bpf: do not use reciprocal divide

At first Jakub Zawadzki noticed that some divisions by reciprocal_divide
were not correct. (off by one in some cases)
http://www.wireshark.org/~darkjames/reciprocal-buggy.c

He could also show this with BPF:
http://www.wireshark.org/~darkjames/set-and-dump-filter-k-bug.c

The reciprocal divide in linux kernel is not generic enough,
lets remove its use in BPF, as it is not worth the pain with
current cpus.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Jakub Zawadzki <darkjames-ws@darkjames.pl>
Cc: Mircea Gherzan <mgherzan@gmail.com>
Cc: Daniel Borkmann <dxchgb@gmail.com>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Cc: Matt Evans <matt@ozlabs.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 43 insertions, 18 deletions

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 9ed155ad0f97..271b5e971568 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -641,10 +641,10 @@ load_ind:
                         emit(ARM_MUL(r_A, r_A, r_X), ctx);
                         break;
                 case BPF_S_ALU_DIV_K:
-                        /* current k == reciprocal_value(userspace k) */
+                        if (k == 1)
+                                break;
                         emit_mov_i(r_scratch, k, ctx);
-                        /* A = top 32 bits of the product */
-                        emit(ARM_UMULL(r_scratch, r_A, r_A, r_scratch), ctx);
+                        emit_udiv(r_A, r_A, r_scratch, ctx);
                         break;
                 case BPF_S_ALU_DIV_X:
                         update_on_xread(ctx);
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index ac3c2a10dafd..555034f8505e 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -223,10 +223,11 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
                         }
                         PPC_DIVWU(r_A, r_A, r_X);
                         break;
-                case BPF_S_ALU_DIV_K: /* A = reciprocal_divide(A, K); */
+                case BPF_S_ALU_DIV_K: /* A /= K */
+                        if (K == 1)
+                                break;
                         PPC_LI32(r_scratch1, K);
-                        /* Top 32 bits of 64bit result -> A */
-                        PPC_MULHWU(r_A, r_A, r_scratch1);
+                        PPC_DIVWU(r_A, r_A, r_scratch1);
                         break;
                 case BPF_S_ALU_AND_X:
                         ctx->seen |= SEEN_XREG;
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 16871da37371..fc0fa77728e1 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -371,11 +371,13 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
                 /* dr %r4,%r12 */
                 EMIT2(0x1d4c);
                 break;
-        case BPF_S_ALU_DIV_K: /* A = reciprocal_divide(A, K) */
-                /* m %r4,<d(K)>(%r13) */
-                EMIT4_DISP(0x5c40d000, EMIT_CONST(K));
-                /* lr %r5,%r4 */
-                EMIT2(0x1854);
+        case BPF_S_ALU_DIV_K: /* A /= K */
+                if (K == 1)
+                        break;
+                /* lhi %r4,0 */
+                EMIT4(0xa7480000);
+                /* d %r4,<d(K)>(%r13) */
+                EMIT4_DISP(0x5d40d000, EMIT_CONST(K));
                 break;
         case BPF_S_ALU_MOD_X: /* A %= X */
                 jit->seen |= SEEN_XREG | SEEN_RET0;
@@ -391,6 +393,11 @@ static int bpf_jit_insn(struct bpf_jit *jit, struct sock_filter *filter,
                 EMIT2(0x1854);
                 break;
         case BPF_S_ALU_MOD_K: /* A %= K */
+                if (K == 1) {
+                        /* lhi %r5,0 */
+                        EMIT4(0xa7580000);
+                        break;
+                }
                 /* lhi %r4,0 */
                 EMIT4(0xa7480000);
                 /* d %r4,<d(K)>(%r13) */
diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c
index 218b6b23c378..01fe9946d388 100644
--- a/arch/sparc/net/bpf_jit_comp.c
+++ b/arch/sparc/net/bpf_jit_comp.c
@@ -497,9 +497,20 @@ void bpf_jit_compile(struct sk_filter *fp)
                         case BPF_S_ALU_MUL_K:   /* A *= K */
                                 emit_alu_K(MUL, K);
                                 break;
-                        case BPF_S_ALU_DIV_K:   /* A /= K */
-                                emit_alu_K(MUL, K);
-                                emit_read_y(r_A);
+                        case BPF_S_ALU_DIV_K:   /* A /= K with K != 0*/
+                                if (K == 1)
+                                        break;
+                                emit_write_y(G0);
+#ifdef CONFIG_SPARC32
+                                /* The Sparc v8 architecture requires
+                                 * three instructions between a %y
+                                 * register write and the first use.
+                                 */
+                                emit_nop();
+                                emit_nop();
+                                emit_nop();
+#endif
+                                emit_alu_K(DIV, K);
                                 break;
                         case BPF_S_ALU_DIV_X:   /* A /= X; */
                                 emit_cmpi(r_X, 0);
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 26328e800869..4ed75dd81d05 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -359,15 +359,21 @@ void bpf_jit_compile(struct sk_filter *fp)
                                 EMIT2(0x89, 0xd0);      /* mov %edx,%eax */
                                 break;
                         case BPF_S_ALU_MOD_K: /* A %= K; */
+                                if (K == 1) {
+                                        CLEAR_A();
+                                        break;
+                                }
                                 EMIT2(0x31, 0xd2);      /* xor %edx,%edx */
                                 EMIT1(0xb9);EMIT(K, 4); /* mov imm32,%ecx */
                                 EMIT2(0xf7, 0xf1);      /* div %ecx */
                                 EMIT2(0x89, 0xd0);      /* mov %edx,%eax */
                                 break;
-                        case BPF_S_ALU_DIV_K: /* A = reciprocal_divide(A, K); */
-                                EMIT3(0x48, 0x69, 0xc0); /* imul imm32,%rax,%rax */
-                                EMIT(K, 4);
-                                EMIT4(0x48, 0xc1, 0xe8, 0x20); /* shr $0x20,%rax */
+                        case BPF_S_ALU_DIV_K: /* A /= K */
+                                if (K == 1)
+                                        break;
+                                EMIT2(0x31, 0xd2);      /* xor %edx,%edx */
+                                EMIT1(0xb9);EMIT(K, 4); /* mov imm32,%ecx */
+                                EMIT2(0xf7, 0xf1);      /* div %ecx */
                                 break;
                         case BPF_S_ALU_AND_X:
                                 seen |= SEEN_XREG;