powerpc/bpf: BPF JIT compiler for 64-bit Little Endian

This enables the Berkeley Packet Filter JIT compiler
for the PowerPC running in 64bit Little Endian.

Signed-off-by: Philippe Bergheaud <felix@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

3 files changed, 20 insertions, 16 deletions

diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
index 8a5dfaf5c6b7..0baf2b826e25 100644
--- a/arch/powerpc/net/bpf_jit.h
+++ b/arch/powerpc/net/bpf_jit.h
@@ -92,6 +92,8 @@ DECLARE_LOAD_FUNC(sk_load_byte_msh);
                                      ___PPC_RA(base) | IMM_L(i))
 #define PPC_LHZ(r, base, i)     EMIT(PPC_INST_LHZ | ___PPC_RT(r) |            \
                                      ___PPC_RA(base) | IMM_L(i))
+#define PPC_LHBRX(r, base, b)   EMIT(PPC_INST_LHBRX | ___PPC_RT(r) |          \
+                                     ___PPC_RA(base) | ___PPC_RB(b))
 /* Convenience helpers for the above with 'far' offsets: */
 #define PPC_LD_OFFS(r, base, i) do { if ((i) < 32768) PPC_LD(r, base, i);     \
                 else {  PPC_ADDIS(r, base, IMM_HA(i));                        \
@@ -186,6 +188,14 @@ DECLARE_LOAD_FUNC(sk_load_byte_msh);
                                 PPC_ORI(d, d, (uintptr_t)(i) & 0xffff);       \
                 } } while (0);
 
+#define PPC_LHBRX_OFFS(r, base, i) \
+                do { PPC_LI32(r, i); PPC_LHBRX(r, r, base); } while(0)
+#ifdef __LITTLE_ENDIAN__
+#define PPC_NTOHS_OFFS(r, base, i)      PPC_LHBRX_OFFS(r, base, i)
+#else
+#define PPC_NTOHS_OFFS(r, base, i)      PPC_LHZ_OFFS(r, base, i)
+#endif
+
 static inline bool is_nearbranch(int offset)
 {
         return (offset < 32768) && (offset >= -32768);
diff --git a/arch/powerpc/net/bpf_jit_64.S b/arch/powerpc/net/bpf_jit_64.S
index 7d3a3b5619a2..e76eba74d9da 100644
--- a/arch/powerpc/net/bpf_jit_64.S
+++ b/arch/powerpc/net/bpf_jit_64.S
@@ -43,8 +43,11 @@ sk_load_word_positive_offset:
         cmpd    r_scratch1, r_addr
         blt     bpf_slow_path_word
         /* Nope, just hitting the header.  cr0 here is eq or gt! */
+#ifdef __LITTLE_ENDIAN__
+        lwbrx   r_A, r_D, r_addr
+#else
         lwzx    r_A, r_D, r_addr
-        /* When big endian we don't need to byteswap. */
+#endif
         blr     /* Return success, cr0 != LT */
 
         .globl  sk_load_half
@@ -56,7 +59,11 @@ sk_load_half_positive_offset:
         subi    r_scratch1, r_HL, 2
         cmpd    r_scratch1, r_addr
         blt     bpf_slow_path_half
+#ifdef __LITTLE_ENDIAN__
+        lhbrx   r_A, r_D, r_addr
+#else
         lhzx    r_A, r_D, r_addr
+#endif
         blr
 
         .globl  sk_load_byte
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index bf56e33f8257..81cd6c79babe 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -17,14 +17,8 @@
 
 #include "bpf_jit.h"
 
-#ifndef __BIG_ENDIAN
-/* There are endianness assumptions herein. */
-#error "Little-endian PPC not supported in BPF compiler"
-#endif
-
 int bpf_jit_enable __read_mostly;
 
-
 static inline void bpf_flush_icache(void *start, void *end)
 {
         smp_wmb();
@@ -346,18 +340,11 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
                         break;
 
                         /*** Ancillary info loads ***/
-
-                        /* None of the BPF_S_ANC* codes appear to be passed by
-                         * sk_chk_filter().  The interpreter and the x86 BPF
-                         * compiler implement them so we do too -- they may be
-                         * planted in future.
-                         */
                 case BPF_S_ANC_PROTOCOL: /* A = ntohs(skb->protocol); */
                         BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff,
                                                   protocol) != 2);
-                        PPC_LHZ_OFFS(r_A, r_skb, offsetof(struct sk_buff,
-                                                          protocol));
-                        /* ntohs is a NOP with BE loads. */
+                        PPC_NTOHS_OFFS(r_A, r_skb, offsetof(struct sk_buff,
+                                                            protocol));
                         break;
                 case BPF_S_ANC_IFINDEX:
                         PPC_LD_OFFS(r_scratch1, r_skb, offsetof(struct sk_buff,