From 61f3c964dfd287b05d7ac6660a4f4ddfef84786c Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 17 Jan 2018 16:52:02 -0800 Subject: bpf: allow socket_filter programs to use bpf_prog_test_run in order to improve test coverage allow socket_filter program type to be run via bpf_prog_test_run command. Since such programs can be loaded by non-root tighten permissions for bpf_prog_test_run to be root only to avoid surprises. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- net/core/filter.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/core') diff --git a/net/core/filter.c b/net/core/filter.c index db2ee8c7e1bd..30fafaaa90fa 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4526,6 +4526,7 @@ const struct bpf_verifier_ops sk_filter_verifier_ops = { }; const struct bpf_prog_ops sk_filter_prog_ops = { + .test_run = bpf_prog_test_run_skb, }; const struct bpf_verifier_ops tc_cls_act_verifier_ops = { -- cgit 1.4.1 From 205c380778d09291668da5267057a80385f89437 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 20 Jan 2018 01:24:30 +0100 Subject: bpf: add csum_diff helper to xdp as well Useful for porting cls_bpf programs w/o increasing program complexity limits much at the same time, so add the helper to XDP as well. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: Alexei Starovoitov --- net/core/filter.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net/core') diff --git a/net/core/filter.c b/net/core/filter.c index 30fafaaa90fa..e5178851536f 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3456,6 +3456,8 @@ xdp_func_proto(enum bpf_func_id func_id) return &bpf_xdp_event_output_proto; case BPF_FUNC_get_smp_processor_id: return &bpf_get_smp_processor_id_proto; + case BPF_FUNC_csum_diff: + return &bpf_csum_diff_proto; case BPF_FUNC_xdp_adjust_head: return &bpf_xdp_adjust_head_proto; case BPF_FUNC_xdp_adjust_meta: -- cgit 1.4.1 From fa9dd599b4dae841924b022768354cfde9affecb Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 20 Jan 2018 01:24:33 +0100 Subject: bpf: get rid of pure_initcall dependency to enable jits Having a pure_initcall() callback just to permanently enable BPF JITs under CONFIG_BPF_JIT_ALWAYS_ON is unnecessary and could leave a small race window in future where JIT is still disabled on boot. Since we know about the setting at compilation time anyway, just initialize it properly there. Also consolidate all the individual bpf_jit_enable variables into a single one and move them under one location. Moreover, don't allow for setting unspecified garbage values on them. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: Alexei Starovoitov --- arch/arm/net/bpf_jit_32.c | 2 -- arch/arm64/net/bpf_jit_comp.c | 2 -- arch/mips/net/bpf_jit.c | 2 -- arch/mips/net/ebpf_jit.c | 2 -- arch/powerpc/net/bpf_jit_comp.c | 2 -- arch/powerpc/net/bpf_jit_comp64.c | 2 -- arch/s390/net/bpf_jit_comp.c | 2 -- arch/sparc/net/bpf_jit_comp_32.c | 2 -- arch/sparc/net/bpf_jit_comp_64.c | 2 -- arch/x86/net/bpf_jit_comp.c | 2 -- kernel/bpf/core.c | 19 ++++++++++++------- net/core/sysctl_net_core.c | 18 ++++++++++++------ net/socket.c | 9 --------- 13 files changed, 24 insertions(+), 42 deletions(-) (limited to 'net/core') diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index 4425189bb24c..a15e7cdf8754 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -25,8 +25,6 @@ #include "bpf_jit_32.h" -int bpf_jit_enable __read_mostly; - #define STACK_OFFSET(k) (k) #define TMP_REG_1 (MAX_BPF_JIT_REG + 0) /* TEMP Register 1 */ #define TMP_REG_2 (MAX_BPF_JIT_REG + 1) /* TEMP Register 2 */ diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index acaa935ed977..8d456ee6dddc 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -31,8 +31,6 @@ #include "bpf_jit.h" -int bpf_jit_enable __read_mostly; - #define TMP_REG_1 (MAX_BPF_JIT_REG + 0) #define TMP_REG_2 (MAX_BPF_JIT_REG + 1) #define TCALL_CNT (MAX_BPF_JIT_REG + 2) diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c index 44b925005dd3..4d8cb9bb8365 100644 --- a/arch/mips/net/bpf_jit.c +++ b/arch/mips/net/bpf_jit.c @@ -1207,8 +1207,6 @@ jmp_cmp: return 0; } -int bpf_jit_enable __read_mostly; - void bpf_jit_compile(struct bpf_prog *fp) { struct jit_ctx ctx; diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c index 97069a1b6f43..4e347030ed2c 100644 --- a/arch/mips/net/ebpf_jit.c +++ b/arch/mips/net/ebpf_jit.c @@ -177,8 +177,6 @@ static u32 b_imm(unsigned int tgt, struct jit_ctx *ctx) (ctx->idx * 4) - 4; } -int bpf_jit_enable __read_mostly; - enum which_ebpf_reg { src_reg, src_reg_no_fp, diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index f9941b3b5770..872d1f6dd11e 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -18,8 +18,6 @@ #include "bpf_jit32.h" -int bpf_jit_enable __read_mostly; - static inline void bpf_flush_icache(void *start, void *end) { smp_wmb(); diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 6771c63b2bec..217a78e84865 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -21,8 +21,6 @@ #include "bpf_jit64.h" -int bpf_jit_enable __read_mostly; - static void bpf_jit_fill_ill_insns(void *area, unsigned int size) { memset32(area, BREAKPOINT_INSTRUCTION, size/4); diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 1dfadbd126f3..e50188773ff3 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -28,8 +28,6 @@ #include #include "bpf_jit.h" -int bpf_jit_enable __read_mostly; - struct bpf_jit { u32 seen; /* Flags to remember seen eBPF instructions */ u32 seen_reg[16]; /* Array to remember which registers are used */ diff --git a/arch/sparc/net/bpf_jit_comp_32.c b/arch/sparc/net/bpf_jit_comp_32.c index 09e318eb34ee..3bd8ca95e521 100644 --- a/arch/sparc/net/bpf_jit_comp_32.c +++ b/arch/sparc/net/bpf_jit_comp_32.c @@ -11,8 +11,6 @@ #include "bpf_jit_32.h" -int bpf_jit_enable __read_mostly; - static inline bool is_simm13(unsigned int value) { return value + 0x1000 < 0x2000; diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c index 635fdefd4ae2..50a24d7bd4c5 100644 --- a/arch/sparc/net/bpf_jit_comp_64.c +++ b/arch/sparc/net/bpf_jit_comp_64.c @@ -12,8 +12,6 @@ #include "bpf_jit_64.h" -int bpf_jit_enable __read_mostly; - static inline bool is_simm13(unsigned int value) { return value + 0x1000 < 0x2000; diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 87f214fbe66e..b881a979efe1 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -15,8 +15,6 @@ #include #include -int bpf_jit_enable __read_mostly; - /* * assembly code in arch/x86/net/bpf_jit.S */ diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 25e723b0dfd4..bc9c5b11d6a9 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -300,6 +300,11 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, } #ifdef CONFIG_BPF_JIT +/* All BPF JIT sysctl knobs here. */ +int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_ALWAYS_ON); +int bpf_jit_harden __read_mostly; +int bpf_jit_kallsyms __read_mostly; + static __always_inline void bpf_get_prog_addr_region(const struct bpf_prog *prog, unsigned long *symbol_start, @@ -381,8 +386,6 @@ static DEFINE_SPINLOCK(bpf_lock); static LIST_HEAD(bpf_kallsyms); static struct latch_tree_root bpf_tree __cacheline_aligned; -int bpf_jit_kallsyms __read_mostly; - static void bpf_prog_ksym_node_add(struct bpf_prog_aux *aux) { WARN_ON_ONCE(!list_empty(&aux->ksym_lnode)); @@ -563,8 +566,6 @@ void __weak bpf_jit_free(struct bpf_prog *fp) bpf_prog_unlock_free(fp); } -int bpf_jit_harden __read_mostly; - static int bpf_jit_blind_insn(const struct bpf_insn *from, const struct bpf_insn *aux, struct bpf_insn *to_buff) @@ -1379,9 +1380,13 @@ void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth) } #else -static unsigned int __bpf_prog_ret0(const void *ctx, - const struct bpf_insn *insn) +static unsigned int __bpf_prog_ret0_warn(const void *ctx, + const struct bpf_insn *insn) { + /* If this handler ever gets executed, then BPF_JIT_ALWAYS_ON + * is not working properly, so warn about it! + */ + WARN_ON_ONCE(1); return 0; } #endif @@ -1441,7 +1446,7 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) fp->bpf_func = interpreters[(round_up(stack_depth, 32) / 32) - 1]; #else - fp->bpf_func = __bpf_prog_ret0; + fp->bpf_func = __bpf_prog_ret0_warn; #endif /* eBPF JITs can rewrite the program in case constant diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index a47ad6cd41c0..6d39b4c01fc6 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -25,6 +25,7 @@ static int zero = 0; static int one = 1; +static int two __maybe_unused = 2; static int min_sndbuf = SOCK_MIN_SNDBUF; static int min_rcvbuf = SOCK_MIN_RCVBUF; static int max_skb_frags = MAX_SKB_FRAGS; @@ -325,13 +326,14 @@ static struct ctl_table net_core_table[] = { .data = &bpf_jit_enable, .maxlen = sizeof(int), .mode = 0644, -#ifndef CONFIG_BPF_JIT_ALWAYS_ON - .proc_handler = proc_dointvec -#else .proc_handler = proc_dointvec_minmax, +# ifdef CONFIG_BPF_JIT_ALWAYS_ON .extra1 = &one, .extra2 = &one, -#endif +# else + .extra1 = &zero, + .extra2 = &two, +# endif }, # ifdef CONFIG_HAVE_EBPF_JIT { @@ -339,14 +341,18 @@ static struct ctl_table net_core_table[] = { .data = &bpf_jit_harden, .maxlen = sizeof(int), .mode = 0600, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &two, }, { .procname = "bpf_jit_kallsyms", .data = &bpf_jit_kallsyms, .maxlen = sizeof(int), .mode = 0600, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, }, # endif #endif diff --git a/net/socket.c b/net/socket.c index fbfae1ed3ff5..1536515b6437 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2613,15 +2613,6 @@ out_fs: core_initcall(sock_init); /* early initcall */ -static int __init jit_init(void) -{ -#ifdef CONFIG_BPF_JIT_ALWAYS_ON - bpf_jit_enable = 1; -#endif - return 0; -} -pure_initcall(jit_init); - #ifdef CONFIG_PROC_FS void socket_seq_show(struct seq_file *seq) { -- cgit 1.4.1 From 2e4a30983b0f9b19b59e38bbf7427d7fdd480d98 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 20 Jan 2018 01:24:34 +0100 Subject: bpf: restrict access to core bpf sysctls Given BPF reaches far beyond just networking these days, it was never intended to allow setting and in some cases reading those knobs out of a user namespace root running without CAP_SYS_ADMIN, thus tighten such access. Also the bpf_jit_enable = 2 debugging mode should only be allowed if kptr_restrict is not set since it otherwise can leak addresses to the kernel log. Dump a note to the kernel log that this is for debugging JITs only when enabled. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: Alexei Starovoitov --- net/core/sysctl_net_core.c | 46 +++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 43 insertions(+), 3 deletions(-) (limited to 'net/core') diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 6d39b4c01fc6..f2d0462611c3 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -251,6 +251,46 @@ static int proc_do_rss_key(struct ctl_table *table, int write, return proc_dostring(&fake_table, write, buffer, lenp, ppos); } +#ifdef CONFIG_BPF_JIT +static int proc_dointvec_minmax_bpf_enable(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int ret, jit_enable = *(int *)table->data; + struct ctl_table tmp = *table; + + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + tmp.data = &jit_enable; + ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); + if (write && !ret) { + if (jit_enable < 2 || + (jit_enable == 2 && bpf_dump_raw_ok())) { + *(int *)table->data = jit_enable; + if (jit_enable == 2) + pr_warn("bpf_jit_enable = 2 was set! NEVER use this in production, only for JIT debugging!\n"); + } else { + ret = -EPERM; + } + } + return ret; +} + +# ifdef CONFIG_HAVE_EBPF_JIT +static int +proc_dointvec_minmax_bpf_restricted(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + return proc_dointvec_minmax(table, write, buffer, lenp, ppos); +} +# endif +#endif + static struct ctl_table net_core_table[] = { #ifdef CONFIG_NET { @@ -326,7 +366,7 @@ static struct ctl_table net_core_table[] = { .data = &bpf_jit_enable, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_dointvec_minmax_bpf_enable, # ifdef CONFIG_BPF_JIT_ALWAYS_ON .extra1 = &one, .extra2 = &one, @@ -341,7 +381,7 @@ static struct ctl_table net_core_table[] = { .data = &bpf_jit_harden, .maxlen = sizeof(int), .mode = 0600, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_dointvec_minmax_bpf_restricted, .extra1 = &zero, .extra2 = &two, }, @@ -350,7 +390,7 @@ static struct ctl_table net_core_table[] = { .data = &bpf_jit_kallsyms, .maxlen = sizeof(int), .mode = 0600, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_dointvec_minmax_bpf_restricted, .extra1 = &zero, .extra2 = &one, }, -- cgit 1.4.1 From 1728a4f2ad6840746a6b1b9f01d652c5842f7e8d Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 20 Jan 2018 01:24:37 +0100 Subject: bpf: move event_output to const_size_or_zero for xdp/skb as well Similar rationale as in a60dd35d2e39 ("bpf: change bpf_perf_event_output arg5 type to ARG_CONST_SIZE_OR_ZERO"), change the type to CONST_SIZE_OR_ZERO such that we can better deal with optimized code. No changes needed in bpf_event_output() as it can also deal with 0 size entirely (e.g. as only wake-up signal with empty frame in perf RB, or packet dumps w/o meta data as another such possibility). Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: Alexei Starovoitov --- net/core/filter.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/core') diff --git a/net/core/filter.c b/net/core/filter.c index e5178851536f..9b9b70dee208 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2861,7 +2861,7 @@ static const struct bpf_func_proto bpf_skb_event_output_proto = { .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM, - .arg5_type = ARG_CONST_SIZE, + .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; static unsigned short bpf_tunnel_key_af(u64 flags) @@ -3150,7 +3150,7 @@ static const struct bpf_func_proto bpf_xdp_event_output_proto = { .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM, - .arg5_type = ARG_CONST_SIZE, + .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; BPF_CALL_1(bpf_get_socket_cookie, struct sk_buff *, skb) -- cgit 1.4.1