(dst_hi, 0, ctx); } else { - emit(ARM_ASR_I(rt[0], rt[1], 31), ctx); + if (is_stacked(dst_hi)) { + emit(ARM_ASR_I(tmp[0], rd, 31), ctx); + arm_bpf_put_reg32(dst_hi, tmp[0], ctx); + } else { + emit(ARM_ASR_I(dst_hi, rd, 31), ctx); + } } } diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 122021f9bdfc..13eac43c632d 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -1844,15 +1844,15 @@ static void invoke_bpf_prog(struct jit_ctx *ctx, struct bpf_tramp_link *l, emit_call(enter_prog, ctx); + /* save return value to callee saved register x20 */ + emit(A64_MOV(1, A64_R(20), A64_R(0)), ctx); + /* if (__bpf_prog_enter(prog) == 0) * goto skip_exec_of_prog; */ branch = ctx->image + ctx->idx; emit(A64_NOP, ctx); - /* save return value to callee saved register x20 */ - emit(A64_MOV(1, A64_R(20), A64_R(0)), ctx); - emit(A64_ADD_I(1, A64_R(0), A64_SP, args_off), ctx); if (!p->jited) emit_addr_mov_i64(A64_R(1), (const u64)p->insnsi, ctx); diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index 1adf2f39ce59..ec9d692838fc 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -722,6 +722,9 @@ static int invoke_bpf_prog(struct bpf_tramp_link *l, int args_off, int retval_of if (ret) return ret; + /* store prog start time */ + emit_mv(RV_REG_S1, RV_REG_A0, ctx); + /* if (__bpf_prog_enter(prog) == 0) * goto skip_exec_of_prog; */ @@ -729,9 +732,6 @@ static int invoke_bpf_prog(struct bpf_tramp_link *l, int args_off, int retval_of /* nop reserved for conditional jump */ emit(rv_nop(), ctx); - /* store prog start time */ - emit_mv(RV_REG_S1, RV_REG_A0, ctx); - /* arg1: &args_off */ emit_addi(RV_REG_A0, RV_REG_FP, -args_off, ctx); if (!p->jited) diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index df5fac428408..59cbc94b6e69 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1807,36 +1807,41 @@ populate_extable: if (BPF_MODE(insn->code) == BPF_PROBE_MEM || BPF_MODE(insn->code) == BPF_PROBE_MEMSX) { /* Conservatively check that src_reg + insn->off is a kernel address: - * src_reg + insn->off >= TASK_SIZE_MAX + PAGE_SIZE - * src_reg is used as scratch for src_reg += insn->off and restored - * after emit_ldx if necessary + * src_reg + insn->off > TASK_SIZE_MAX + PAGE_SIZE + * and + * src_reg + insn->off < VSYSCALL_ADDR */ - u64 limit = TASK_SIZE_MAX + PAGE_SIZE; + u64 limit = TASK_SIZE_MAX + PAGE_SIZE - VSYSCALL_ADDR; u8 *end_of_jmp; - /* At end of these emitted checks, insn->off will have been added - * to src_reg, so no need to do relative load with insn->off offset - */ - insn_off = 0; + /* movabsq r10, VSYSCALL_ADDR */ + emit_mov_imm64(&prog, BPF_REG_AX, (long)VSYSCALL_ADDR >> 32, + (u32)(long)VSYSCALL_ADDR); - /* movabsq r11, limit */ - EMIT2(add_1mod(0x48, AUX_REG), add_1reg(0xB8, AUX_REG)); - EMIT((u32)limit, 4); - EMIT(limit >> 32, 4); + /* mov src_reg, r11 */ + EMIT_mov(AUX_REG, src_reg); if (insn->off) { - /* add src_reg, insn->off */ - maybe_emit_1mod(&prog, src_reg, true); - EMIT2_off32(0x81, add_1reg(0xC0, src_reg), insn->off); + /* add r11, insn->off */ + maybe_emit_1mod(&prog, AUX_REG, true); + EMIT2_off32(0x81, add_1reg(0xC0, AUX_REG), insn->off); } - /* cmp src_reg, r11 */ - maybe_emit_mod(&prog, src_reg, AUX_REG, true); - EMIT2(0x39, add_2reg(0xC0, src_reg, AUX_REG)); + /* sub r11, r10 */ + maybe_emit_mod(&prog, AUX_REG, BPF_REG_AX, true); + EMIT2(0x29, add_2reg(0xC0, AUX_REG, BPF_REG_AX)); - /* if unsigned '>=', goto load */ - EMIT2(X86_JAE, 0); + /* movabsq r10, limit */ + emit_mov_imm64(&prog, BPF_REG_AX, (long)limit >> 32, + (u32)(long)limit); + + /* cmp r10, r11 */ + maybe_emit_mod(&prog, AUX_REG, BPF_REG_AX, true); + EMIT2(0x39, add_2reg(0xC0, AUX_REG, BPF_REG_AX)); + + /* if unsigned '>', goto load */ + EMIT2(X86_JA, 0); end_of_jmp = prog; /* xor dst_reg, dst_reg */ @@ -1862,18 +1867,6 @@ populate_extable: /* populate jmp_offset for JMP above */ start_of_ldx[-1] = prog - start_of_ldx; - if (insn->off && src_reg != dst_reg) { - /* sub src_reg, insn->off - * Restore src_reg after "add src_reg, insn->off" in prev - * if statement. But if src_reg == dst_reg, emit_ldx - * above already clobbered src_reg, so no need to restore. - * If add src_reg, insn->off was unnecessary, no need to - * restore either. - */ - maybe_emit_1mod(&prog, src_reg, true); - EMIT2_off32(0x81, add_1reg(0xE8, src_reg), insn->off); - } - if (!bpf_prog->aux->extable) break; @@ -3473,3 +3466,9 @@ bool bpf_jit_supports_ptr_xchg(void) { return true; } + +/* x86-64 JIT emits its own code to filter user addresses so return 0 here */ +u64 bpf_arch_uaddress_limit(void) +{ + return 0; +} diff --git a/include/linux/filter.h b/include/linux/filter.h index c99bc3df2d28..219ee7a76874 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -963,6 +963,7 @@ bool bpf_jit_supports_far_kfunc_call(void); bool bpf_jit_supports_exceptions(void); bool bpf_jit_supports_ptr_xchg(void); bool bpf_jit_supports_arena(void); +u64 bpf_arch_uaddress_limit(void); void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie); bool bpf_helper_changes_pkt_data(void *func); diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index e65ec3fd2799..a509caf823d6 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -461,10 +461,12 @@ static inline void sk_psock_put(struct sock *sk, struct sk_psock *psock) static inline void sk_psock_data_ready(struct sock *sk, struct sk_psock *psock) { + read_lock_bh(&sk->sk_callback_lock); if (psock->saved_data_ready) psock->saved_data_ready(sk); else sk->sk_data_ready(sk); + read_unlock_bh(&sk->sk_callback_lock); } static inline void psock_set_prog(struct bpf_prog **pprog, diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 696bc55de8e8..1ea5ce5bb599 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2942,6 +2942,15 @@ bool __weak bpf_jit_supports_arena(void) return false; } +u64 __weak bpf_arch_uaddress_limit(void) +{ +#if defined(CONFIG_64BIT) && defined(CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE) + return TASK_SIZE; +#else + return 0; +#endif +} + /* Return TRUE if the JIT backend satisfies the following two conditions: * 1) JIT backend supports atomic_xchg() on pointer-sized words. * 2) Under the specific arch, the implementation of xchg() is the same diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 98188379d5c7..cb7ad1f795e1 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -18289,8 +18289,7 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) f = fdget(fd); map = __bpf_map_get(f); if (IS_ERR(map)) { - verbose(env, "fd %d is not pointing to valid bpf_map\n", - insn[0].imm); + verbose(env, "fd %d is not pointing to valid bpf_map\n", fd); return PTR_ERR(map); } @@ -19676,6 +19675,36 @@ static int do_misc_fixups(struct bpf_verifier_env *env) goto next_insn; } + /* Make it impossible to de-reference a userspace address */ + if (BPF_CLASS(insn->code) == BPF_LDX && + (BPF_MODE(insn->code) == BPF_PROBE_MEM || + BPF_MODE(insn->code) == BPF_PROBE_MEMSX)) { + struct bpf_insn *patch = &insn_buf[0]; + u64 uaddress_limit = bpf_arch_uaddress_limit(); + + if (!uaddress_limit) + goto next_insn; + + *patch++ = BPF_MOV64_REG(BPF_REG_AX, insn->src_reg); + if (insn->off) + *patch++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_AX, insn->off); + *patch++ = BPF_ALU64_IMM(BPF_RSH, BPF_REG_AX, 32); + *patch++ = BPF_JMP_IMM(BPF_JLE, BPF_REG_AX, uaddress_limit >> 32, 2); + *patch++ = *insn; + *patch++ = BPF_JMP_IMM(BPF_JA, 0, 0, 1); + *patch++ = BPF_MOV64_IMM(insn->dst_reg, 0); + + cnt = patch - insn_buf; + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + goto next_insn; + } + /* Implement LD_ABS and LD_IND with a rewrite, if supported by the program type. */ if (BPF_CLASS(insn->code) == BPF_LD && (BPF_MODE(insn->code) == BPF_ABS || diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index c63a5fbf1f1c..291185f54ee4 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -375,7 +375,7 @@ config DEBUG_INFO_SPLIT Incompatible with older versions of ccache. config DEBUG_INFO_BTF - bool "Generate BTF typeinfo" + bool "Generate BTF type information" depends on !DEBUG_INFO_SPLIT && !DEBUG_INFO_REDUCED depends on !GCC_PLUGIN_RANDSTRUCT || COMPILE_TEST depends on BPF_SYSCALL @@ -408,7 +408,8 @@ config PAHOLE_HAS_LANG_EXCLUDE using DEBUG_INFO_BTF_MODULES. config DEBUG_INFO_BTF_MODULES - def_bool y + bool "Generate BTF type information for kernel modules" + default y depends on DEBUG_INFO_BTF && MODULES && PAHOLE_HAS_SPLIT_BTF help Generate compact split BTF type information for kernel modules. diff --git a/net/core/filter.c b/net/core/filter.c index 8adf95765cdd..ae5254f712c9 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4360,10 +4360,12 @@ static __always_inline int __xdp_do_redirect_frame(struct bpf_redirect_info *ri, enum bpf_map_type map_type = ri->map_type; void *fwd = ri->tgt_value; u32 map_id = ri->map_id; + u32 flags = ri->flags; struct bpf_map *map; int err; ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */ + ri->flags = 0; ri->map_type = BPF_MAP_TYPE_UNSPEC; if (unlikely(!xdpf)) { @@ -4375,11 +4377,20 @@ static __always_inline int __xdp_do_redirect_frame(struct bpf_redirect_info *ri, case BPF_MAP_TYPE_DEVMAP: fallthrough; case BPF_MAP_TYPE_DEVMAP_HASH: - map = READ_ONCE(ri->map); - if (unlikely(map)) { + if (unlikely(flags & BPF_F_BROADCAST)) { + map = READ_ONCE(ri->map); + + /* The map pointer is cleared when the map is being torn + * down by bpf_clear_redirect_map() + */ + if (unlikely(!map)) { + err = -ENOENT; + break; + } + WRITE_ONCE(ri->map, NULL); err = dev_map_enqueue_multi(xdpf, dev, map, - ri->flags & BPF_F_EXCLUDE_INGRESS); + flags & BPF_F_EXCLUDE_INGRESS); } else { err = dev_map_enqueue(fwd, xdpf, dev); } @@ -4442,9 +4453,9 @@ EXPORT_SYMBOL_GPL(xdp_do_redirect_frame); static int xdp_do_generic_redirect_map(struct net_device *dev, struct sk_buff *skb, struct xdp_buff *xdp, - struct bpf_prog *xdp_prog, - void *fwd, - enum bpf_map_type map_type, u32 map_id) + struct bpf_prog *xdp_prog, void *fwd, + enum bpf_map_type map_type, u32 map_id, + u32 flags) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); struct bpf_map *map; @@ -4454,11 +4465,20 @@ static int xdp_do_generic_redirect_map(struct net_device *dev, case BPF_MAP_TYPE_DEVMAP: fallthrough; case BPF_MAP_TYPE_DEVMAP_HASH: - map = READ_ONCE(ri->map); - if (unlikely(map)) { + if (unlikely(flags & BPF_F_BROADCAST)) { + map = READ_ONCE(ri->map); + + /* The map pointer is cleared when the map is being torn + * down by bpf_clear_redirect_map() + */ + if (unlikely(!map)) { + err = -ENOENT; + break; + } + WRITE_ONCE(ri->map, NULL); err = dev_map_redirect_multi(dev, skb, xdp_prog, map, - ri->flags & BPF_F_EXCLUDE_INGRESS); + flags & BPF_F_EXCLUDE_INGRESS); } else { err = dev_map_generic_redirect(fwd, skb, xdp_prog); } @@ -4495,9 +4515,11 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, enum bpf_map_type map_type = ri->map_type; void *fwd = ri->tgt_value; u32 map_id = ri->map_id; + u32 flags = ri->flags; int err; ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */ + ri->flags = 0; ri->map_type = BPF_MAP_TYPE_UNSPEC; if (map_type == BPF_MAP_TYPE_UNSPEC && map_id == INT_MAX) { @@ -4517,7 +4539,7 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, return 0; } - return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog, fwd, map_type, map_id); + return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog, fwd, map_type, map_id, flags); err: _trace_xdp_redirect_err(dev, xdp_prog, ri->tgt_index, err); return err; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 4d75ef9d24bf..fd20aae30be2 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -1226,11 +1226,8 @@ static void sk_psock_verdict_data_ready(struct sock *sk) rcu_read_lock(); psock = sk_psock(sk); - if (psock) { - read_lock_bh(&sk->sk_callback_lock); + if (psock) sk_psock_data_ready(sk, psock); - read_unlock_bh(&sk->sk_callback_lock); - } rcu_read_unlock(); } } diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index 39ad96a18123..edcd26106557 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -205,6 +205,9 @@ __weak noinline struct file *bpf_testmod_return_ptr(int arg) case 5: return (void *)~(1ull << 30); /* trigger extable */ case 6: return &f; /* valid addr */ case 7: return (void *)((long)&f | 1); /* kernel tricks */ +#ifdef CONFIG_X86_64 + case 8: return (void *)VSYSCALL_ADDR; /* vsyscall page address */ +#endif default: return NULL; } }