Re: [PATCH v7 1/7] powerpc/bpf: fix alignment of long branch trampoline address
From: Hari Bathini <hbathini@linux.ibm.com>
Date: 2026-06-13 12:35:15
Also in:
bpf, linux-kselftest, stable
On 11/06/26 9:08 pm, adubey@linux.ibm.com wrote:
From: Abhishek Dubey <redacted>
Ensure the dummy trampoline address field present between the OOL stub
and the long branch stub is 8-byte aligned, for memory compatibility
when content loaded to a register.
Reported-by: Hari Bathini <hbathini@linux.ibm.com>
Fixes: d243b62b7bd3 ("powerpc64/bpf: Add support for bpf trampolines")
Cc: stable@vger.kernel.orgExcept for a couple of minor nits below, the patch looks good to me Reviewed-by: Hari Bathini <hbathini@linux.ibm.com>
quoted hunk ↗ jump to hunk
Signed-off-by: Abhishek Dubey <redacted> --- arch/powerpc/net/bpf_jit.h | 4 ++-- arch/powerpc/net/bpf_jit_comp.c | 39 +++++++++++++++++++++++++++---- arch/powerpc/net/bpf_jit_comp32.c | 4 ++-- arch/powerpc/net/bpf_jit_comp64.c | 4 ++-- 4 files changed, 40 insertions(+), 11 deletions(-)diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h index f32de8704d4d..71e6e7d01057 100644 --- a/arch/powerpc/net/bpf_jit.h +++ b/arch/powerpc/net/bpf_jit.h@@ -214,8 +214,8 @@ int bpf_jit_emit_func_call_rel(u32 *image, u32 *fimage, struct codegen_context * int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct codegen_context *ctx, u32 *addrs, int pass, bool extra_pass); void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx); -void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx); -void bpf_jit_build_fentry_stubs(u32 *image, struct codegen_context *ctx); +void bpf_jit_build_epilogue(u32 *image, u32 *fimage, struct codegen_context *ctx); +void bpf_jit_build_fentry_stubs(u32 *image, u32 *fimage, struct codegen_context *ctx); void bpf_jit_realloc_regs(struct codegen_context *ctx); int bpf_jit_emit_exit_insn(u32 *image, struct codegen_context *ctx, int tmp_reg, long exit_addr); void prepare_for_fsession_fentry(u32 *image, struct codegen_context *ctx, int cookie_cnt,diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 6351a187ca61..79288ff789b5 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c@@ -49,11 +49,39 @@ asm ( " .popsection ;" ); -void bpf_jit_build_fentry_stubs(u32 *image, struct codegen_context *ctx) +void bpf_jit_build_fentry_stubs(u32 *image, u32 *fimage, struct codegen_context *ctx) { int ool_stub_idx, long_branch_stub_idx; + int ool_instrs; /* + * In the final pass, align the mis-aligned dummy_tramp_addr field + * in the fimage. The alignment NOP must appear before OOL stub, + * to make ool_stub_idx & long_branch_stub_idx constant from end. + * + * dummy_tramp_addr must be 8-byte aligned for load-register + * compatibility. The fimage can be non 8-byte aligned, so final + * alignment depends on start of fimage and the stub's instruction + * count offset. The OOL stub has 4 instructions (with
s/stub's instruction count offset/OOL stub size/
+ * CONFIG_PPC_FTRACE_OUT_OF_LINE) or 3 instructions (without) + * before dummy_tramp_addr. + * + * Emit a NOP here if (ctx->idx + ool_instrs) is odd, so that + * dummy_tramp_addr lands at an even instruction offset (== 8-byte + * aligned from an 8-byte aligned base). + * + * In pass=0 when image==NULL, conservatively account for space + * required to accommodate alignment NOP. In case final pass skips + * emitting alignment NOP, the image buffer have 4 spare bytes and + * jited_len signifies correct program size. + */ + + ool_instrs = IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE) ? 4*4 : 3*4;
ool_stub_sz sounds like a better name here instead of ool_instrs..
As the comment above already mentioned the no. of instructions in
each case, this could simply be:
ool_stub_sz = IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE) ? 16 : 12;
quoted hunk ↗ jump to hunk
+ if (!image || !IS_ALIGNED((unsigned long)fimage + ctx->idx*4 + ool_instrs, SZL)) + EMIT(PPC_RAW_NOP()); + + /* + * nop // optional, for alignment of dummy_tramp_addr * Out-of-line stub: * mflr r0 * [b|bl] tramp@@ -70,7 +98,7 @@ void bpf_jit_build_fentry_stubs(u32 *image, struct codegen_context *ctx) /* * Long branch stub: - * .long <dummy_tramp_addr> + * .long <dummy_tramp_addr> // 8-byte aligned * mflr r11 * bcl 20,31,$+4 * mflr r12@@ -81,6 +109,7 @@ void bpf_jit_build_fentry_stubs(u32 *image, struct codegen_context *ctx) */ if (image) *((unsigned long *)&image[ctx->idx]) = (unsigned long)dummy_tramp; + ctx->idx += SZL / 4; long_branch_stub_idx = ctx->idx; EMIT(PPC_RAW_MFLR(_R11));@@ -107,7 +136,7 @@ int bpf_jit_emit_exit_insn(u32 *image, struct codegen_context *ctx, int tmp_reg, PPC_JMP(ctx->alt_exit_addr); } else { ctx->alt_exit_addr = ctx->idx * 4; - bpf_jit_build_epilogue(image, ctx); + bpf_jit_build_epilogue(image, NULL, ctx); } return 0;@@ -286,7 +315,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_pr */ bpf_jit_build_prologue(NULL, &cgctx); addrs[fp->len] = cgctx.idx * 4; - bpf_jit_build_epilogue(NULL, &cgctx); + bpf_jit_build_epilogue(NULL, NULL, &cgctx); fixup_len = fp->aux->num_exentries * BPF_FIXUP_LEN * 4; extable_len = fp->aux->num_exentries * sizeof(struct exception_table_entry);@@ -318,7 +347,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_pr bpf_jit_binary_pack_free(fhdr, hdr); goto out_err; } - bpf_jit_build_epilogue(code_base, &cgctx); + bpf_jit_build_epilogue(code_base, fcode_base, &cgctx); if (bpf_jit_enable > 1) pr_info("Pass %d: shrink = %d, seen = 0x%x\n", pass,diff --git a/arch/powerpc/net/bpf_jit_comp32.c b/arch/powerpc/net/bpf_jit_comp32.c index bfdc50740da8..95bda0dee925 100644 --- a/arch/powerpc/net/bpf_jit_comp32.c +++ b/arch/powerpc/net/bpf_jit_comp32.c@@ -229,7 +229,7 @@ static void bpf_jit_emit_common_epilogue(u32 *image, struct codegen_context *ctx } -void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx) +void bpf_jit_build_epilogue(u32 *image, u32 *fimage, struct codegen_context *ctx) { EMIT(PPC_RAW_MR(_R3, bpf_to_ppc(BPF_REG_0)));@@ -237,7 +237,7 @@ void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx) EMIT(PPC_RAW_BLR()); - bpf_jit_build_fentry_stubs(image, ctx); + bpf_jit_build_fentry_stubs(image, fimage, ctx); } /* Relative offset needs to be calculated based on final image location */diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index db364d9083e7..885dc8cf55a2 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c@@ -398,7 +398,7 @@ static void bpf_jit_emit_common_epilogue(u32 *image, struct codegen_context *ctx } } -void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx) +void bpf_jit_build_epilogue(u32 *image, u32 *fimage, struct codegen_context *ctx) { bpf_jit_emit_common_epilogue(image, ctx);@@ -407,7 +407,7 @@ void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx) EMIT(PPC_RAW_BLR()); - bpf_jit_build_fentry_stubs(image, ctx); + bpf_jit_build_fentry_stubs(image, fimage, ctx); } /*
- Hari