@@ -150,22 +150,20 @@ void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
static int bpf_jit_emit_func_call_hlp(u32 *image, struct codegen_context *ctx, u64 func)
{
unsigned long func_addr = func ? ppc_function_entry((void *)func) : 0;
+ long reladdr;
if (WARN_ON_ONCE(!core_kernel_text(func_addr)))
return -EINVAL;
-#ifdef PPC64_ELF_ABI_v1
- /* func points to the function descriptor */
- PPC_LI64(b2p[TMP_REG_2], func);
- /* Load actual entry point from function descriptor */
- PPC_BPF_LL(b2p[TMP_REG_1], b2p[TMP_REG_2], 0);
- /* ... and move it to CTR */
- EMIT(PPC_RAW_MTCTR(b2p[TMP_REG_1]));
-#else
- /* We can clobber r12 */
- PPC_FUNC_ADDR(12, func);
- EMIT(PPC_RAW_MTCTR(12));
-#endif
+ reladdr = func_addr - kernel_toc_addr();
+ if (reladdr > 0x7FFFFFFF || reladdr < -(0x80000000L)) {
+ pr_err("eBPF: address of %ps out of range of kernel_toc.\n", (void *)func);
+ return -ERANGE;
+ }
+
+ EMIT(PPC_RAW_ADDIS(_R12, _R2, PPC_HA(reladdr)));
+ EMIT(PPC_RAW_ADDI(_R12, _R12, PPC_LO(reladdr)));
+ EMIT(PPC_RAW_MTCTR(_R12));
EMIT(PPC_RAW_BCTRL());
return 0;
@@ -178,6 +176,9 @@ int bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 func
if (WARN_ON_ONCE(func && is_module_text_address(func)))
return -EINVAL;
+ /* skip past descriptor if elf v1 */
+ func += FUNCTION_DESCR_SIZE;
+
/* Load function address into r12 */
PPC_LI64(12, func);
@@ -194,11 +195,6 @@ int bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 func
for (i = ctx->idx - ctx_idx; i < 5; i++)
EMIT(PPC_RAW_NOP());
-#ifdef PPC64_ELF_ABI_v1
- /* Load actual entry point from function descriptor */
- PPC_BPF_LL(12, 12, 0);
-#endif
-
EMIT(PPC_RAW_MTCTR(12));
EMIT(PPC_RAW_BCTRL());
When calling BPF helpers, we load the function address to call into a register. This can result in upto 5 instructions. Optimize this by instead using the kernel toc in r2 and adjusting offset to the BPF helper. This works since all BPF helpers are part of kernel text, and all BPF programs/functions utilize the kernel TOC. Further more: - load the actual function entry address in elf v1, rather than loading it through the function descriptor address. - load the Local Entry Point (LEP) in elf v2 skipping TOC setup. - consolidate code across elf abi v1 and v2 by using r12 on both. Reported-by: Anton Blanchard <anton@ozlabs.org> Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> --- arch/powerpc/net/bpf_jit_comp64.c | 30 +++++++++++++----------------- 1 file changed, 13 insertions(+), 17 deletions(-)