From ca36960211eb228bcbc7aaebfa0d027368a94c60 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 23 Feb 2018 22:29:05 +0100 Subject: [PATCH 1/4] bpf: allow xadd only on aligned memory The requirements around atomic_add() / atomic64_add() resp. their JIT implementations differ across architectures. E.g. while x86_64 seems just fine with BPF's xadd on unaligned memory, on arm64 it triggers via interpreter but also JIT the following crash: [ 830.864985] Unable to handle kernel paging request at virtual address ffff8097d7ed6703 [...] [ 830.916161] Internal error: Oops: 96000021 [#1] SMP [ 830.984755] CPU: 37 PID: 2788 Comm: test_verifier Not tainted 4.16.0-rc2+ #8 [ 830.991790] Hardware name: Huawei TaiShan 2280 /BC11SPCD, BIOS 1.29 07/17/2017 [ 830.998998] pstate: 80400005 (Nzcv daif +PAN -UAO) [ 831.003793] pc : __ll_sc_atomic_add+0x4/0x18 [ 831.008055] lr : ___bpf_prog_run+0x1198/0x1588 [ 831.012485] sp : ffff00001ccabc20 [ 831.015786] x29: ffff00001ccabc20 x28: ffff8017d56a0f00 [ 831.021087] x27: 0000000000000001 x26: 0000000000000000 [ 831.026387] x25: 000000c168d9db98 x24: 0000000000000000 [ 831.031686] x23: ffff000008203878 x22: ffff000009488000 [ 831.036986] x21: ffff000008b14e28 x20: ffff00001ccabcb0 [ 831.042286] x19: ffff0000097b5080 x18: 0000000000000a03 [ 831.047585] x17: 0000000000000000 x16: 0000000000000000 [ 831.052885] x15: 0000ffffaeca8000 x14: 0000000000000000 [ 831.058184] x13: 0000000000000000 x12: 0000000000000000 [ 831.063484] x11: 0000000000000001 x10: 0000000000000000 [ 831.068783] x9 : 0000000000000000 x8 : 0000000000000000 [ 831.074083] x7 : 0000000000000000 x6 : 000580d428000000 [ 831.079383] x5 : 0000000000000018 x4 : 0000000000000000 [ 831.084682] x3 : ffff00001ccabcb0 x2 : 0000000000000001 [ 831.089982] x1 : ffff8097d7ed6703 x0 : 0000000000000001 [ 831.095282] Process test_verifier (pid: 2788, stack limit = 0x0000000018370044) [ 831.102577] Call trace: [ 831.105012] __ll_sc_atomic_add+0x4/0x18 [ 831.108923] __bpf_prog_run32+0x4c/0x70 [ 831.112748] bpf_test_run+0x78/0xf8 [ 831.116224] bpf_prog_test_run_xdp+0xb4/0x120 [ 831.120567] SyS_bpf+0x77c/0x1110 [ 831.123873] el0_svc_naked+0x30/0x34 [ 831.127437] Code: 97fffe97 17ffffec 00000000 f9800031 (885f7c31) Reason for this is because memory is required to be aligned. In case of BPF, we always enforce alignment in terms of stack access, but not when accessing map values or packet data when the underlying arch (e.g. arm64) has CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS set. xadd on packet data that is local to us anyway is just wrong, so forbid this case entirely. The only place where xadd makes sense in fact are map values; xadd on stack is wrong as well, but it's been around for much longer. Specifically enforce strict alignment in case of xadd, so that we handle this case generically and avoid such crashes in the first place. Fixes: 17a5267067f3 ("bpf: verifier (add verifier core)") Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 42 +++++++++------ tools/testing/selftests/bpf/test_verifier.c | 58 +++++++++++++++++++++ 2 files changed, 84 insertions(+), 16 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 5fb69a85d967..c6eff108aa99 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1356,6 +1356,13 @@ static bool is_ctx_reg(struct bpf_verifier_env *env, int regno) return reg->type == PTR_TO_CTX; } +static bool is_pkt_reg(struct bpf_verifier_env *env, int regno) +{ + const struct bpf_reg_state *reg = cur_regs(env) + regno; + + return type_is_pkt_pointer(reg->type); +} + static int check_pkt_ptr_alignment(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int off, int size, bool strict) @@ -1416,10 +1423,10 @@ static int check_generic_ptr_alignment(struct bpf_verifier_env *env, } static int check_ptr_alignment(struct bpf_verifier_env *env, - const struct bpf_reg_state *reg, - int off, int size) + const struct bpf_reg_state *reg, int off, + int size, bool strict_alignment_once) { - bool strict = env->strict_alignment; + bool strict = env->strict_alignment || strict_alignment_once; const char *pointer_desc = ""; switch (reg->type) { @@ -1576,9 +1583,9 @@ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size) * if t==write && value_regno==-1, some unknown value is stored into memory * if t==read && value_regno==-1, don't care what we read from memory */ -static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regno, int off, - int bpf_size, enum bpf_access_type t, - int value_regno) +static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regno, + int off, int bpf_size, enum bpf_access_type t, + int value_regno, bool strict_alignment_once) { struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *reg = regs + regno; @@ -1590,7 +1597,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn return size; /* alignment checks will add in reg->off themselves */ - err = check_ptr_alignment(env, reg, off, size); + err = check_ptr_alignment(env, reg, off, size, strict_alignment_once); if (err) return err; @@ -1735,21 +1742,23 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins return -EACCES; } - if (is_ctx_reg(env, insn->dst_reg)) { - verbose(env, "BPF_XADD stores into R%d context is not allowed\n", - insn->dst_reg); + if (is_ctx_reg(env, insn->dst_reg) || + is_pkt_reg(env, insn->dst_reg)) { + verbose(env, "BPF_XADD stores into R%d %s is not allowed\n", + insn->dst_reg, is_ctx_reg(env, insn->dst_reg) ? + "context" : "packet"); return -EACCES; } /* check whether atomic_add can read the memory */ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, - BPF_SIZE(insn->code), BPF_READ, -1); + BPF_SIZE(insn->code), BPF_READ, -1, true); if (err) return err; /* check whether atomic_add can write into the same memory */ return check_mem_access(env, insn_idx, insn->dst_reg, insn->off, - BPF_SIZE(insn->code), BPF_WRITE, -1); + BPF_SIZE(insn->code), BPF_WRITE, -1, true); } /* when register 'regno' is passed into function that will read 'access_size' @@ -2388,7 +2397,8 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn * is inferred from register state. */ for (i = 0; i < meta.access_size; i++) { - err = check_mem_access(env, insn_idx, meta.regno, i, BPF_B, BPF_WRITE, -1); + err = check_mem_access(env, insn_idx, meta.regno, i, BPF_B, + BPF_WRITE, -1, false); if (err) return err; } @@ -4632,7 +4642,7 @@ static int do_check(struct bpf_verifier_env *env) */ err = check_mem_access(env, insn_idx, insn->src_reg, insn->off, BPF_SIZE(insn->code), BPF_READ, - insn->dst_reg); + insn->dst_reg, false); if (err) return err; @@ -4684,7 +4694,7 @@ static int do_check(struct bpf_verifier_env *env) /* check that memory (dst_reg + off) is writeable */ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_WRITE, - insn->src_reg); + insn->src_reg, false); if (err) return err; @@ -4719,7 +4729,7 @@ static int do_check(struct bpf_verifier_env *env) /* check that memory (dst_reg + off) is writeable */ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_WRITE, - -1); + -1, false); if (err) return err; diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index c73592fa3d41..437c0b1c9d21 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -11163,6 +11163,64 @@ static struct bpf_test tests[] = { .result = REJECT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, + { + "xadd/w check unaligned stack", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8), + BPF_STX_XADD(BPF_W, BPF_REG_10, BPF_REG_0, -7), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "misaligned stack access off", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "xadd/w check unaligned map", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_1, 1), + BPF_STX_XADD(BPF_W, BPF_REG_0, BPF_REG_1, 3), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 3), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .result = REJECT, + .errstr = "misaligned value access off", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "xadd/w check unaligned pkt", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 2), + BPF_MOV64_IMM(BPF_REG_0, 99), + BPF_JMP_IMM(BPF_JA, 0, 0, 6), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_ST_MEM(BPF_W, BPF_REG_2, 0, 0), + BPF_ST_MEM(BPF_W, BPF_REG_2, 3, 0), + BPF_STX_XADD(BPF_W, BPF_REG_2, BPF_REG_0, 1), + BPF_STX_XADD(BPF_W, BPF_REG_2, BPF_REG_0, 2), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 1), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "BPF_XADD stores into R2 packet", + .prog_type = BPF_PROG_TYPE_XDP, + }, }; static int probe_filter_length(const struct bpf_insn *fp) From d40bc96257fe070796c63934913f95cc183016b0 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 26 Feb 2018 10:52:46 -0800 Subject: [PATCH 2/4] test_bpf: add a schedule point test_bpf() is taking 1.6 seconds nowadays, it is time to add a schedule point in it. Signed-off-by: Eric Dumazet Signed-off-by: Daniel Borkmann --- lib/test_bpf.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/lib/test_bpf.c b/lib/test_bpf.c index b4e22345963f..e6f550608d72 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -24,6 +24,7 @@ #include #include #include +#include /* General test specific settings */ #define MAX_SUBTESTS 3 @@ -6582,6 +6583,7 @@ static __init int test_bpf(void) struct bpf_prog *fp; int err; + cond_resched(); if (exclude_test(i)) continue; From d269176e766c71c998cb75b4ea8cbc321cc0019d Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 26 Feb 2018 22:00:47 +0100 Subject: [PATCH 3/4] bpf, ppc64: fix out of bounds access in tail call While working on 16338a9b3ac3 ("bpf, arm64: fix out of bounds access in tail call") I noticed that ppc64 JIT is partially affected as well. While the bound checking is correctly performed as unsigned comparison, the register with the index value however, is never truncated into 32 bit space, so e.g. a index value of 0x100000000ULL with a map of 1 element would pass with PPC_CMPLW() whereas we later on continue with the full 64 bit register value. Therefore, as we do in interpreter and other JITs truncate the value to 32 bit initially in order to fix access. Fixes: ce0761419fae ("powerpc/bpf: Implement support for tail calls") Signed-off-by: Daniel Borkmann Reviewed-by: Naveen N. Rao Tested-by: Naveen N. Rao Signed-off-by: Alexei Starovoitov --- arch/powerpc/net/bpf_jit_comp64.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 0a34b0cec7b7..0ef3d9580e98 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -240,6 +240,7 @@ static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 * goto out; */ PPC_LWZ(b2p[TMP_REG_1], b2p_bpf_array, offsetof(struct bpf_array, map.max_entries)); + PPC_RLWINM(b2p_index, b2p_index, 0, 0, 31); PPC_CMPLW(b2p_index, b2p[TMP_REG_1]); PPC_BCC(COND_GE, out); From 9960d7669eaa42e82a2f4393adf549191de2e587 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 28 Feb 2018 08:39:20 -0800 Subject: [PATCH 4/4] test_bpf: reduce MAX_TESTRUNS For tests that are using the maximal number of BPF instruction, each run takes 20 usec. Looping 10,000 times on them totals 200 ms, which is bad when the loop is not preemptible. test_bpf: #264 BPF_MAXINSNS: Call heavy transformations jited:1 19248 18548 PASS test_bpf: #269 BPF_MAXINSNS: ld_abs+get_processor_id jited:1 20896 PASS Lets divide by ten the number of iterations, so that max latency is 20ms. We could use need_resched() to break the loop earlier if we believe 20 ms is too much. Signed-off-by: Eric Dumazet Signed-off-by: Daniel Borkmann --- lib/test_bpf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/test_bpf.c b/lib/test_bpf.c index e6f550608d72..2efb213716fa 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -28,7 +28,7 @@ /* General test specific settings */ #define MAX_SUBTESTS 3 -#define MAX_TESTRUNS 10000 +#define MAX_TESTRUNS 1000 #define MAX_DATA 128 #define MAX_INSNS 512 #define MAX_K 0xffffFFFF