[PATCH v2 1/5] powerpc/bpf: fix alignment of long branch trampoline address

[adubey at linux.ibm.com]

From: Abhishek Dubey <adubey at linux.ibm.com>

Ensure the dummy trampoline address field present between the OOL stub
and the long branch stub is 8-byte aligned, for compatibility when
loaded into a register.

Fixes: d243b62b7bd3 ("powerpc64/bpf: Add support for bpf trampolines")
Cc: stable at vger.kernel.org
Signed-off-by: Abhishek Dubey <adubey at linux.ibm.com>
---
 arch/powerpc/net/bpf_jit.h        |  4 ++--
 arch/powerpc/net/bpf_jit_comp.c   | 34 ++++++++++++++++++++++++++-----
 arch/powerpc/net/bpf_jit_comp64.c |  4 ++--
 3 files changed, 33 insertions(+), 9 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 9b2b456b0765..3cbb3647f7a0 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -49,11 +49,34 @@ 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;
 
 	/*
+	 * In the final pass, align the mis-aligned dummy tramp address
+	 * in the fimage. The alignment NOP must appear before OOL stub,
+	 * to make ool_stub_idx & long_branch_stub_idx constant from end.
+	 *
+	 * Need alignment NOP in following conditions:
+	 *
+	 * OOL stub aligned	CONFIG_PPC_FTRACE_OUT_OF_LINE	Alignment NOP
+	 *      Y                               Y                     N
+	 *      Y                               N                     Y
+	 *      N                               Y                     Y
+	 *      N                               N                     N
+	 */
+#ifdef CONFIG_PPC64
+	if (fimage && image) {
+		unsigned long pc = (unsigned long)fimage + CTX_NIA(ctx);
+
+		if (IS_ALIGNED(pc, 8) ^
+			IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE))
+			EMIT(PPC_RAW_NOP());
+	}
+#endif
+
+	/*      nop     // optional, for alignment of dummy_tramp_addr
 	 * Out-of-line stub:
 	 *	mflr	r0
 	 *	[b|bl]	tramp
@@ -70,7 +93,7 @@ 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 +104,7 @@ 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 +131,7 @@ 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;
@@ -308,7 +332,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	 */
 	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);
@@ -343,7 +367,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 			fp = org_fp;
 			goto out_addrs;
 		}
-		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_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index d39241444cd9..57992c1e8386 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);
 }
 
 /*
-- 
2.52.0