diff mbox series

[v1,07/10] powerpc/bpf: Only pad length-variable code at initial pass

Message ID ee5253722c2a1e26b8bec3691166d7081538c7cb.1669881248.git.christophe.leroy@csgroup.eu (mailing list archive)
State Not Applicable
Delegated to: BPF
Headers show
Series [v1,01/10] powerpc/bpf/32: Fix Oops on tail call tests | expand

Checks

Context Check Description
netdev/tree_selection success Not a local patch
bpf/vmtest-bpf-PR success PR summary
bpf/vmtest-bpf-VM_Test-1 success Logs for ShellCheck
bpf/vmtest-bpf-VM_Test-2 success Logs for build for aarch64 with gcc
bpf/vmtest-bpf-VM_Test-3 success Logs for build for aarch64 with llvm-16
bpf/vmtest-bpf-VM_Test-4 success Logs for build for s390x with gcc
bpf/vmtest-bpf-VM_Test-5 success Logs for build for x86_64 with gcc
bpf/vmtest-bpf-VM_Test-6 success Logs for build for x86_64 with llvm-16
bpf/vmtest-bpf-VM_Test-7 success Logs for llvm-toolchain
bpf/vmtest-bpf-VM_Test-8 success Logs for set-matrix
bpf/vmtest-bpf-VM_Test-9 success Logs for test_maps on aarch64 with gcc
bpf/vmtest-bpf-VM_Test-10 success Logs for test_maps on aarch64 with llvm-16
bpf/vmtest-bpf-VM_Test-11 success Logs for test_maps on s390x with gcc
bpf/vmtest-bpf-VM_Test-12 success Logs for test_maps on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-13 success Logs for test_maps on x86_64 with llvm-16
bpf/vmtest-bpf-VM_Test-14 fail Logs for test_progs on aarch64 with gcc
bpf/vmtest-bpf-VM_Test-15 fail Logs for test_progs on aarch64 with llvm-16
bpf/vmtest-bpf-VM_Test-16 fail Logs for test_progs on s390x with gcc
bpf/vmtest-bpf-VM_Test-17 fail Logs for test_progs on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-18 fail Logs for test_progs on x86_64 with llvm-16
bpf/vmtest-bpf-VM_Test-19 fail Logs for test_progs_no_alu32 on aarch64 with gcc
bpf/vmtest-bpf-VM_Test-20 fail Logs for test_progs_no_alu32 on aarch64 with llvm-16
bpf/vmtest-bpf-VM_Test-21 fail Logs for test_progs_no_alu32 on s390x with gcc
bpf/vmtest-bpf-VM_Test-22 fail Logs for test_progs_no_alu32 on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-23 fail Logs for test_progs_no_alu32 on x86_64 with llvm-16
bpf/vmtest-bpf-VM_Test-24 success Logs for test_progs_no_alu32_parallel on aarch64 with gcc
bpf/vmtest-bpf-VM_Test-25 success Logs for test_progs_no_alu32_parallel on aarch64 with llvm-16
bpf/vmtest-bpf-VM_Test-26 success Logs for test_progs_no_alu32_parallel on s390x with gcc
bpf/vmtest-bpf-VM_Test-27 success Logs for test_progs_no_alu32_parallel on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-28 success Logs for test_progs_no_alu32_parallel on x86_64 with llvm-16
bpf/vmtest-bpf-VM_Test-29 success Logs for test_progs_parallel on aarch64 with gcc
bpf/vmtest-bpf-VM_Test-30 success Logs for test_progs_parallel on aarch64 with llvm-16
bpf/vmtest-bpf-VM_Test-31 success Logs for test_progs_parallel on s390x with gcc
bpf/vmtest-bpf-VM_Test-32 success Logs for test_progs_parallel on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-33 success Logs for test_progs_parallel on x86_64 with llvm-16
bpf/vmtest-bpf-VM_Test-34 success Logs for test_verifier on aarch64 with gcc
bpf/vmtest-bpf-VM_Test-35 success Logs for test_verifier on aarch64 with llvm-16
bpf/vmtest-bpf-VM_Test-36 success Logs for test_verifier on s390x with gcc
bpf/vmtest-bpf-VM_Test-37 success Logs for test_verifier on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-38 success Logs for test_verifier on x86_64 with llvm-16

Commit Message

Christophe Leroy Dec. 1, 2022, 7:56 a.m. UTC 
Now that two real additional passes are performed in case of extra pass
requested by BPF core, padding is not needed anymore except during
initial pass done before memory allocation to count maximum possible
program size.

So, only do the padding when 'image' is NULL.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
 arch/powerpc/net/bpf_jit_comp32.c |  8 +++-----
 arch/powerpc/net/bpf_jit_comp64.c | 12 +++++++-----
 2 files changed, 10 insertions(+), 10 deletions(-)
diff mbox series

Patch

diff --git a/arch/powerpc/net/bpf_jit_comp32.c b/arch/powerpc/net/bpf_jit_comp32.c
index 7c129fe810f5..6c45d953d4e8 100644
--- a/arch/powerpc/net/bpf_jit_comp32.c
+++ b/arch/powerpc/net/bpf_jit_comp32.c
@@ -206,9 +206,6 @@  int bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 func
 
 	if (image && rel < 0x2000000 && rel >= -0x2000000) {
 		PPC_BL(func);
-		EMIT(PPC_RAW_NOP());
-		EMIT(PPC_RAW_NOP());
-		EMIT(PPC_RAW_NOP());
 	} else {
 		/* Load function address into r0 */
 		EMIT(PPC_RAW_LIS(_R0, IMM_H(func)));
@@ -973,8 +970,9 @@  int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 			PPC_LI32(dst_reg_h, (u32)insn[i + 1].imm);
 			PPC_LI32(dst_reg, (u32)insn[i].imm);
 			/* padding to allow full 4 instructions for later patching */
-			for (j = ctx->idx - tmp_idx; j < 4; j++)
-				EMIT(PPC_RAW_NOP());
+			if (!image)
+				for (j = ctx->idx - tmp_idx; j < 4; j++)
+					EMIT(PPC_RAW_NOP());
 			/* Adjust for two bpf instructions */
 			addrs[++i] = ctx->idx * 4;
 			break;
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 29ee306d6302..1c2931b4bc15 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -240,13 +240,14 @@  int bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 func
 	 * load the callee's address, but this may optimize the number of
 	 * instructions required based on the nature of the address.
 	 *
-	 * Since we don't want the number of instructions emitted to change,
+	 * Since we don't want the number of instructions emitted to increase,
 	 * we pad the optimized PPC_LI64() call with NOPs to guarantee that
 	 * we always have a five-instruction sequence, which is the maximum
 	 * that PPC_LI64() can emit.
 	 */
-	for (i = ctx->idx - ctx_idx; i < 5; i++)
-		EMIT(PPC_RAW_NOP());
+	if (!image)
+		for (i = ctx->idx - ctx_idx; i < 5; i++)
+			EMIT(PPC_RAW_NOP());
 
 	EMIT(PPC_RAW_MTCTR(_R12));
 	EMIT(PPC_RAW_BCTRL());
@@ -938,8 +939,9 @@  int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 			tmp_idx = ctx->idx;
 			PPC_LI64(dst_reg, imm64);
 			/* padding to allow full 5 instructions for later patching */
-			for (j = ctx->idx - tmp_idx; j < 5; j++)
-				EMIT(PPC_RAW_NOP());
+			if (!image)
+				for (j = ctx->idx - tmp_idx; j < 5; j++)
+					EMIT(PPC_RAW_NOP());
 			/* Adjust for two bpf instructions */
 			addrs[++i] = ctx->idx * 4;
 			break;