4.19-stable review patch. If anyone has any objections, please let me know.
------------------
From: Naveen N. Rao naveen.n.rao@linux.vnet.ibm.com
commit 86be36f6502c52ddb4b85938145324fd07332da1 upstream.
Yauheni Kaliuta pointed out that PTR_TO_STACK store/load verifier test was failing on powerpc64 BE, and rightfully indicated that the PPC_LD() macro is not masking away the last two bits of the offset per the ISA, resulting in the generation of 'lwa' instruction instead of the intended 'ld' instruction.
Segher also pointed out that we can't simply mask away the last two bits as that will result in loading/storing from/to a memory location that was not intended.
This patch addresses this by using ldx/stdx if the offset is not word-aligned. We load the offset into a temporary register (TMP_REG_2) and use that as the index register in a subsequent ldx/stdx. We fix PPC_LD() macro to mask off the last two bits, but enhance PPC_BPF_LL() and PPC_BPF_STL() to factor in the offset value and generate the proper instruction sequence. We also convert all existing users of PPC_LD() and PPC_STD() to use these macros. All existing uses of these macros have been audited to ensure that TMP_REG_2 can be clobbered.
Fixes: 156d0e290e96 ("powerpc/ebpf/jit: Implement JIT compiler for extended BPF") Cc: stable@vger.kernel.org # v4.9+
Reported-by: Yauheni Kaliuta yauheni.kaliuta@redhat.com Signed-off-by: Naveen N. Rao naveen.n.rao@linux.vnet.ibm.com Signed-off-by: Daniel Borkmann daniel@iogearbox.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org
--- arch/powerpc/include/asm/ppc-opcode.h | 2 ++ arch/powerpc/net/bpf_jit.h | 17 +++++------------ arch/powerpc/net/bpf_jit32.h | 4 ++++ arch/powerpc/net/bpf_jit64.h | 20 ++++++++++++++++++++ arch/powerpc/net/bpf_jit_comp64.c | 12 ++++++------ 5 files changed, 37 insertions(+), 18 deletions(-)
--- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -300,6 +300,7 @@ /* Misc instructions for BPF compiler */ #define PPC_INST_LBZ 0x88000000 #define PPC_INST_LD 0xe8000000 +#define PPC_INST_LDX 0x7c00002a #define PPC_INST_LHZ 0xa0000000 #define PPC_INST_LWZ 0x80000000 #define PPC_INST_LHBRX 0x7c00062c @@ -307,6 +308,7 @@ #define PPC_INST_STB 0x98000000 #define PPC_INST_STH 0xb0000000 #define PPC_INST_STD 0xf8000000 +#define PPC_INST_STDX 0x7c00012a #define PPC_INST_STDU 0xf8000001 #define PPC_INST_STW 0x90000000 #define PPC_INST_STWU 0x94000000 --- a/arch/powerpc/net/bpf_jit.h +++ b/arch/powerpc/net/bpf_jit.h @@ -51,6 +51,8 @@ #define PPC_LIS(r, i) PPC_ADDIS(r, 0, i) #define PPC_STD(r, base, i) EMIT(PPC_INST_STD | ___PPC_RS(r) | \ ___PPC_RA(base) | ((i) & 0xfffc)) +#define PPC_STDX(r, base, b) EMIT(PPC_INST_STDX | ___PPC_RS(r) | \ + ___PPC_RA(base) | ___PPC_RB(b)) #define PPC_STDU(r, base, i) EMIT(PPC_INST_STDU | ___PPC_RS(r) | \ ___PPC_RA(base) | ((i) & 0xfffc)) #define PPC_STW(r, base, i) EMIT(PPC_INST_STW | ___PPC_RS(r) | \ @@ -65,7 +67,9 @@ #define PPC_LBZ(r, base, i) EMIT(PPC_INST_LBZ | ___PPC_RT(r) | \ ___PPC_RA(base) | IMM_L(i)) #define PPC_LD(r, base, i) EMIT(PPC_INST_LD | ___PPC_RT(r) | \ - ___PPC_RA(base) | IMM_L(i)) + ___PPC_RA(base) | ((i) & 0xfffc)) +#define PPC_LDX(r, base, b) EMIT(PPC_INST_LDX | ___PPC_RT(r) | \ + ___PPC_RA(base) | ___PPC_RB(b)) #define PPC_LWZ(r, base, i) EMIT(PPC_INST_LWZ | ___PPC_RT(r) | \ ___PPC_RA(base) | IMM_L(i)) #define PPC_LHZ(r, base, i) EMIT(PPC_INST_LHZ | ___PPC_RT(r) | \ @@ -85,17 +89,6 @@ ___PPC_RA(a) | ___PPC_RB(b)) #define PPC_BPF_STDCX(s, a, b) EMIT(PPC_INST_STDCX | ___PPC_RS(s) | \ ___PPC_RA(a) | ___PPC_RB(b)) - -#ifdef CONFIG_PPC64 -#define PPC_BPF_LL(r, base, i) do { PPC_LD(r, base, i); } while(0) -#define PPC_BPF_STL(r, base, i) do { PPC_STD(r, base, i); } while(0) -#define PPC_BPF_STLU(r, base, i) do { PPC_STDU(r, base, i); } while(0) -#else -#define PPC_BPF_LL(r, base, i) do { PPC_LWZ(r, base, i); } while(0) -#define PPC_BPF_STL(r, base, i) do { PPC_STW(r, base, i); } while(0) -#define PPC_BPF_STLU(r, base, i) do { PPC_STWU(r, base, i); } while(0) -#endif - #define PPC_CMPWI(a, i) EMIT(PPC_INST_CMPWI | ___PPC_RA(a) | IMM_L(i)) #define PPC_CMPDI(a, i) EMIT(PPC_INST_CMPDI | ___PPC_RA(a) | IMM_L(i)) #define PPC_CMPW(a, b) EMIT(PPC_INST_CMPW | ___PPC_RA(a) | \ --- a/arch/powerpc/net/bpf_jit32.h +++ b/arch/powerpc/net/bpf_jit32.h @@ -123,6 +123,10 @@ DECLARE_LOAD_FUNC(sk_load_byte_msh); #define PPC_NTOHS_OFFS(r, base, i) PPC_LHZ_OFFS(r, base, i) #endif
+#define PPC_BPF_LL(r, base, i) do { PPC_LWZ(r, base, i); } while(0) +#define PPC_BPF_STL(r, base, i) do { PPC_STW(r, base, i); } while(0) +#define PPC_BPF_STLU(r, base, i) do { PPC_STWU(r, base, i); } while(0) + #define SEEN_DATAREF 0x10000 /* might call external helpers */ #define SEEN_XREG 0x20000 /* X reg is used */ #define SEEN_MEM 0x40000 /* SEEN_MEM+(1<<n) = use mem[n] for temporary --- a/arch/powerpc/net/bpf_jit64.h +++ b/arch/powerpc/net/bpf_jit64.h @@ -68,6 +68,26 @@ static const int b2p[] = { /* PPC NVR range -- update this if we ever use NVRs below r27 */ #define BPF_PPC_NVR_MIN 27
+/* + * WARNING: These can use TMP_REG_2 if the offset is not at word boundary, + * so ensure that it isn't in use already. + */ +#define PPC_BPF_LL(r, base, i) do { \ + if ((i) % 4) { \ + PPC_LI(b2p[TMP_REG_2], (i)); \ + PPC_LDX(r, base, b2p[TMP_REG_2]); \ + } else \ + PPC_LD(r, base, i); \ + } while(0) +#define PPC_BPF_STL(r, base, i) do { \ + if ((i) % 4) { \ + PPC_LI(b2p[TMP_REG_2], (i)); \ + PPC_STDX(r, base, b2p[TMP_REG_2]); \ + } else \ + PPC_STD(r, base, i); \ + } while(0) +#define PPC_BPF_STLU(r, base, i) do { PPC_STDU(r, base, i); } while(0) + #define SEEN_FUNC 0x1000 /* might call external helpers */ #define SEEN_STACK 0x2000 /* uses BPF stack */ #define SEEN_TAILCALL 0x4000 /* uses tail calls */ --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -226,7 +226,7 @@ static void bpf_jit_emit_tail_call(u32 * * if (tail_call_cnt > MAX_TAIL_CALL_CNT) * goto out; */ - PPC_LD(b2p[TMP_REG_1], 1, bpf_jit_stack_tailcallcnt(ctx)); + PPC_BPF_LL(b2p[TMP_REG_1], 1, bpf_jit_stack_tailcallcnt(ctx)); PPC_CMPLWI(b2p[TMP_REG_1], MAX_TAIL_CALL_CNT); PPC_BCC(COND_GT, out);
@@ -239,7 +239,7 @@ static void bpf_jit_emit_tail_call(u32 * /* prog = array->ptrs[index]; */ PPC_MULI(b2p[TMP_REG_1], b2p_index, 8); PPC_ADD(b2p[TMP_REG_1], b2p[TMP_REG_1], b2p_bpf_array); - PPC_LD(b2p[TMP_REG_1], b2p[TMP_REG_1], offsetof(struct bpf_array, ptrs)); + PPC_BPF_LL(b2p[TMP_REG_1], b2p[TMP_REG_1], offsetof(struct bpf_array, ptrs));
/* * if (prog == NULL) @@ -249,7 +249,7 @@ static void bpf_jit_emit_tail_call(u32 * PPC_BCC(COND_EQ, out);
/* goto *(prog->bpf_func + prologue_size); */ - PPC_LD(b2p[TMP_REG_1], b2p[TMP_REG_1], offsetof(struct bpf_prog, bpf_func)); + PPC_BPF_LL(b2p[TMP_REG_1], b2p[TMP_REG_1], offsetof(struct bpf_prog, bpf_func)); #ifdef PPC64_ELF_ABI_v1 /* skip past the function descriptor */ PPC_ADDI(b2p[TMP_REG_1], b2p[TMP_REG_1], @@ -573,7 +573,7 @@ bpf_alu32_trunc: * the instructions generated will remain the * same across all passes */ - PPC_STD(dst_reg, 1, bpf_jit_stack_local(ctx)); + PPC_BPF_STL(dst_reg, 1, bpf_jit_stack_local(ctx)); PPC_ADDI(b2p[TMP_REG_1], 1, bpf_jit_stack_local(ctx)); PPC_LDBRX(dst_reg, 0, b2p[TMP_REG_1]); break; @@ -629,7 +629,7 @@ emit_clear: PPC_LI32(b2p[TMP_REG_1], imm); src_reg = b2p[TMP_REG_1]; } - PPC_STD(src_reg, dst_reg, off); + PPC_BPF_STL(src_reg, dst_reg, off); break;
/* @@ -676,7 +676,7 @@ emit_clear: break; /* dst = *(u64 *)(ul) (src + off) */ case BPF_LDX | BPF_MEM | BPF_DW: - PPC_LD(dst_reg, src_reg, off); + PPC_BPF_LL(dst_reg, src_reg, off); break;
/*