Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Ravi Bangoria <ravi.bangoria@linux.ibm.com>
To:     naveen.n.rao@linux.ibm.com, mpe@ellerman.id.au, ast@kernel.org,
        daniel@iogearbox.net
Cc:     ravi.bangoria@linux.ibm.com, sandipan@linux.ibm.com,
        paulus@samba.org, andrii@kernel.org, kafai@fb.com,
        songliubraving@fb.com, yhs@fb.com, john.fastabend@gmail.com,
        kpsingh@kernel.org, netdev@vger.kernel.org, bpf@vger.kernel.org,
        linuxppc-dev@lists.ozlabs.org, linux-kernel@vger.kernel.org
Subject: [PATCH 4/4] bpf powerpc: Add addr > TASK_SIZE_MAX explicit check
Date:   Tue,  6 Jul 2021 13:02:11 +0530
Message-Id: <20210706073211.349889-5-ravi.bangoria@linux.ibm.com>
In-Reply-To: <20210706073211.349889-1-ravi.bangoria@linux.ibm.com>
References: <20210706073211.349889-1-ravi.bangoria@linux.ibm.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

On PowerPC with KUAP enabled, any kernel code which wants to
access userspace needs to be surrounded by disable-enable KUAP.
But that is not happening for BPF_PROBE_MEM load instruction.
So, when BPF program tries to access invalid userspace address,
page-fault handler considers it as bad KUAP fault:

  Kernel attempted to read user page (d0000000) - exploit attempt? (uid: 0)

Considering the fact that PTR_TO_BTF_ID (which uses BPF_PROBE_MEM
mode) could either be a valid kernel pointer or NULL but should
never be a pointer to userspace address, execute BPF_PROBE_MEM load
only if addr > TASK_SIZE_MAX, otherwise set dst_reg=0 and move on.

This will catch NULL, valid or invalid userspace pointers. Only bad
kernel pointer will be handled by BPF exception table.

[Alexei suggested for x86]
Suggested-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
---
 arch/powerpc/net/bpf_jit_comp64.c | 38 +++++++++++++++++++++++++++++++
 1 file changed, 38 insertions(+)

diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 1884c6dca89a..46becae76210 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -753,6 +753,14 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 		/* dst = *(u8 *)(ul) (src + off) */
 		case BPF_LDX | BPF_MEM | BPF_B:
 		case BPF_LDX | BPF_PROBE_MEM | BPF_B:
+			if (BPF_MODE(code) == BPF_PROBE_MEM) {
+				EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], src_reg, off));
+				PPC_LI64(b2p[TMP_REG_2], TASK_SIZE_MAX);
+				EMIT(PPC_RAW_CMPLD(b2p[TMP_REG_1], b2p[TMP_REG_2]));
+				PPC_BCC(COND_GT, (ctx->idx + 4) * 4);
+				EMIT(PPC_RAW_XOR(dst_reg, dst_reg, dst_reg));
+				PPC_JMP((ctx->idx + 2) * 4);
+			}
 			EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off));
 			if (insn_is_zext(&insn[i + 1]))
 				addrs[++i] = ctx->idx * 4;
@@ -763,6 +771,14 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 		/* dst = *(u16 *)(ul) (src + off) */
 		case BPF_LDX | BPF_MEM | BPF_H:
 		case BPF_LDX | BPF_PROBE_MEM | BPF_H:
+			if (BPF_MODE(code) == BPF_PROBE_MEM) {
+				EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], src_reg, off));
+				PPC_LI64(b2p[TMP_REG_2], TASK_SIZE_MAX);
+				EMIT(PPC_RAW_CMPLD(b2p[TMP_REG_1], b2p[TMP_REG_2]));
+				PPC_BCC(COND_GT, (ctx->idx + 4) * 4);
+				EMIT(PPC_RAW_XOR(dst_reg, dst_reg, dst_reg));
+				PPC_JMP((ctx->idx + 2) * 4);
+			}
 			EMIT(PPC_RAW_LHZ(dst_reg, src_reg, off));
 			if (insn_is_zext(&insn[i + 1]))
 				addrs[++i] = ctx->idx * 4;
@@ -773,6 +789,14 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 		/* dst = *(u32 *)(ul) (src + off) */
 		case BPF_LDX | BPF_MEM | BPF_W:
 		case BPF_LDX | BPF_PROBE_MEM | BPF_W:
+			if (BPF_MODE(code) == BPF_PROBE_MEM) {
+				EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], src_reg, off));
+				PPC_LI64(b2p[TMP_REG_2], TASK_SIZE_MAX);
+				EMIT(PPC_RAW_CMPLD(b2p[TMP_REG_1], b2p[TMP_REG_2]));
+				PPC_BCC(COND_GT, (ctx->idx + 4) * 4);
+				EMIT(PPC_RAW_XOR(dst_reg, dst_reg, dst_reg));
+				PPC_JMP((ctx->idx + 2) * 4);
+			}
 			EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off));
 			if (insn_is_zext(&insn[i + 1]))
 				addrs[++i] = ctx->idx * 4;
@@ -783,6 +807,20 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 		/* dst = *(u64 *)(ul) (src + off) */
 		case BPF_LDX | BPF_MEM | BPF_DW:
 		case BPF_LDX | BPF_PROBE_MEM | BPF_DW:
+			if (BPF_MODE(code) == BPF_PROBE_MEM) {
+				EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], src_reg, off));
+				PPC_LI64(b2p[TMP_REG_2], TASK_SIZE_MAX);
+				EMIT(PPC_RAW_CMPLD(b2p[TMP_REG_1], b2p[TMP_REG_2]));
+				if (off % 4)
+					PPC_BCC(COND_GT, (ctx->idx + 5) * 4);
+				else
+					PPC_BCC(COND_GT, (ctx->idx + 4) * 4);
+				EMIT(PPC_RAW_XOR(dst_reg, dst_reg, dst_reg));
+				if (off % 4)
+					PPC_JMP((ctx->idx + 3) * 4);
+				else
+					PPC_JMP((ctx->idx + 2) * 4);
+			}
 			PPC_BPF_LL(dst_reg, src_reg, off);
 			ret = add_extable_entry(fp, image, pass, code, ctx, dst_reg);
 			if (ret)
-- 
2.26.3