powerpc/bpf: use bpf_jit_binary_pack_[alloc|finalize|free]

commit 90d862f370 upstream.

Use bpf_jit_binary_pack_alloc in powerpc jit. The jit engine first
writes the program to the rw buffer. When the jit is done, the program
is copied to the final location with bpf_jit_binary_pack_finalize.
With multiple jit_subprogs, bpf_jit_free is called on some subprograms
that haven't got bpf_jit_binary_pack_finalize() yet. Implement custom
bpf_jit_free() like in commit 1d5f82d9dd ("bpf, x86: fix freeing of
not-finalized bpf_prog_pack") to call bpf_jit_binary_pack_finalize(),
if necessary. As bpf_flush_icache() is not needed anymore, remove it.

Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
Acked-by: Song Liu <song@kernel.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://msgid.link/20231020141358.643575-6-hbathini@linux.ibm.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

arch/powerpc/net/bpf_jit.h

@@ -36,9 +36,6 @@
 		EMIT(PPC_RAW_BRANCH(offset));				      \
 	} while (0)
 
-/* bl (unconditional 'branch' with link) */
-#define PPC_BL(dest)	EMIT(PPC_RAW_BL((dest) - (unsigned long)(image + ctx->idx)))
-
 /* "cond" here covers BO:BI fields. */
 #define PPC_BCC_SHORT(cond, dest)					      \
 	do {								      \
@@ -147,12 +144,6 @@ struct codegen_context {
 #define BPF_FIXUP_LEN	2 /* Two instructions => 8 bytes */
 #endif
 
-static inline void bpf_flush_icache(void *start, void *end)
-{
-	smp_wmb();	/* smp write barrier */
-	flush_icache_range((unsigned long)start, (unsigned long)end);
-}
-
 static inline bool bpf_is_seen_register(struct codegen_context *ctx, int i)
 {
 	return ctx->seen & (1 << (31 - i));
@@ -169,16 +160,17 @@ static inline void bpf_clear_seen_register(struct codegen_context *ctx, int i)
 }
 
 void bpf_jit_init_reg_mapping(struct codegen_context *ctx);
-int bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 func);
-int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *ctx,
+int bpf_jit_emit_func_call_rel(u32 *image, u32 *fimage, struct codegen_context *ctx, u64 func);
+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_realloc_regs(struct codegen_context *ctx);
 int bpf_jit_emit_exit_insn(u32 *image, struct codegen_context *ctx, int tmp_reg, long exit_addr);
 
-int bpf_add_extable_entry(struct bpf_prog *fp, u32 *image, int pass, struct codegen_context *ctx,
-			  int insn_idx, int jmp_off, int dst_reg);
+int bpf_add_extable_entry(struct bpf_prog *fp, u32 *image, u32 *fimage, int pass,
+			  struct codegen_context *ctx, int insn_idx,
+			  int jmp_off, int dst_reg);
 
 #endif
 

arch/powerpc/net/bpf_jit_comp.c

@@ -40,9 +40,12 @@ int bpf_jit_emit_exit_insn(u32 *image, struct codegen_context *ctx, int tmp_reg,
 }
 
 struct powerpc_jit_data {
-	struct bpf_binary_header *header;
+	/* address of rw header */
+	struct bpf_binary_header *hdr;
+	/* address of ro final header */
+	struct bpf_binary_header *fhdr;
 	u32 *addrs;
-	u8 *image;
+	u8 *fimage;
 	u32 proglen;
 	struct codegen_context ctx;
 };
@@ -63,11 +66,14 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	struct codegen_context cgctx;
 	int pass;
 	int flen;
-	struct bpf_binary_header *bpf_hdr;
+	struct bpf_binary_header *fhdr = NULL;
+	struct bpf_binary_header *hdr = NULL;
 	struct bpf_prog *org_fp = fp;
 	struct bpf_prog *tmp_fp;
 	bool bpf_blinded = false;
 	bool extra_pass = false;
+	u8 *fimage = NULL;
+	u32 *fcode_base;
 	u32 extable_len;
 	u32 fixup_len;
 
@@ -97,9 +103,16 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	addrs = jit_data->addrs;
 	if (addrs) {
 		cgctx = jit_data->ctx;
-		image = jit_data->image;
-		bpf_hdr = jit_data->header;
+		/*
+		 * JIT compiled to a writable location (image/code_base) first.
+		 * It is then moved to the readonly final location (fimage/fcode_base)
+		 * using instruction patching.
+		 */
+		fimage = jit_data->fimage;
+		fhdr = jit_data->fhdr;
 		proglen = jit_data->proglen;
+		hdr = jit_data->hdr;
+		image = (void *)hdr + ((void *)fimage - (void *)fhdr);
 		extra_pass = true;
 		/* During extra pass, ensure index is reset before repopulating extable entries */
 		cgctx.exentry_idx = 0;
@@ -119,7 +132,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	cgctx.stack_size = round_up(fp->aux->stack_depth, 16);
 
 	/* Scouting faux-generate pass 0 */
-	if (bpf_jit_build_body(fp, 0, &cgctx, addrs, 0, false)) {
+	if (bpf_jit_build_body(fp, NULL, NULL, &cgctx, addrs, 0, false)) {
 		/* We hit something illegal or unsupported. */
 		fp = org_fp;
 		goto out_addrs;
@@ -134,7 +147,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	 */
 	if (cgctx.seen & SEEN_TAILCALL || !is_offset_in_branch_range((long)cgctx.idx * 4)) {
 		cgctx.idx = 0;
-		if (bpf_jit_build_body(fp, 0, &cgctx, addrs, 0, false)) {
+		if (bpf_jit_build_body(fp, NULL, NULL, &cgctx, addrs, 0, false)) {
 			fp = org_fp;
 			goto out_addrs;
 		}
@@ -156,17 +169,19 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	proglen = cgctx.idx * 4;
 	alloclen = proglen + FUNCTION_DESCR_SIZE + fixup_len + extable_len;
 
-	bpf_hdr = bpf_jit_binary_alloc(alloclen, &image, 4, bpf_jit_fill_ill_insns);
-	if (!bpf_hdr) {
+	fhdr = bpf_jit_binary_pack_alloc(alloclen, &fimage, 4, &hdr, &image,
+					      bpf_jit_fill_ill_insns);
+	if (!fhdr) {
 		fp = org_fp;
 		goto out_addrs;
 	}
 
 	if (extable_len)
-		fp->aux->extable = (void *)image + FUNCTION_DESCR_SIZE + proglen + fixup_len;
+		fp->aux->extable = (void *)fimage + FUNCTION_DESCR_SIZE + proglen + fixup_len;
 
 skip_init_ctx:
 	code_base = (u32 *)(image + FUNCTION_DESCR_SIZE);
+	fcode_base = (u32 *)(fimage + FUNCTION_DESCR_SIZE);
 
 	/* Code generation passes 1-2 */
 	for (pass = 1; pass < 3; pass++) {
@@ -174,8 +189,10 @@ skip_init_ctx:
 		cgctx.idx = 0;
 		cgctx.alt_exit_addr = 0;
 		bpf_jit_build_prologue(code_base, &cgctx);
-		if (bpf_jit_build_body(fp, code_base, &cgctx, addrs, pass, extra_pass)) {
-			bpf_jit_binary_free(bpf_hdr);
+		if (bpf_jit_build_body(fp, code_base, fcode_base, &cgctx, addrs, pass,
+				       extra_pass)) {
+			bpf_arch_text_copy(&fhdr->size, &hdr->size, sizeof(hdr->size));
+			bpf_jit_binary_pack_free(fhdr, hdr);
 			fp = org_fp;
 			goto out_addrs;
 		}
@@ -195,17 +212,19 @@ skip_init_ctx:
 
 #ifdef CONFIG_PPC64_ELF_ABI_V1
 	/* Function descriptor nastiness: Address + TOC */
-	((u64 *)image)[0] = (u64)code_base;
+	((u64 *)image)[0] = (u64)fcode_base;
 	((u64 *)image)[1] = local_paca->kernel_toc;
 #endif
 
-	fp->bpf_func = (void *)image;
+	fp->bpf_func = (void *)fimage;
 	fp->jited = 1;
 	fp->jited_len = proglen + FUNCTION_DESCR_SIZE;
 
-	bpf_flush_icache(bpf_hdr, (u8 *)bpf_hdr + bpf_hdr->size);
 	if (!fp->is_func || extra_pass) {
-		bpf_jit_binary_lock_ro(bpf_hdr);
+		if (bpf_jit_binary_pack_finalize(fp, fhdr, hdr)) {
+			fp = org_fp;
+			goto out_addrs;
+		}
 		bpf_prog_fill_jited_linfo(fp, addrs);
 out_addrs:
 		kfree(addrs);
@@ -215,8 +234,9 @@ out_addrs:
 		jit_data->addrs = addrs;
 		jit_data->ctx = cgctx;
 		jit_data->proglen = proglen;
-		jit_data->image = image;
-		jit_data->header = bpf_hdr;
+		jit_data->fimage = fimage;
+		jit_data->fhdr = fhdr;
+		jit_data->hdr = hdr;
 	}
 
 out:
@@ -230,12 +250,13 @@ out:
  * The caller should check for (BPF_MODE(code) == BPF_PROBE_MEM) before calling
  * this function, as this only applies to BPF_PROBE_MEM, for now.
  */
-int bpf_add_extable_entry(struct bpf_prog *fp, u32 *image, int pass, struct codegen_context *ctx,
-			  int insn_idx, int jmp_off, int dst_reg)
+int bpf_add_extable_entry(struct bpf_prog *fp, u32 *image, u32 *fimage, int pass,
+			  struct codegen_context *ctx, int insn_idx, int jmp_off,
+			  int dst_reg)
 {
 	off_t offset;
 	unsigned long pc;
-	struct exception_table_entry *ex;
+	struct exception_table_entry *ex, *ex_entry;
 	u32 *fixup;
 
 	/* Populate extable entries only in the last pass */
@@ -246,9 +267,16 @@ int bpf_add_extable_entry(struct bpf_prog *fp, u32 *image, int pass, struct code
 	    WARN_ON_ONCE(ctx->exentry_idx >= fp->aux->num_exentries))
 		return -EINVAL;
 
+	/*
+	 * Program is first written to image before copying to the
+	 * final location (fimage). Accordingly, update in the image first.
+	 * As all offsets used are relative, copying as is to the
+	 * final location should be alright.
+	 */
 	pc = (unsigned long)&image[insn_idx];
+	ex = (void *)fp->aux->extable - (void *)fimage + (void *)image;
 
-	fixup = (void *)fp->aux->extable -
+	fixup = (void *)ex -
 		(fp->aux->num_exentries * BPF_FIXUP_LEN * 4) +
 		(ctx->exentry_idx * BPF_FIXUP_LEN * 4);
 
@@ -259,18 +287,42 @@ int bpf_add_extable_entry(struct bpf_prog *fp, u32 *image, int pass, struct code
 	fixup[BPF_FIXUP_LEN - 1] =
 		PPC_RAW_BRANCH((long)(pc + jmp_off) - (long)&fixup[BPF_FIXUP_LEN - 1]);
 
-	ex = &fp->aux->extable[ctx->exentry_idx];
+	ex_entry = &ex[ctx->exentry_idx];
 
-	offset = pc - (long)&ex->insn;
+	offset = pc - (long)&ex_entry->insn;
 	if (WARN_ON_ONCE(offset >= 0 || offset < INT_MIN))
 		return -ERANGE;
-	ex->insn = offset;
+	ex_entry->insn = offset;
 
-	offset = (long)fixup - (long)&ex->fixup;
+	offset = (long)fixup - (long)&ex_entry->fixup;
 	if (WARN_ON_ONCE(offset >= 0 || offset < INT_MIN))
 		return -ERANGE;
-	ex->fixup = offset;
+	ex_entry->fixup = offset;
 
 	ctx->exentry_idx++;
 	return 0;
 }
+
+void bpf_jit_free(struct bpf_prog *fp)
+{
+	if (fp->jited) {
+		struct powerpc_jit_data *jit_data = fp->aux->jit_data;
+		struct bpf_binary_header *hdr;
+
+		/*
+		 * If we fail the final pass of JIT (from jit_subprogs),
+		 * the program may not be finalized yet. Call finalize here
+		 * before freeing it.
+		 */
+		if (jit_data) {
+			bpf_jit_binary_pack_finalize(fp, jit_data->fhdr, jit_data->hdr);
+			kvfree(jit_data->addrs);
+			kfree(jit_data);
+		}
+		hdr = bpf_jit_binary_pack_hdr(fp);
+		bpf_jit_binary_pack_free(hdr, NULL);
+		WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(fp));
+	}
+
+	bpf_prog_unlock_free(fp);
+}

arch/powerpc/net/bpf_jit_comp32.c

@@ -200,12 +200,13 @@ void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
 	EMIT(PPC_RAW_BLR());
 }
 
-int bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 func)
+/* Relative offset needs to be calculated based on final image location */
+int bpf_jit_emit_func_call_rel(u32 *image, u32 *fimage, struct codegen_context *ctx, u64 func)
 {
-	s32 rel = (s32)func - (s32)(image + ctx->idx);
+	s32 rel = (s32)func - (s32)(fimage + ctx->idx);
 
 	if (image && rel < 0x2000000 && rel >= -0x2000000) {
-		PPC_BL(func);
+		EMIT(PPC_RAW_BL(rel));
 	} else {
 		/* Load function address into r0 */
 		EMIT(PPC_RAW_LIS(_R0, IMM_H(func)));
@@ -278,7 +279,7 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o
 }
 
 /* Assemble the body code between the prologue & epilogue */
-int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *ctx,
+int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct codegen_context *ctx,
 		       u32 *addrs, int pass, bool extra_pass)
 {
 	const struct bpf_insn *insn = fp->insnsi;
@@ -1009,7 +1010,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 					jmp_off += 4;
 				}
 
-				ret = bpf_add_extable_entry(fp, image, pass, ctx, insn_idx,
+				ret = bpf_add_extable_entry(fp, image, fimage, pass, ctx, insn_idx,
 							    jmp_off, dst_reg);
 				if (ret)
 					return ret;
@@ -1065,7 +1066,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 				EMIT(PPC_RAW_STW(bpf_to_ppc(BPF_REG_5), _R1, 12));
 			}
 
-			ret = bpf_jit_emit_func_call_rel(image, ctx, func_addr);
+			ret = bpf_jit_emit_func_call_rel(image, fimage, ctx, func_addr);
 			if (ret)
 				return ret;
 

arch/powerpc/net/bpf_jit_comp64.c

@@ -240,7 +240,7 @@ static int bpf_jit_emit_func_call_hlp(u32 *image, struct codegen_context *ctx, u
 	return 0;
 }
 
-int bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 func)
+int bpf_jit_emit_func_call_rel(u32 *image, u32 *fimage, struct codegen_context *ctx, u64 func)
 {
 	unsigned int i, ctx_idx = ctx->idx;
 
@@ -361,7 +361,7 @@ asm (
 );
 
 /* Assemble the body code between the prologue & epilogue */
-int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *ctx,
+int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct codegen_context *ctx,
 		       u32 *addrs, int pass, bool extra_pass)
 {
 	enum stf_barrier_type stf_barrier = stf_barrier_type_get();
@@ -952,8 +952,8 @@ emit_clear:
 				addrs[++i] = ctx->idx * 4;
 
 			if (BPF_MODE(code) == BPF_PROBE_MEM) {
-				ret = bpf_add_extable_entry(fp, image, pass, ctx, ctx->idx - 1,
-							    4, dst_reg);
+				ret = bpf_add_extable_entry(fp, image, fimage, pass, ctx,
+							    ctx->idx - 1, 4, dst_reg);
 				if (ret)
 					return ret;
 			}
@@ -1007,7 +1007,7 @@ emit_clear:
 			if (func_addr_fixed)
 				ret = bpf_jit_emit_func_call_hlp(image, ctx, func_addr);
 			else
-				ret = bpf_jit_emit_func_call_rel(image, ctx, func_addr);
+				ret = bpf_jit_emit_func_call_rel(image, fimage, ctx, func_addr);
 
 			if (ret)
 				return ret;