Merge tag 'bpf-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf

Pull bpf fixes from Alexei Starovoitov:
 "Most of the diff stat comes from Xu Kuohai's fix to emit ENDBR/BTI,
  since all JITs had to be touched to move constant blinding out and
  pass bpf_verifier_env in.

   - Fix use-after-free in arena_vm_close on fork (Alexei Starovoitov)

   - Dissociate struct_ops program with map if map_update fails (Amery
     Hung)

   - Fix out-of-range and off-by-one bugs in arm64 JIT (Daniel Borkmann)

   - Fix precedence bug in convert_bpf_ld_abs alignment check (Daniel
     Borkmann)

   - Fix arg tracking for imprecise/multi-offset in BPF_ST/STX insns
     (Eduard Zingerman)

   - Copy token from main to subprogs to fix missing kallsyms (Eduard
     Zingerman)

   - Prevent double close and leak of btf objects in libbpf (Jiri Olsa)

   - Fix af_unix null-ptr-deref in sockmap (Michal Luczaj)

   - Fix NULL deref in map_kptr_match_type for scalar regs (Mykyta
     Yatsenko)

   - Avoid unnecessary IPIs. Remove redundant bpf_flush_icache() in
     arm64 and riscv JITs (Puranjay Mohan)

   - Fix out of bounds access. Validate node_id in arena_alloc_pages()
     (Puranjay Mohan)

   - Reject BPF-to-BPF calls and callbacks in arm32 JIT (Puranjay Mohan)

   - Refactor all JITs to pass bpf_verifier_env to emit ENDBR/BTI for
     indirect jump targets on x86-64, arm64 JITs (Xu Kuohai)

   - Allow UTF-8 literals in bpf_bprintf_prepare() (Yihan Ding)"

* tag 'bpf-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf: (32 commits)
  bpf, arm32: Reject BPF-to-BPF calls and callbacks in the JIT
  bpf: Dissociate struct_ops program with map if map_update fails
  bpf: Validate node_id in arena_alloc_pages()
  libbpf: Prevent double close and leak of btf objects
  selftests/bpf: cover UTF-8 trace_printk output
  bpf: allow UTF-8 literals in bpf_bprintf_prepare()
  selftests/bpf: Reject scalar store into kptr slot
  bpf: Fix NULL deref in map_kptr_match_type for scalar regs
  bpf: Fix precedence bug in convert_bpf_ld_abs alignment check
  bpf, arm64: Emit BTI for indirect jump target
  bpf, x86: Emit ENDBR for indirect jump targets
  bpf: Add helper to detect indirect jump targets
  bpf: Pass bpf_verifier_env to JIT
  bpf: Move constants blinding out of arch-specific JITs
  bpf, sockmap: Take state lock for af_unix iter
  bpf, sockmap: Fix af_unix null-ptr-deref in proto update
  selftests/bpf: Extend bpf_iter_unix to attempt deadlocking
  bpf, sockmap: Fix af_unix iter deadlock
  bpf, sockmap: Annotate af_unix sock:: Sk_state data-races
  selftests/bpf: verify kallsyms entries for token-loaded subprograms
  ...

arch/arc/net/bpf_jit_core.c

@@ -79,7 +79,6 @@ struct arc_jit_data {
  * The JIT pertinent context that is used by different functions.
  *
  * prog:		The current eBPF program being handled.
- * orig_prog:		The original eBPF program before any possible change.
  * jit:			The JIT buffer and its length.
  * bpf_header:		The JITed program header. "jit.buf" points inside it.
  * emit:		If set, opcodes are written to memory; else, a dry-run.
@@ -94,12 +93,10 @@ struct arc_jit_data {
  * need_extra_pass:	A forecast if an "extra_pass" will occur.
  * is_extra_pass:	Indicates if the current pass is an extra pass.
  * user_bpf_prog:	True, if VM opcodes come from a real program.
- * blinded:		True if "constant blinding" step returned a new "prog".
  * success:		Indicates if the whole JIT went OK.
  */
 struct jit_context {
 	struct bpf_prog			*prog;
-	struct bpf_prog			*orig_prog;
 	struct jit_buffer		jit;
 	struct bpf_binary_header	*bpf_header;
 	bool				emit;
@@ -114,7 +111,6 @@ struct jit_context {
 	bool				need_extra_pass;
 	bool				is_extra_pass;
 	bool				user_bpf_prog;
-	bool				blinded;
 	bool				success;
 };
 
@@ -161,13 +157,7 @@ static int jit_ctx_init(struct jit_context *ctx, struct bpf_prog *prog)
 {
 	memset(ctx, 0, sizeof(*ctx));
 
-	ctx->orig_prog = prog;
-
-	/* If constant blinding was requested but failed, scram. */
-	ctx->prog = bpf_jit_blind_constants(prog);
-	if (IS_ERR(ctx->prog))
-		return PTR_ERR(ctx->prog);
-	ctx->blinded = (ctx->prog != ctx->orig_prog);
+	ctx->prog = prog;
 
 	/* If the verifier doesn't zero-extend, then we have to do it. */
 	ctx->do_zext = !ctx->prog->aux->verifier_zext;
@@ -214,14 +204,6 @@ static inline void maybe_free(struct jit_context *ctx, void **mem)
  */
 static void jit_ctx_cleanup(struct jit_context *ctx)
 {
-	if (ctx->blinded) {
-		/* if all went well, release the orig_prog. */
-		if (ctx->success)
-			bpf_jit_prog_release_other(ctx->prog, ctx->orig_prog);
-		else
-			bpf_jit_prog_release_other(ctx->orig_prog, ctx->prog);
-	}
-
 	maybe_free(ctx, (void **)&ctx->bpf2insn);
 	maybe_free(ctx, (void **)&ctx->jit_data);
 
@@ -229,12 +211,19 @@ static void jit_ctx_cleanup(struct jit_context *ctx)
 		ctx->bpf2insn_valid = false;
 
 	/* Freeing "bpf_header" is enough. "jit.buf" is a sub-array of it. */
-	if (!ctx->success && ctx->bpf_header) {
-		bpf_jit_binary_free(ctx->bpf_header);
-		ctx->bpf_header = NULL;
-		ctx->jit.buf    = NULL;
-		ctx->jit.index  = 0;
-		ctx->jit.len    = 0;
+	if (!ctx->success) {
+		if (ctx->bpf_header) {
+			bpf_jit_binary_free(ctx->bpf_header);
+			ctx->bpf_header = NULL;
+			ctx->jit.buf    = NULL;
+			ctx->jit.index  = 0;
+			ctx->jit.len    = 0;
+		}
+		if (ctx->is_extra_pass) {
+			ctx->prog->bpf_func = NULL;
+			ctx->prog->jited = 0;
+			ctx->prog->jited_len = 0;
+		}
 	}
 
 	ctx->emit = false;
@@ -1411,7 +1400,7 @@ static struct bpf_prog *do_extra_pass(struct bpf_prog *prog)
  * (re)locations involved that their addresses are not known
  * during the first run.
  */
-struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
+struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_prog *prog)
 {
 	vm_dump(prog);
 

arch/arm/net/bpf_jit_32.c

@@ -1852,6 +1852,9 @@ exit:
 	{
 		u64 val = (u32)imm | (u64)insn[1].imm << 32;
 
+		if (insn->src_reg == BPF_PSEUDO_FUNC)
+			goto notyet;
+
 		emit_a32_mov_i64(dst, val, ctx);
 
 		return 1;
@@ -2055,6 +2058,9 @@ go_jmp:
 		const s8 *r5 = bpf2a32[BPF_REG_5];
 		const u32 func = (u32)__bpf_call_base + (u32)imm;
 
+		if (insn->src_reg == BPF_PSEUDO_CALL)
+			goto notyet;
+
 		emit_a32_mov_r64(true, r0, r1, ctx);
 		emit_a32_mov_r64(true, r1, r2, ctx);
 		emit_push_r64(r5, ctx);
@@ -2142,11 +2148,9 @@ bool bpf_jit_needs_zext(void)
 	return true;
 }
 
-struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
+struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_prog *prog)
 {
-	struct bpf_prog *tmp, *orig_prog = prog;
 	struct bpf_binary_header *header;
-	bool tmp_blinded = false;
 	struct jit_ctx ctx;
 	unsigned int tmp_idx;
 	unsigned int image_size;
@@ -2156,20 +2160,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	 * the interpreter.
 	 */
 	if (!prog->jit_requested)
-		return orig_prog;
-
-	/* If constant blinding was enabled and we failed during blinding
-	 * then we must fall back to the interpreter. Otherwise, we save
-	 * the new JITed code.
-	 */
-	tmp = bpf_jit_blind_constants(prog);
-
-	if (IS_ERR(tmp))
-		return orig_prog;
-	if (tmp != prog) {
-		tmp_blinded = true;
-		prog = tmp;
-	}
+		return prog;
 
 	memset(&ctx, 0, sizeof(ctx));
 	ctx.prog = prog;
@@ -2179,10 +2170,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	 * we must fall back to the interpreter
 	 */
 	ctx.offsets = kcalloc(prog->len, sizeof(int), GFP_KERNEL);
-	if (ctx.offsets == NULL) {
-		prog = orig_prog;
-		goto out;
-	}
+	if (ctx.offsets == NULL)
+		return prog;
 
 	/* 1) fake pass to find in the length of the JITed code,
 	 * to compute ctx->offsets and other context variables
@@ -2194,10 +2183,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	 * being successful in the second pass, so just fall back
 	 * to the interpreter.
 	 */
-	if (build_body(&ctx)) {
-		prog = orig_prog;
+	if (build_body(&ctx))
 		goto out_off;
-	}
 
 	tmp_idx = ctx.idx;
 	build_prologue(&ctx);
@@ -2213,10 +2200,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	ctx.idx += ctx.imm_count;
 	if (ctx.imm_count) {
 		ctx.imms = kcalloc(ctx.imm_count, sizeof(u32), GFP_KERNEL);
-		if (ctx.imms == NULL) {
-			prog = orig_prog;
+		if (ctx.imms == NULL)
 			goto out_off;
-		}
 	}
 #else
 	/* there's nothing about the epilogue on ARMv7 */
@@ -2238,10 +2223,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	/* Not able to allocate memory for the structure then
 	 * we must fall back to the interpretation
 	 */
-	if (header == NULL) {
-		prog = orig_prog;
+	if (header == NULL)
 		goto out_imms;
-	}
 
 	/* 2.) Actual pass to generate final JIT code */
 	ctx.target = (u32 *) image_ptr;
@@ -2278,16 +2261,12 @@ out_imms:
 #endif
 out_off:
 	kfree(ctx.offsets);
-out:
-	if (tmp_blinded)
-		bpf_jit_prog_release_other(prog, prog == orig_prog ?
-					   tmp : orig_prog);
+
 	return prog;
 
 out_free:
 	image_ptr = NULL;
 	bpf_jit_binary_free(header);
-	prog = orig_prog;
 	goto out_imms;
 }
 

arch/arm64/lib/insn.c

@@ -338,6 +338,8 @@ u32 aarch64_insn_gen_cond_branch_imm(unsigned long pc, unsigned long addr,
 	long offset;
 
 	offset = label_imm_common(pc, addr, SZ_1M);
+	if (offset >= SZ_1M)
+		return AARCH64_BREAK_FAULT;
 
 	insn = aarch64_insn_get_bcond_value();
 

arch/arm64/net/bpf_jit_comp.c

@@ -18,7 +18,6 @@
 
 #include <asm/asm-extable.h>
 #include <asm/byteorder.h>
-#include <asm/cacheflush.h>
 #include <asm/cpufeature.h>
 #include <asm/debug-monitors.h>
 #include <asm/insn.h>
@@ -35,8 +34,8 @@
 #define ARENA_VM_START (MAX_BPF_JIT_REG + 5)
 
 #define check_imm(bits, imm) do {				\
-	if ((((imm) > 0) && ((imm) >> (bits))) ||		\
-	    (((imm) < 0) && (~(imm) >> (bits)))) {		\
+	if ((((imm) > 0) && ((imm) >> ((bits) - 1))) ||		\
+	    (((imm) < 0) && (~(imm) >> ((bits) - 1)))) {	\
 		pr_info("[%2d] imm=%d(0x%x) out of range\n",	\
 			i, imm, imm);				\
 		return -EINVAL;					\
@@ -1198,8 +1197,8 @@ static int add_exception_handler(const struct bpf_insn *insn,
  * >0 - successfully JITed a 16-byte eBPF instruction.
  * <0 - failed to JIT.
  */
-static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
-		      bool extra_pass)
+static int build_insn(const struct bpf_verifier_env *env, const struct bpf_insn *insn,
+		      struct jit_ctx *ctx, bool extra_pass)
 {
 	const u8 code = insn->code;
 	u8 dst = bpf2a64[insn->dst_reg];
@@ -1224,6 +1223,9 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
 	int ret;
 	bool sign_extend;
 
+	if (bpf_insn_is_indirect_target(env, ctx->prog, i))
+		emit_bti(A64_BTI_J, ctx);
+
 	switch (code) {
 	/* dst = src */
 	case BPF_ALU | BPF_MOV | BPF_X:
@@ -1899,7 +1901,7 @@ emit_cond_jmp:
 	return 0;
 }
 
-static int build_body(struct jit_ctx *ctx, bool extra_pass)
+static int build_body(struct bpf_verifier_env *env, struct jit_ctx *ctx, bool extra_pass)
 {
 	const struct bpf_prog *prog = ctx->prog;
 	int i;
@@ -1918,7 +1920,7 @@ static int build_body(struct jit_ctx *ctx, bool extra_pass)
 		int ret;
 
 		ctx->offset[i] = ctx->idx;
-		ret = build_insn(insn, ctx, extra_pass);
+		ret = build_insn(env, insn, ctx, extra_pass);
 		if (ret > 0) {
 			i++;
 			ctx->offset[i] = ctx->idx;
@@ -1961,11 +1963,6 @@ static int validate_ctx(struct jit_ctx *ctx)
 	return 0;
 }
 
-static inline void bpf_flush_icache(void *start, void *end)
-{
-	flush_icache_range((unsigned long)start, (unsigned long)end);
-}
-
 static void priv_stack_init_guard(void __percpu *priv_stack_ptr, int alloc_size)
 {
 	int cpu, underflow_idx = (alloc_size - PRIV_STACK_GUARD_SZ) >> 3;
@@ -2006,17 +2003,15 @@ struct arm64_jit_data {
 	struct jit_ctx ctx;
 };
 
-struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
+struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_prog *prog)
 {
 	int image_size, prog_size, extable_size, extable_align, extable_offset;
-	struct bpf_prog *tmp, *orig_prog = prog;
 	struct bpf_binary_header *header;
 	struct bpf_binary_header *ro_header = NULL;
 	struct arm64_jit_data *jit_data;
 	void __percpu *priv_stack_ptr = NULL;
 	bool was_classic = bpf_prog_was_classic(prog);
 	int priv_stack_alloc_sz;
-	bool tmp_blinded = false;
 	bool extra_pass = false;
 	struct jit_ctx ctx;
 	u8 *image_ptr;
@@ -2025,26 +2020,13 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	int exentry_idx;
 
 	if (!prog->jit_requested)
-		return orig_prog;
-
-	tmp = bpf_jit_blind_constants(prog);
-	/* If blinding was requested and we failed during blinding,
-	 * we must fall back to the interpreter.
-	 */
-	if (IS_ERR(tmp))
-		return orig_prog;
-	if (tmp != prog) {
-		tmp_blinded = true;
-		prog = tmp;
-	}
+		return prog;
 
 	jit_data = prog->aux->jit_data;
 	if (!jit_data) {
 		jit_data = kzalloc_obj(*jit_data);
-		if (!jit_data) {
-			prog = orig_prog;
-			goto out;
-		}
+		if (!jit_data)
+			return prog;
 		prog->aux->jit_data = jit_data;
 	}
 	priv_stack_ptr = prog->aux->priv_stack_ptr;
@@ -2056,10 +2038,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		priv_stack_alloc_sz = round_up(prog->aux->stack_depth, 16) +
 				      2 * PRIV_STACK_GUARD_SZ;
 		priv_stack_ptr = __alloc_percpu_gfp(priv_stack_alloc_sz, 16, GFP_KERNEL);
-		if (!priv_stack_ptr) {
-			prog = orig_prog;
+		if (!priv_stack_ptr)
 			goto out_priv_stack;
-		}
 
 		priv_stack_init_guard(priv_stack_ptr, priv_stack_alloc_sz);
 		prog->aux->priv_stack_ptr = priv_stack_ptr;
@@ -2079,10 +2059,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	ctx.prog = prog;
 
 	ctx.offset = kvzalloc_objs(int, prog->len + 1);
-	if (ctx.offset == NULL) {
-		prog = orig_prog;
+	if (ctx.offset == NULL)
 		goto out_off;
-	}
 
 	ctx.user_vm_start = bpf_arena_get_user_vm_start(prog->aux->arena);
 	ctx.arena_vm_start = bpf_arena_get_kern_vm_start(prog->aux->arena);
@@ -2095,15 +2073,11 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	 * BPF line info needs ctx->offset[i] to be the offset of
 	 * instruction[i] in jited image, so build prologue first.
 	 */
-	if (build_prologue(&ctx, was_classic)) {
-		prog = orig_prog;
+	if (build_prologue(&ctx, was_classic))
 		goto out_off;
-	}
 
-	if (build_body(&ctx, extra_pass)) {
-		prog = orig_prog;
+	if (build_body(env, &ctx, extra_pass))
 		goto out_off;
-	}
 
 	ctx.epilogue_offset = ctx.idx;
 	build_epilogue(&ctx, was_classic);
@@ -2121,10 +2095,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	ro_header = bpf_jit_binary_pack_alloc(image_size, &ro_image_ptr,
 					      sizeof(u64), &header, &image_ptr,
 					      jit_fill_hole);
-	if (!ro_header) {
-		prog = orig_prog;
+	if (!ro_header)
 		goto out_off;
-	}
 
 	/* Pass 2: Determine jited position and result for each instruction */
 
@@ -2152,10 +2124,8 @@ skip_init_ctx:
 	/* Dont write body instructions to memory for now */
 	ctx.write = false;
 
-	if (build_body(&ctx, extra_pass)) {
-		prog = orig_prog;
+	if (build_body(env, &ctx, extra_pass))
 		goto out_free_hdr;
-	}
 
 	ctx.epilogue_offset = ctx.idx;
 	ctx.exentry_idx = exentry_idx;
@@ -2163,20 +2133,16 @@ skip_init_ctx:
 	ctx.write = true;
 
 	/* Pass 3: Adjust jump offset and write final image */
-	if (build_body(&ctx, extra_pass) ||
-		WARN_ON_ONCE(ctx.idx != ctx.epilogue_offset)) {
-		prog = orig_prog;
+	if (build_body(env, &ctx, extra_pass) ||
+		WARN_ON_ONCE(ctx.idx != ctx.epilogue_offset))
 		goto out_free_hdr;
-	}
 
 	build_epilogue(&ctx, was_classic);
 	build_plt(&ctx);
 
 	/* Extra pass to validate JITed code. */
-	if (validate_ctx(&ctx)) {
-		prog = orig_prog;
+	if (validate_ctx(&ctx))
 		goto out_free_hdr;
-	}
 
 	/* update the real prog size */
 	prog_size = sizeof(u32) * ctx.idx;
@@ -2193,23 +2159,14 @@ skip_init_ctx:
 		if (extra_pass && ctx.idx > jit_data->ctx.idx) {
 			pr_err_once("multi-func JIT bug %d > %d\n",
 				    ctx.idx, jit_data->ctx.idx);
-			prog->bpf_func = NULL;
-			prog->jited = 0;
-			prog->jited_len = 0;
 			goto out_free_hdr;
 		}
 		if (WARN_ON(bpf_jit_binary_pack_finalize(ro_header, header))) {
-			/* ro_header has been freed */
+			/* ro_header and header has been freed */
 			ro_header = NULL;
-			prog = orig_prog;
-			goto out_off;
+			header = NULL;
+			goto out_free_hdr;
 		}
-		/*
-		 * The instructions have now been copied to the ROX region from
-		 * where they will execute. Now the data cache has to be cleaned to
-		 * the PoU and the I-cache has to be invalidated for the VAs.
-		 */
-		bpf_flush_icache(ro_header, ctx.ro_image + ctx.idx);
 	} else {
 		jit_data->ctx = ctx;
 		jit_data->ro_image = ro_image_ptr;
@@ -2245,13 +2202,15 @@ out_priv_stack:
 		kfree(jit_data);
 		prog->aux->jit_data = NULL;
 	}
-out:
-	if (tmp_blinded)
-		bpf_jit_prog_release_other(prog, prog == orig_prog ?
-					   tmp : orig_prog);
+
 	return prog;
 
 out_free_hdr:
+	if (extra_pass) {
+		prog->bpf_func = NULL;
+		prog->jited = 0;
+		prog->jited_len = 0;
+	}
 	if (header) {
 		bpf_arch_text_copy(&ro_header->size, &header->size,
 				   sizeof(header->size));

arch/loongarch/net/bpf_jit.c

@@ -1920,45 +1920,28 @@ int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
 	return ret < 0 ? ret : ret * LOONGARCH_INSN_SIZE;
 }
 
-struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
+struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_prog *prog)
 {
-	bool tmp_blinded = false, extra_pass = false;
+	bool extra_pass = false;
 	u8 *image_ptr, *ro_image_ptr;
 	int image_size, prog_size, extable_size;
 	struct jit_ctx ctx;
 	struct jit_data *jit_data;
 	struct bpf_binary_header *header;
 	struct bpf_binary_header *ro_header;
-	struct bpf_prog *tmp, *orig_prog = prog;
 
 	/*
 	 * If BPF JIT was not enabled then we must fall back to
 	 * the interpreter.
 	 */
 	if (!prog->jit_requested)
-		return orig_prog;
-
-	tmp = bpf_jit_blind_constants(prog);
-	/*
-	 * If blinding was requested and we failed during blinding,
-	 * we must fall back to the interpreter. Otherwise, we save
-	 * the new JITed code.
-	 */
-	if (IS_ERR(tmp))
-		return orig_prog;
-
-	if (tmp != prog) {
-		tmp_blinded = true;
-		prog = tmp;
-	}
+		return prog;
 
 	jit_data = prog->aux->jit_data;
 	if (!jit_data) {
 		jit_data = kzalloc_obj(*jit_data);
-		if (!jit_data) {
-			prog = orig_prog;
-			goto out;
-		}
+		if (!jit_data)
+			return prog;
 		prog->aux->jit_data = jit_data;
 	}
 	if (jit_data->ctx.offset) {
@@ -1978,17 +1961,13 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	ctx.user_vm_start = bpf_arena_get_user_vm_start(prog->aux->arena);
 
 	ctx.offset = kvcalloc(prog->len + 1, sizeof(u32), GFP_KERNEL);
-	if (ctx.offset == NULL) {
-		prog = orig_prog;
+	if (ctx.offset == NULL)
 		goto out_offset;
-	}
 
 	/* 1. Initial fake pass to compute ctx->idx and set ctx->flags */
 	build_prologue(&ctx);
-	if (build_body(&ctx, extra_pass)) {
-		prog = orig_prog;
+	if (build_body(&ctx, extra_pass))
 		goto out_offset;
-	}
 	ctx.epilogue_offset = ctx.idx;
 	build_epilogue(&ctx);
 
@@ -2004,10 +1983,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	/* Now we know the size of the structure to make */
 	ro_header = bpf_jit_binary_pack_alloc(image_size, &ro_image_ptr, sizeof(u32),
 					      &header, &image_ptr, jit_fill_hole);
-	if (!ro_header) {
-		prog = orig_prog;
+	if (!ro_header)
 		goto out_offset;
-	}
 
 	/* 2. Now, the actual pass to generate final JIT code */
 	/*
@@ -2027,17 +2004,13 @@ skip_init_ctx:
 	ctx.num_exentries = 0;
 
 	build_prologue(&ctx);
-	if (build_body(&ctx, extra_pass)) {
-		prog = orig_prog;
+	if (build_body(&ctx, extra_pass))
 		goto out_free;
-	}
 	build_epilogue(&ctx);
 
 	/* 3. Extra pass to validate JITed code */
-	if (validate_ctx(&ctx)) {
-		prog = orig_prog;
+	if (validate_ctx(&ctx))
 		goto out_free;
-	}
 
 	/* And we're done */
 	if (bpf_jit_enable > 1)
@@ -2050,9 +2023,9 @@ skip_init_ctx:
 			goto out_free;
 		}
 		if (WARN_ON(bpf_jit_binary_pack_finalize(ro_header, header))) {
-			/* ro_header has been freed */
+			/* ro_header and header have been freed */
 			ro_header = NULL;
-			prog = orig_prog;
+			header = NULL;
 			goto out_free;
 		}
 		/*
@@ -2084,13 +2057,15 @@ out_offset:
 		prog->aux->jit_data = NULL;
 	}
 
-out:
-	if (tmp_blinded)
-		bpf_jit_prog_release_other(prog, prog == orig_prog ? tmp : orig_prog);
-
 	return prog;
 
 out_free:
+	if (extra_pass) {
+		prog->bpf_func = NULL;
+		prog->jited = 0;
+		prog->jited_len = 0;
+	}
+
 	if (header) {
 		bpf_arch_text_copy(&ro_header->size, &header->size, sizeof(header->size));
 		bpf_jit_binary_pack_free(ro_header, header);

arch/mips/net/bpf_jit_comp.c

@@ -909,12 +909,10 @@ bool bpf_jit_needs_zext(void)
 	return true;
 }
 
-struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
+struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_prog *prog)
 {
-	struct bpf_prog *tmp, *orig_prog = prog;
 	struct bpf_binary_header *header = NULL;
 	struct jit_context ctx;
-	bool tmp_blinded = false;
 	unsigned int tmp_idx;
 	unsigned int image_size;
 	u8 *image_ptr;
@@ -925,19 +923,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	 * the interpreter.
 	 */
 	if (!prog->jit_requested)
-		return orig_prog;
-	/*
-	 * If constant blinding was enabled and we failed during blinding
-	 * then we must fall back to the interpreter. Otherwise, we save
-	 * the new JITed code.
-	 */
-	tmp = bpf_jit_blind_constants(prog);
-	if (IS_ERR(tmp))
-		return orig_prog;
-	if (tmp != prog) {
-		tmp_blinded = true;
-		prog = tmp;
-	}
+		return prog;
 
 	memset(&ctx, 0, sizeof(ctx));
 	ctx.program = prog;
@@ -1025,14 +1011,10 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	prog->jited_len = image_size;
 
 out:
-	if (tmp_blinded)
-		bpf_jit_prog_release_other(prog, prog == orig_prog ?
-					   tmp : orig_prog);
 	kfree(ctx.descriptors);
 	return prog;
 
 out_err:
-	prog = orig_prog;
 	if (header)
 		bpf_jit_binary_free(header);
 	goto out;

arch/parisc/net/bpf_jit_core.c

@@ -41,33 +41,22 @@ bool bpf_jit_needs_zext(void)
 	return true;
 }
 
-struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
+struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_prog *prog)
 {
 	unsigned int prog_size = 0, extable_size = 0;
-	bool tmp_blinded = false, extra_pass = false;
-	struct bpf_prog *tmp, *orig_prog = prog;
+	bool extra_pass = false;
 	int pass = 0, prev_ninsns = 0, prologue_len, i;
 	struct hppa_jit_data *jit_data;
 	struct hppa_jit_context *ctx;
 
 	if (!prog->jit_requested)
-		return orig_prog;
-
-	tmp = bpf_jit_blind_constants(prog);
-	if (IS_ERR(tmp))
-		return orig_prog;
-	if (tmp != prog) {
-		tmp_blinded = true;
-		prog = tmp;
-	}
+		return prog;
 
 	jit_data = prog->aux->jit_data;
 	if (!jit_data) {
 		jit_data = kzalloc_obj(*jit_data);
-		if (!jit_data) {
-			prog = orig_prog;
-			goto out;
-		}
+		if (!jit_data)
+			return prog;
 		prog->aux->jit_data = jit_data;
 	}
 
@@ -81,10 +70,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 
 	ctx->prog = prog;
 	ctx->offset = kzalloc_objs(int, prog->len);
-	if (!ctx->offset) {
-		prog = orig_prog;
-		goto out_offset;
-	}
+	if (!ctx->offset)
+		goto out_err;
 	for (i = 0; i < prog->len; i++) {
 		prev_ninsns += 20;
 		ctx->offset[i] = prev_ninsns;
@@ -93,10 +80,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	for (i = 0; i < NR_JIT_ITERATIONS; i++) {
 		pass++;
 		ctx->ninsns = 0;
-		if (build_body(ctx, extra_pass, ctx->offset)) {
-			prog = orig_prog;
-			goto out_offset;
-		}
+		if (build_body(ctx, extra_pass, ctx->offset))
+			goto out_err;
 		ctx->body_len = ctx->ninsns;
 		bpf_jit_build_prologue(ctx);
 		ctx->prologue_len = ctx->ninsns - ctx->body_len;
@@ -116,10 +101,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 						     &jit_data->image,
 						     sizeof(long),
 						     bpf_fill_ill_insns);
-			if (!jit_data->header) {
-				prog = orig_prog;
-				goto out_offset;
-			}
+			if (!jit_data->header)
+				goto out_err;
 
 			ctx->insns = (u32 *)jit_data->image;
 			/*
@@ -134,8 +117,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		pr_err("bpf-jit: image did not converge in <%d passes!\n", i);
 		if (jit_data->header)
 			bpf_jit_binary_free(jit_data->header);
-		prog = orig_prog;
-		goto out_offset;
+		goto out_err;
 	}
 
 	if (extable_size)
@@ -148,8 +130,7 @@ skip_init_ctx:
 	bpf_jit_build_prologue(ctx);
 	if (build_body(ctx, extra_pass, NULL)) {
 		bpf_jit_binary_free(jit_data->header);
-		prog = orig_prog;
-		goto out_offset;
+		goto out_err;
 	}
 	bpf_jit_build_epilogue(ctx);
 
@@ -160,20 +141,19 @@ skip_init_ctx:
 			{ extern int machine_restart(char *); machine_restart(""); }
 	}
 
+	if (!prog->is_func || extra_pass) {
+		if (bpf_jit_binary_lock_ro(jit_data->header)) {
+			bpf_jit_binary_free(jit_data->header);
+			goto out_err;
+		}
+		bpf_flush_icache(jit_data->header, ctx->insns + ctx->ninsns);
+	}
+
 	prog->bpf_func = (void *)ctx->insns;
 	prog->jited = 1;
 	prog->jited_len = prog_size;
 
-	bpf_flush_icache(jit_data->header, ctx->insns + ctx->ninsns);
-
 	if (!prog->is_func || extra_pass) {
-		if (bpf_jit_binary_lock_ro(jit_data->header)) {
-			bpf_jit_binary_free(jit_data->header);
-			prog->bpf_func = NULL;
-			prog->jited = 0;
-			prog->jited_len = 0;
-			goto out_offset;
-		}
 		prologue_len = ctx->epilogue_offset - ctx->body_len;
 		for (i = 0; i < prog->len; i++)
 			ctx->offset[i] += prologue_len;
@@ -183,14 +163,19 @@ out_offset:
 		kfree(jit_data);
 		prog->aux->jit_data = NULL;
 	}
-out:
+
 	if (HPPA_JIT_REBOOT)
 		{ extern int machine_restart(char *); machine_restart(""); }
 
-	if (tmp_blinded)
-		bpf_jit_prog_release_other(prog, prog == orig_prog ?
-					   tmp : orig_prog);
 	return prog;
+
+out_err:
+	if (extra_pass) {
+		prog->bpf_func = NULL;
+		prog->jited = 0;
+		prog->jited_len = 0;
+	}
+	goto out_offset;
 }
 
 u64 hppa_div64(u64 div, u64 divisor)

arch/powerpc/net/bpf_jit_comp.c

@@ -162,7 +162,7 @@ static void priv_stack_check_guard(void __percpu *priv_stack_ptr, int alloc_size
 	}
 }
 
-struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
+struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_prog *fp)
 {
 	u32 proglen;
 	u32 alloclen;
@@ -177,9 +177,6 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	void __percpu *priv_stack_ptr = NULL;
 	struct bpf_binary_header *fhdr = NULL;
 	struct bpf_binary_header *hdr = NULL;
-	struct bpf_prog *org_fp = fp;
-	struct bpf_prog *tmp_fp = NULL;
-	bool bpf_blinded = false;
 	bool extra_pass = false;
 	u8 *fimage = NULL;
 	u32 *fcode_base = NULL;
@@ -187,24 +184,13 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	u32 fixup_len;
 
 	if (!fp->jit_requested)
-		return org_fp;
-
-	tmp_fp = bpf_jit_blind_constants(org_fp);
-	if (IS_ERR(tmp_fp))
-		return org_fp;
-
-	if (tmp_fp != org_fp) {
-		bpf_blinded = true;
-		fp = tmp_fp;
-	}
+		return fp;
 
 	jit_data = fp->aux->jit_data;
 	if (!jit_data) {
 		jit_data = kzalloc_obj(*jit_data);
-		if (!jit_data) {
-			fp = org_fp;
-			goto out;
-		}
+		if (!jit_data)
+			return fp;
 		fp->aux->jit_data = jit_data;
 	}
 
@@ -219,10 +205,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 		priv_stack_alloc_size = round_up(fp->aux->stack_depth, 16) +
 							2 * PRIV_STACK_GUARD_SZ;
 		priv_stack_ptr = __alloc_percpu_gfp(priv_stack_alloc_size, 16, GFP_KERNEL);
-		if (!priv_stack_ptr) {
-			fp = org_fp;
+		if (!priv_stack_ptr)
 			goto out_priv_stack;
-		}
 
 		priv_stack_init_guard(priv_stack_ptr, priv_stack_alloc_size);
 		fp->aux->priv_stack_ptr = priv_stack_ptr;
@@ -249,10 +233,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	}
 
 	addrs = kcalloc(flen + 1, sizeof(*addrs), GFP_KERNEL);
-	if (addrs == NULL) {
-		fp = org_fp;
-		goto out_addrs;
-	}
+	if (addrs == NULL)
+		goto out_err;
 
 	memset(&cgctx, 0, sizeof(struct codegen_context));
 	bpf_jit_init_reg_mapping(&cgctx);
@@ -279,11 +261,9 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	}
 
 	/* Scouting faux-generate pass 0 */
-	if (bpf_jit_build_body(fp, NULL, NULL, &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;
-	}
+		goto out_err;
 
 	/*
 	 * If we have seen a tail call, we need a second pass.
@@ -294,10 +274,8 @@ 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, NULL, NULL, &cgctx, addrs, 0, false)) {
-			fp = org_fp;
-			goto out_addrs;
-		}
+		if (bpf_jit_build_body(fp, NULL, NULL, &cgctx, addrs, 0, false))
+			goto out_err;
 	}
 
 	bpf_jit_realloc_regs(&cgctx);
@@ -318,10 +296,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 
 	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 (!fhdr)
+		goto out_err;
 
 	if (extable_len)
 		fp->aux->extable = (void *)fimage + FUNCTION_DESCR_SIZE + proglen + fixup_len;
@@ -340,8 +316,7 @@ skip_init_ctx:
 				       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;
+			goto out_err;
 		}
 		bpf_jit_build_epilogue(code_base, &cgctx);
 
@@ -363,15 +338,16 @@ skip_init_ctx:
 	((u64 *)image)[1] = local_paca->kernel_toc;
 #endif
 
+	if (!fp->is_func || extra_pass) {
+		if (bpf_jit_binary_pack_finalize(fhdr, hdr))
+			goto out_err;
+	}
+
 	fp->bpf_func = (void *)fimage;
 	fp->jited = 1;
 	fp->jited_len = cgctx.idx * 4 + FUNCTION_DESCR_SIZE;
 
 	if (!fp->is_func || extra_pass) {
-		if (bpf_jit_binary_pack_finalize(fhdr, hdr)) {
-			fp = org_fp;
-			goto out_addrs;
-		}
 		bpf_prog_fill_jited_linfo(fp, addrs);
 		/*
 		 * On ABI V1, executable code starts after the function
@@ -398,11 +374,15 @@ out_priv_stack:
 		jit_data->hdr = hdr;
 	}
 
-out:
-	if (bpf_blinded)
-		bpf_jit_prog_release_other(fp, fp == org_fp ? tmp_fp : org_fp);
-
 	return fp;
+
+out_err:
+	if (extra_pass) {
+		fp->bpf_func = NULL;
+		fp->jited = 0;
+		fp->jited_len = 0;
+	}
+	goto out_addrs;
 }
 
 /*

arch/riscv/net/bpf_jit.h

@@ -11,7 +11,6 @@
 
 #include <linux/bpf.h>
 #include <linux/filter.h>
-#include <asm/cacheflush.h>
 
 /* verify runtime detection extension status */
 #define rv_ext_enabled(ext) \
@@ -105,11 +104,6 @@ static inline void bpf_fill_ill_insns(void *area, unsigned int size)
 	memset(area, 0, size);
 }
 
-static inline void bpf_flush_icache(void *start, void *end)
-{
-	flush_icache_range((unsigned long)start, (unsigned long)end);
-}
-
 /* Emit a 4-byte riscv instruction. */
 static inline void emit(const u32 insn, struct rv_jit_context *ctx)
 {

arch/riscv/net/bpf_jit_core.c

@@ -41,32 +41,22 @@ bool bpf_jit_needs_zext(void)
 	return true;
 }
 
-struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
+struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_prog *prog)
 {
 	unsigned int prog_size = 0, extable_size = 0;
-	bool tmp_blinded = false, extra_pass = false;
-	struct bpf_prog *tmp, *orig_prog = prog;
+	bool extra_pass = false;
 	int pass = 0, prev_ninsns = 0, i;
 	struct rv_jit_data *jit_data;
 	struct rv_jit_context *ctx;
 
 	if (!prog->jit_requested)
-		return orig_prog;
-
-	tmp = bpf_jit_blind_constants(prog);
-	if (IS_ERR(tmp))
-		return orig_prog;
-	if (tmp != prog) {
-		tmp_blinded = true;
-		prog = tmp;
-	}
+		return prog;
 
 	jit_data = prog->aux->jit_data;
 	if (!jit_data) {
 		jit_data = kzalloc_obj(*jit_data);
 		if (!jit_data) {
-			prog = orig_prog;
-			goto out;
+			return prog;
 		}
 		prog->aux->jit_data = jit_data;
 	}
@@ -83,15 +73,11 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	ctx->user_vm_start = bpf_arena_get_user_vm_start(prog->aux->arena);
 	ctx->prog = prog;
 	ctx->offset = kzalloc_objs(int, prog->len);
-	if (!ctx->offset) {
-		prog = orig_prog;
+	if (!ctx->offset)
 		goto out_offset;
-	}
 
-	if (build_body(ctx, extra_pass, NULL)) {
-		prog = orig_prog;
+	if (build_body(ctx, extra_pass, NULL))
 		goto out_offset;
-	}
 
 	for (i = 0; i < prog->len; i++) {
 		prev_ninsns += 32;
@@ -105,10 +91,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		bpf_jit_build_prologue(ctx, bpf_is_subprog(prog));
 		ctx->prologue_len = ctx->ninsns;
 
-		if (build_body(ctx, extra_pass, ctx->offset)) {
-			prog = orig_prog;
+		if (build_body(ctx, extra_pass, ctx->offset))
 			goto out_offset;
-		}
 
 		ctx->epilogue_offset = ctx->ninsns;
 		bpf_jit_build_epilogue(ctx);
@@ -126,10 +110,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 							  &jit_data->ro_image, sizeof(u32),
 							  &jit_data->header, &jit_data->image,
 							  bpf_fill_ill_insns);
-			if (!jit_data->ro_header) {
-				prog = orig_prog;
+			if (!jit_data->ro_header)
 				goto out_offset;
-			}
 
 			/*
 			 * Use the image(RW) for writing the JITed instructions. But also save
@@ -150,7 +132,6 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 
 	if (i == NR_JIT_ITERATIONS) {
 		pr_err("bpf-jit: image did not converge in <%d passes!\n", i);
-		prog = orig_prog;
 		goto out_free_hdr;
 	}
 
@@ -163,33 +144,27 @@ skip_init_ctx:
 	ctx->nexentries = 0;
 
 	bpf_jit_build_prologue(ctx, bpf_is_subprog(prog));
-	if (build_body(ctx, extra_pass, NULL)) {
-		prog = orig_prog;
+	if (build_body(ctx, extra_pass, NULL))
 		goto out_free_hdr;
-	}
 	bpf_jit_build_epilogue(ctx);
 
 	if (bpf_jit_enable > 1)
 		bpf_jit_dump(prog->len, prog_size, pass, ctx->insns);
 
+	if (!prog->is_func || extra_pass) {
+		if (WARN_ON(bpf_jit_binary_pack_finalize(jit_data->ro_header, jit_data->header))) {
+			/* ro_header has been freed */
+			jit_data->ro_header = NULL;
+			jit_data->header = NULL;
+			goto out_free_hdr;
+		}
+	}
+
 	prog->bpf_func = (void *)ctx->ro_insns + cfi_get_offset();
 	prog->jited = 1;
 	prog->jited_len = prog_size - cfi_get_offset();
 
 	if (!prog->is_func || extra_pass) {
-		if (WARN_ON(bpf_jit_binary_pack_finalize(jit_data->ro_header, jit_data->header))) {
-			/* ro_header has been freed */
-			jit_data->ro_header = NULL;
-			prog = orig_prog;
-			goto out_offset;
-		}
-		/*
-		 * The instructions have now been copied to the ROX region from
-		 * where they will execute.
-		 * Write any modified data cache blocks out to memory and
-		 * invalidate the corresponding blocks in the instruction cache.
-		 */
-		bpf_flush_icache(jit_data->ro_header, ctx->ro_insns + ctx->ninsns);
 		for (i = 0; i < prog->len; i++)
 			ctx->offset[i] = ninsns_rvoff(ctx->offset[i]);
 		bpf_prog_fill_jited_linfo(prog, ctx->offset);
@@ -198,14 +173,15 @@ out_offset:
 		kfree(jit_data);
 		prog->aux->jit_data = NULL;
 	}
-out:
 
-	if (tmp_blinded)
-		bpf_jit_prog_release_other(prog, prog == orig_prog ?
-					   tmp : orig_prog);
 	return prog;
 
 out_free_hdr:
+	if (extra_pass) {
+		prog->bpf_func = NULL;
+		prog->jited = 0;
+		prog->jited_len = 0;
+	}
 	if (jit_data->header) {
 		bpf_arch_text_copy(&jit_data->ro_header->size, &jit_data->header->size,
 				   sizeof(jit_data->header->size));

arch/s390/net/bpf_jit_comp.c

@@ -2312,38 +2312,22 @@ static struct bpf_binary_header *bpf_jit_alloc(struct bpf_jit *jit,
 /*
  * Compile eBPF program "fp"
  */
-struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
+struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_prog *fp)
 {
-	struct bpf_prog *tmp, *orig_fp = fp;
 	struct bpf_binary_header *header;
 	struct s390_jit_data *jit_data;
-	bool tmp_blinded = false;
 	bool extra_pass = false;
 	struct bpf_jit jit;
 	int pass;
 
 	if (!fp->jit_requested)
-		return orig_fp;
-
-	tmp = bpf_jit_blind_constants(fp);
-	/*
-	 * If blinding was requested and we failed during blinding,
-	 * we must fall back to the interpreter.
-	 */
-	if (IS_ERR(tmp))
-		return orig_fp;
-	if (tmp != fp) {
-		tmp_blinded = true;
-		fp = tmp;
-	}
+		return fp;
 
 	jit_data = fp->aux->jit_data;
 	if (!jit_data) {
 		jit_data = kzalloc_obj(*jit_data);
-		if (!jit_data) {
-			fp = orig_fp;
-			goto out;
-		}
+		if (!jit_data)
+			return fp;
 		fp->aux->jit_data = jit_data;
 	}
 	if (jit_data->ctx.addrs) {
@@ -2356,34 +2340,27 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 
 	memset(&jit, 0, sizeof(jit));
 	jit.addrs = kvcalloc(fp->len + 1, sizeof(*jit.addrs), GFP_KERNEL);
-	if (jit.addrs == NULL) {
-		fp = orig_fp;
-		goto free_addrs;
-	}
+	if (jit.addrs == NULL)
+		goto out_err;
 	/*
 	 * Three initial passes:
 	 *   - 1/2: Determine clobbered registers
 	 *   - 3:   Calculate program size and addrs array
 	 */
 	for (pass = 1; pass <= 3; pass++) {
-		if (bpf_jit_prog(&jit, fp, extra_pass)) {
-			fp = orig_fp;
-			goto free_addrs;
-		}
+		if (bpf_jit_prog(&jit, fp, extra_pass))
+			goto out_err;
 	}
 	/*
 	 * Final pass: Allocate and generate program
 	 */
 	header = bpf_jit_alloc(&jit, fp);
-	if (!header) {
-		fp = orig_fp;
-		goto free_addrs;
-	}
+	if (!header)
+		goto out_err;
 skip_init_ctx:
 	if (bpf_jit_prog(&jit, fp, extra_pass)) {
 		bpf_jit_binary_free(header);
-		fp = orig_fp;
-		goto free_addrs;
+		goto out_err;
 	}
 	if (bpf_jit_enable > 1) {
 		bpf_jit_dump(fp->len, jit.size, pass, jit.prg_buf);
@@ -2392,8 +2369,7 @@ skip_init_ctx:
 	if (!fp->is_func || extra_pass) {
 		if (bpf_jit_binary_lock_ro(header)) {
 			bpf_jit_binary_free(header);
-			fp = orig_fp;
-			goto free_addrs;
+			goto out_err;
 		}
 	} else {
 		jit_data->header = header;
@@ -2411,11 +2387,16 @@ free_addrs:
 		kfree(jit_data);
 		fp->aux->jit_data = NULL;
 	}
-out:
-	if (tmp_blinded)
-		bpf_jit_prog_release_other(fp, fp == orig_fp ?
-					   tmp : orig_fp);
+
 	return fp;
+
+out_err:
+	if (extra_pass) {
+		fp->bpf_func = NULL;
+		fp->jited = 0;
+		fp->jited_len = 0;
+	}
+	goto free_addrs;
 }
 
 bool bpf_jit_supports_kfunc_call(void)

arch/sparc/net/bpf_jit_comp_64.c

@@ -1477,39 +1477,24 @@ struct sparc64_jit_data {
 	struct jit_ctx ctx;
 };
 
-struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
+struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_prog *prog)
 {
-	struct bpf_prog *tmp, *orig_prog = prog;
 	struct sparc64_jit_data *jit_data;
 	struct bpf_binary_header *header;
 	u32 prev_image_size, image_size;
-	bool tmp_blinded = false;
 	bool extra_pass = false;
 	struct jit_ctx ctx;
 	u8 *image_ptr;
 	int pass, i;
 
 	if (!prog->jit_requested)
-		return orig_prog;
-
-	tmp = bpf_jit_blind_constants(prog);
-	/* If blinding was requested and we failed during blinding,
-	 * we must fall back to the interpreter.
-	 */
-	if (IS_ERR(tmp))
-		return orig_prog;
-	if (tmp != prog) {
-		tmp_blinded = true;
-		prog = tmp;
-	}
+		return prog;
 
 	jit_data = prog->aux->jit_data;
 	if (!jit_data) {
 		jit_data = kzalloc_obj(*jit_data);
-		if (!jit_data) {
-			prog = orig_prog;
-			goto out;
-		}
+		if (!jit_data)
+			return prog;
 		prog->aux->jit_data = jit_data;
 	}
 	if (jit_data->ctx.offset) {
@@ -1527,10 +1512,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	ctx.prog = prog;
 
 	ctx.offset = kmalloc_array(prog->len, sizeof(unsigned int), GFP_KERNEL);
-	if (ctx.offset == NULL) {
-		prog = orig_prog;
-		goto out_off;
-	}
+	if (ctx.offset == NULL)
+		goto out_err;
 
 	/* Longest sequence emitted is for bswap32, 12 instructions.  Pre-cook
 	 * the offset array so that we converge faster.
@@ -1543,10 +1526,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		ctx.idx = 0;
 
 		build_prologue(&ctx);
-		if (build_body(&ctx)) {
-			prog = orig_prog;
-			goto out_off;
-		}
+		if (build_body(&ctx))
+			goto out_err;
 		build_epilogue(&ctx);
 
 		if (bpf_jit_enable > 1)
@@ -1569,10 +1550,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	image_size = sizeof(u32) * ctx.idx;
 	header = bpf_jit_binary_alloc(image_size, &image_ptr,
 				      sizeof(u32), jit_fill_hole);
-	if (header == NULL) {
-		prog = orig_prog;
-		goto out_off;
-	}
+	if (header == NULL)
+		goto out_err;
 
 	ctx.image = (u32 *)image_ptr;
 skip_init_ctx:
@@ -1582,8 +1561,7 @@ skip_init_ctx:
 
 	if (build_body(&ctx)) {
 		bpf_jit_binary_free(header);
-		prog = orig_prog;
-		goto out_off;
+		goto out_err;
 	}
 
 	build_epilogue(&ctx);
@@ -1592,8 +1570,7 @@ skip_init_ctx:
 		pr_err("bpf_jit: Failed to converge, prev_size=%u size=%d\n",
 		       prev_image_size, ctx.idx * 4);
 		bpf_jit_binary_free(header);
-		prog = orig_prog;
-		goto out_off;
+		goto out_err;
 	}
 
 	if (bpf_jit_enable > 1)
@@ -1604,8 +1581,7 @@ skip_init_ctx:
 	if (!prog->is_func || extra_pass) {
 		if (bpf_jit_binary_lock_ro(header)) {
 			bpf_jit_binary_free(header);
-			prog = orig_prog;
-			goto out_off;
+			goto out_err;
 		}
 	} else {
 		jit_data->ctx = ctx;
@@ -1624,9 +1600,14 @@ out_off:
 		kfree(jit_data);
 		prog->aux->jit_data = NULL;
 	}
-out:
-	if (tmp_blinded)
-		bpf_jit_prog_release_other(prog, prog == orig_prog ?
-					   tmp : orig_prog);
+
 	return prog;
+
+out_err:
+	if (extra_pass) {
+		prog->bpf_func = NULL;
+		prog->jited = 0;
+		prog->jited_len = 0;
+	}
+	goto out_off;
 }

arch/x86/net/bpf_jit_comp.c

@@ -58,8 +58,8 @@ static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
 #define EMIT_ENDBR()		EMIT(gen_endbr(), 4)
 #define EMIT_ENDBR_POISON()	EMIT(gen_endbr_poison(), 4)
 #else
-#define EMIT_ENDBR()
-#define EMIT_ENDBR_POISON()
+#define EMIT_ENDBR()		do { } while (0)
+#define EMIT_ENDBR_POISON()	do { } while (0)
 #endif
 
 static bool is_imm8(int value)
@@ -1649,8 +1649,8 @@ static int emit_spectre_bhb_barrier(u8 **pprog, u8 *ip,
 	return 0;
 }
 
-static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image,
-		  int oldproglen, struct jit_context *ctx, bool jmp_padding)
+static int do_jit(struct bpf_verifier_env *env, struct bpf_prog *bpf_prog, int *addrs, u8 *image,
+		  u8 *rw_image, int oldproglen, struct jit_context *ctx, bool jmp_padding)
 {
 	bool tail_call_reachable = bpf_prog->aux->tail_call_reachable;
 	struct bpf_insn *insn = bpf_prog->insnsi;
@@ -1663,7 +1663,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
 	void __percpu *priv_stack_ptr;
 	int i, excnt = 0;
 	int ilen, proglen = 0;
-	u8 *prog = temp;
+	u8 *ip, *prog = temp;
 	u32 stack_depth;
 	int err;
 
@@ -1734,6 +1734,11 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
 				dst_reg = X86_REG_R9;
 		}
 
+		if (bpf_insn_is_indirect_target(env, bpf_prog, i - 1))
+			EMIT_ENDBR();
+
+		ip = image + addrs[i - 1] + (prog - temp);
+
 		switch (insn->code) {
 			/* ALU */
 		case BPF_ALU | BPF_ADD | BPF_X:
@@ -2440,8 +2445,6 @@ populate_extable:
 
 			/* call */
 		case BPF_JMP | BPF_CALL: {
-			u8 *ip = image + addrs[i - 1];
-
 			func = (u8 *) __bpf_call_base + imm32;
 			if (src_reg == BPF_PSEUDO_CALL && tail_call_reachable) {
 				LOAD_TAIL_CALL_CNT_PTR(stack_depth);
@@ -2465,7 +2468,8 @@ populate_extable:
 			if (imm32)
 				emit_bpf_tail_call_direct(bpf_prog,
 							  &bpf_prog->aux->poke_tab[imm32 - 1],
-							  &prog, image + addrs[i - 1],
+							  &prog,
+							  ip,
 							  callee_regs_used,
 							  stack_depth,
 							  ctx);
@@ -2474,7 +2478,7 @@ populate_extable:
 							    &prog,
 							    callee_regs_used,
 							    stack_depth,
-							    image + addrs[i - 1],
+							    ip,
 							    ctx);
 			break;
 
@@ -2639,7 +2643,7 @@ emit_cond_jmp:		/* Convert BPF opcode to x86 */
 			break;
 
 		case BPF_JMP | BPF_JA | BPF_X:
-			emit_indirect_jump(&prog, insn->dst_reg, image + addrs[i - 1]);
+			emit_indirect_jump(&prog, insn->dst_reg, ip);
 			break;
 		case BPF_JMP | BPF_JA:
 		case BPF_JMP32 | BPF_JA:
@@ -2729,8 +2733,6 @@ emit_jmp:
 			ctx->cleanup_addr = proglen;
 			if (bpf_prog_was_classic(bpf_prog) &&
 			    !ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN)) {
-				u8 *ip = image + addrs[i - 1];
-
 				if (emit_spectre_bhb_barrier(&prog, ip, bpf_prog))
 					return -EINVAL;
 			}
@@ -3713,17 +3715,15 @@ struct x64_jit_data {
 #define MAX_PASSES 20
 #define PADDING_PASSES (MAX_PASSES - 5)
 
-struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
+struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_prog *prog)
 {
 	struct bpf_binary_header *rw_header = NULL;
 	struct bpf_binary_header *header = NULL;
-	struct bpf_prog *tmp, *orig_prog = prog;
 	void __percpu *priv_stack_ptr = NULL;
 	struct x64_jit_data *jit_data;
 	int priv_stack_alloc_sz;
 	int proglen, oldproglen = 0;
 	struct jit_context ctx = {};
-	bool tmp_blinded = false;
 	bool extra_pass = false;
 	bool padding = false;
 	u8 *rw_image = NULL;
@@ -3733,27 +3733,13 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	int i;
 
 	if (!prog->jit_requested)
-		return orig_prog;
-
-	tmp = bpf_jit_blind_constants(prog);
-	/*
-	 * If blinding was requested and we failed during blinding,
-	 * we must fall back to the interpreter.
-	 */
-	if (IS_ERR(tmp))
-		return orig_prog;
-	if (tmp != prog) {
-		tmp_blinded = true;
-		prog = tmp;
-	}
+		return prog;
 
 	jit_data = prog->aux->jit_data;
 	if (!jit_data) {
 		jit_data = kzalloc_obj(*jit_data);
-		if (!jit_data) {
-			prog = orig_prog;
-			goto out;
-		}
+		if (!jit_data)
+			return prog;
 		prog->aux->jit_data = jit_data;
 	}
 	priv_stack_ptr = prog->aux->priv_stack_ptr;
@@ -3765,10 +3751,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		priv_stack_alloc_sz = round_up(prog->aux->stack_depth, 8) +
 				      2 * PRIV_STACK_GUARD_SZ;
 		priv_stack_ptr = __alloc_percpu_gfp(priv_stack_alloc_sz, 8, GFP_KERNEL);
-		if (!priv_stack_ptr) {
-			prog = orig_prog;
+		if (!priv_stack_ptr)
 			goto out_priv_stack;
-		}
 
 		priv_stack_init_guard(priv_stack_ptr, priv_stack_alloc_sz);
 		prog->aux->priv_stack_ptr = priv_stack_ptr;
@@ -3786,10 +3770,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		goto skip_init_addrs;
 	}
 	addrs = kvmalloc_objs(*addrs, prog->len + 1);
-	if (!addrs) {
-		prog = orig_prog;
+	if (!addrs)
 		goto out_addrs;
-	}
 
 	/*
 	 * Before first pass, make a rough estimation of addrs[]
@@ -3811,7 +3793,7 @@ skip_init_addrs:
 	for (pass = 0; pass < MAX_PASSES || image; pass++) {
 		if (!padding && pass >= PADDING_PASSES)
 			padding = true;
-		proglen = do_jit(prog, addrs, image, rw_image, oldproglen, &ctx, padding);
+		proglen = do_jit(env, prog, addrs, image, rw_image, oldproglen, &ctx, padding);
 		if (proglen <= 0) {
 out_image:
 			image = NULL;
@@ -3820,8 +3802,6 @@ out_image:
 						   sizeof(rw_header->size));
 				bpf_jit_binary_pack_free(header, rw_header);
 			}
-			/* Fall back to interpreter mode */
-			prog = orig_prog;
 			if (extra_pass) {
 				prog->bpf_func = NULL;
 				prog->jited = 0;
@@ -3852,10 +3832,8 @@ out_image:
 			header = bpf_jit_binary_pack_alloc(roundup(proglen, align) + extable_size,
 							   &image, align, &rw_header, &rw_image,
 							   jit_fill_hole);
-			if (!header) {
-				prog = orig_prog;
+			if (!header)
 				goto out_addrs;
-			}
 			prog->aux->extable = (void *) image + roundup(proglen, align);
 		}
 		oldproglen = proglen;
@@ -3908,8 +3886,6 @@ out_image:
 		prog->bpf_func = (void *)image + cfi_get_offset();
 		prog->jited = 1;
 		prog->jited_len = proglen - cfi_get_offset();
-	} else {
-		prog = orig_prog;
 	}
 
 	if (!image || !prog->is_func || extra_pass) {
@@ -3925,10 +3901,7 @@ out_priv_stack:
 		kfree(jit_data);
 		prog->aux->jit_data = NULL;
 	}
-out:
-	if (tmp_blinded)
-		bpf_jit_prog_release_other(prog, prog == orig_prog ?
-					   tmp : orig_prog);
+
 	return prog;
 }
 

arch/x86/net/bpf_jit_comp32.c

@@ -2518,38 +2518,22 @@ bool bpf_jit_needs_zext(void)
 	return true;
 }
 
-struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
+struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_prog *prog)
 {
 	struct bpf_binary_header *header = NULL;
-	struct bpf_prog *tmp, *orig_prog = prog;
 	int proglen, oldproglen = 0;
 	struct jit_context ctx = {};
-	bool tmp_blinded = false;
 	u8 *image = NULL;
 	int *addrs;
 	int pass;
 	int i;
 
 	if (!prog->jit_requested)
-		return orig_prog;
-
-	tmp = bpf_jit_blind_constants(prog);
-	/*
-	 * If blinding was requested and we failed during blinding,
-	 * we must fall back to the interpreter.
-	 */
-	if (IS_ERR(tmp))
-		return orig_prog;
-	if (tmp != prog) {
-		tmp_blinded = true;
-		prog = tmp;
-	}
+		return prog;
 
 	addrs = kmalloc_objs(*addrs, prog->len);
-	if (!addrs) {
-		prog = orig_prog;
-		goto out;
-	}
+	if (!addrs)
+		return prog;
 
 	/*
 	 * Before first pass, make a rough estimation of addrs[]
@@ -2574,7 +2558,6 @@ out_image:
 			image = NULL;
 			if (header)
 				bpf_jit_binary_free(header);
-			prog = orig_prog;
 			goto out_addrs;
 		}
 		if (image) {
@@ -2588,10 +2571,8 @@ out_image:
 		if (proglen == oldproglen) {
 			header = bpf_jit_binary_alloc(proglen, &image,
 						      1, jit_fill_hole);
-			if (!header) {
-				prog = orig_prog;
+			if (!header)
 				goto out_addrs;
-			}
 		}
 		oldproglen = proglen;
 		cond_resched();
@@ -2604,16 +2585,10 @@ out_image:
 		prog->bpf_func = (void *)image;
 		prog->jited = 1;
 		prog->jited_len = proglen;
-	} else {
-		prog = orig_prog;
 	}
 
 out_addrs:
 	kfree(addrs);
-out:
-	if (tmp_blinded)
-		bpf_jit_prog_release_other(prog, prog == orig_prog ?
-					   tmp : orig_prog);
 	return prog;
 }
 

include/linux/bpf.h

@@ -1541,6 +1541,8 @@ bool bpf_has_frame_pointer(unsigned long ip);
 int bpf_jit_charge_modmem(u32 size);
 void bpf_jit_uncharge_modmem(u32 size);
 bool bpf_prog_has_trampoline(const struct bpf_prog *prog);
+bool bpf_insn_is_indirect_target(const struct bpf_verifier_env *env, const struct bpf_prog *prog,
+				 int insn_idx);
 #else
 static inline int bpf_trampoline_link_prog(struct bpf_tramp_link *link,
 					   struct bpf_trampoline *tr,

include/linux/bpf_verifier.h

@@ -630,16 +630,17 @@ struct bpf_insn_aux_data {
 
 	/* below fields are initialized once */
 	unsigned int orig_idx; /* original instruction index */
-	bool jmp_point;
-	bool prune_point;
+	u32 jmp_point:1;
+	u32 prune_point:1;
 	/* ensure we check state equivalence and save state checkpoint and
 	 * this instruction, regardless of any heuristics
 	 */
-	bool force_checkpoint;
+	u32 force_checkpoint:1;
 	/* true if instruction is a call to a helper function that
 	 * accepts callback function as a parameter.
 	 */
-	bool calls_callback;
+	u32 calls_callback:1;
+	u32 indirect_target:1; /* if it is an indirect jump target */
 	/*
 	 * CFG strongly connected component this instruction belongs to,
 	 * zero if it is a singleton SCC.

include/linux/filter.h

@@ -1108,6 +1108,8 @@ sk_filter_reason(struct sock *sk, struct sk_buff *skb)
 	return sk_filter_trim_cap(sk, skb, 1);
 }
 
+struct bpf_prog *__bpf_prog_select_runtime(struct bpf_verifier_env *env, struct bpf_prog *fp,
+					   int *err);
 struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err);
 void bpf_prog_free(struct bpf_prog *fp);
 
@@ -1153,7 +1155,7 @@ u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
 	((u64 (*)(u64, u64, u64, u64, u64, const struct bpf_insn *)) \
 	 (void *)__bpf_call_base)
 
-struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog);
+struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_prog *prog);
 void bpf_jit_compile(struct bpf_prog *prog);
 bool bpf_jit_needs_zext(void);
 bool bpf_jit_inlines_helper_call(s32 imm);
@@ -1184,6 +1186,31 @@ static inline bool bpf_dump_raw_ok(const struct cred *cred)
 
 struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
 				       const struct bpf_insn *patch, u32 len);
+
+#ifdef CONFIG_BPF_SYSCALL
+struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 off,
+				     const struct bpf_insn *patch, u32 len);
+struct bpf_insn_aux_data *bpf_dup_insn_aux_data(struct bpf_verifier_env *env);
+void bpf_restore_insn_aux_data(struct bpf_verifier_env *env,
+			       struct bpf_insn_aux_data *orig_insn_aux);
+#else
+static inline struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 off,
+						   const struct bpf_insn *patch, u32 len)
+{
+	return ERR_PTR(-ENOTSUPP);
+}
+
+static inline struct bpf_insn_aux_data *bpf_dup_insn_aux_data(struct bpf_verifier_env *env)
+{
+	return NULL;
+}
+
+static inline void bpf_restore_insn_aux_data(struct bpf_verifier_env *env,
+					     struct bpf_insn_aux_data *orig_insn_aux)
+{
+}
+#endif /* CONFIG_BPF_SYSCALL */
+
 int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt);
 
 static inline bool xdp_return_frame_no_direct(void)
@@ -1310,9 +1337,14 @@ int bpf_jit_get_func_addr(const struct bpf_prog *prog,
 
 const char *bpf_jit_get_prog_name(struct bpf_prog *prog);
 
-struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *fp);
+struct bpf_prog *bpf_jit_blind_constants(struct bpf_verifier_env *env, struct bpf_prog *prog);
 void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other);
 
+static inline bool bpf_prog_need_blind(const struct bpf_prog *prog)
+{
+	return prog->blinding_requested && !prog->blinded;
+}
+
 static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen,
 				u32 pass, void *image)
 {
@@ -1451,6 +1483,20 @@ static inline void bpf_prog_kallsyms_del(struct bpf_prog *fp)
 {
 }
 
+static inline bool bpf_prog_need_blind(const struct bpf_prog *prog)
+{
+	return false;
+}
+
+static inline
+struct bpf_prog *bpf_jit_blind_constants(struct bpf_verifier_env *env, struct bpf_prog *prog)
+{
+	return prog;
+}
+
+static inline void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other)
+{
+}
 #endif /* CONFIG_BPF_JIT */
 
 void bpf_prog_kallsyms_del_all(struct bpf_prog *fp);

kernel/bpf/arena.c

@@ -341,6 +341,16 @@ static void arena_vm_open(struct vm_area_struct *vma)
 	refcount_inc(&vml->mmap_count);
 }
 
+static int arena_vm_may_split(struct vm_area_struct *vma, unsigned long addr)
+{
+	return -EINVAL;
+}
+
+static int arena_vm_mremap(struct vm_area_struct *vma)
+{
+	return -EINVAL;
+}
+
 static void arena_vm_close(struct vm_area_struct *vma)
 {
 	struct bpf_map *map = vma->vm_file->private_data;
@@ -417,6 +427,8 @@ out_unlock_sigsegv:
 
 static const struct vm_operations_struct arena_vm_ops = {
 	.open		= arena_vm_open,
+	.may_split	= arena_vm_may_split,
+	.mremap		= arena_vm_mremap,
 	.close		= arena_vm_close,
 	.fault          = arena_vm_fault,
 };
@@ -486,10 +498,11 @@ static int arena_map_mmap(struct bpf_map *map, struct vm_area_struct *vma)
 	arena->user_vm_end = vma->vm_end;
 	/*
 	 * bpf_map_mmap() checks that it's being mmaped as VM_SHARED and
-	 * clears VM_MAYEXEC. Set VM_DONTEXPAND as well to avoid
-	 * potential change of user_vm_start.
+	 * clears VM_MAYEXEC. Set VM_DONTEXPAND to avoid potential change
+	 * of user_vm_start. Set VM_DONTCOPY to prevent arena VMA from
+	 * being copied into the child process on fork.
 	 */
-	vm_flags_set(vma, VM_DONTEXPAND);
+	vm_flags_set(vma, VM_DONTEXPAND | VM_DONTCOPY);
 	vma->vm_ops = &arena_vm_ops;
 	return 0;
 }
@@ -549,6 +562,10 @@ static long arena_alloc_pages(struct bpf_arena *arena, long uaddr, long page_cnt
 	u32 uaddr32;
 	int ret, i;
 
+	if (node_id != NUMA_NO_NODE &&
+	    ((unsigned int)node_id >= nr_node_ids || !node_online(node_id)))
+		return 0;
+
 	if (page_cnt > page_cnt_max)
 		return 0;
 

kernel/bpf/bpf_struct_ops.c

@@ -811,9 +811,6 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 			goto reset_unlock;
 		}
 
-		/* Poison pointer on error instead of return for backward compatibility */
-		bpf_prog_assoc_struct_ops(prog, &st_map->map);
-
 		link = kzalloc_obj(*link, GFP_USER);
 		if (!link) {
 			bpf_prog_put(prog);
@@ -824,6 +821,9 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 			      &bpf_struct_ops_link_lops, prog, prog->expected_attach_type);
 		*plink++ = &link->link;
 
+		/* Poison pointer on error instead of return for backward compatibility */
+		bpf_prog_assoc_struct_ops(prog, &st_map->map);
+
 		ksym = kzalloc_obj(*ksym, GFP_USER);
 		if (!ksym) {
 			err = -ENOMEM;
@@ -906,6 +906,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 reset_unlock:
 	bpf_struct_ops_map_free_ksyms(st_map);
 	bpf_struct_ops_map_free_image(st_map);
+	bpf_struct_ops_map_dissoc_progs(st_map);
 	bpf_struct_ops_map_put_progs(st_map);
 	memset(uvalue, 0, map->value_size);
 	memset(kvalue, 0, map->value_size);

kernel/bpf/core.c

@@ -1491,24 +1491,11 @@ void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other)
 	bpf_prog_clone_free(fp_other);
 }
 
-static void adjust_insn_arrays(struct bpf_prog *prog, u32 off, u32 len)
-{
-#ifdef CONFIG_BPF_SYSCALL
-	struct bpf_map *map;
-	int i;
-
-	if (len <= 1)
-		return;
-
-	for (i = 0; i < prog->aux->used_map_cnt; i++) {
-		map = prog->aux->used_maps[i];
-		if (map->map_type == BPF_MAP_TYPE_INSN_ARRAY)
-			bpf_insn_array_adjust(map, off, len);
-	}
-#endif
-}
-
-struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *prog)
+/*
+ * Now this function is used only to blind the main prog and must be invoked only when
+ * bpf_prog_need_blind() returns true.
+ */
+struct bpf_prog *bpf_jit_blind_constants(struct bpf_verifier_env *env, struct bpf_prog *prog)
 {
 	struct bpf_insn insn_buff[16], aux[2];
 	struct bpf_prog *clone, *tmp;
@@ -1516,13 +1503,17 @@ struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *prog)
 	struct bpf_insn *insn;
 	int i, rewritten;
 
-	if (!prog->blinding_requested || prog->blinded)
-		return prog;
+	if (WARN_ON_ONCE(env && env->prog != prog))
+		return ERR_PTR(-EINVAL);
 
 	clone = bpf_prog_clone_create(prog, GFP_USER);
 	if (!clone)
 		return ERR_PTR(-ENOMEM);
 
+	/* make sure bpf_patch_insn_data() patches the correct prog */
+	if (env)
+		env->prog = clone;
+
 	insn_cnt = clone->len;
 	insn = clone->insnsi;
 
@@ -1550,21 +1541,28 @@ struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *prog)
 		if (!rewritten)
 			continue;
 
-		tmp = bpf_patch_insn_single(clone, i, insn_buff, rewritten);
-		if (IS_ERR(tmp)) {
+		if (env)
+			tmp = bpf_patch_insn_data(env, i, insn_buff, rewritten);
+		else
+			tmp = bpf_patch_insn_single(clone, i, insn_buff, rewritten);
+
+		if (IS_ERR_OR_NULL(tmp)) {
+			if (env)
+				/* restore the original prog */
+				env->prog = prog;
 			/* Patching may have repointed aux->prog during
 			 * realloc from the original one, so we need to
 			 * fix it up here on error.
 			 */
 			bpf_jit_prog_release_other(prog, clone);
-			return tmp;
+			return IS_ERR(tmp) ? tmp : ERR_PTR(-ENOMEM);
 		}
 
 		clone = tmp;
 		insn_delta = rewritten - 1;
 
-		/* Instructions arrays must be updated using absolute xlated offsets */
-		adjust_insn_arrays(clone, prog->aux->subprog_start + i, rewritten);
+		if (env)
+			env->prog = clone;
 
 		/* Walk new program and skip insns we just inserted. */
 		insn = clone->insnsi + i + insn_delta;
@@ -1575,6 +1573,15 @@ struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *prog)
 	clone->blinded = 1;
 	return clone;
 }
+
+bool bpf_insn_is_indirect_target(const struct bpf_verifier_env *env, const struct bpf_prog *prog,
+				 int insn_idx)
+{
+	if (!env)
+		return false;
+	insn_idx += prog->aux->subprog_start;
+	return env->insn_aux_data[insn_idx].indirect_target;
+}
 #endif /* CONFIG_BPF_JIT */
 
 /* Base function for offset calculation. Needs to go into .text section,
@@ -2533,18 +2540,55 @@ static bool bpf_prog_select_interpreter(struct bpf_prog *fp)
 	return select_interpreter;
 }
 
-/**
- *	bpf_prog_select_runtime - select exec runtime for BPF program
- *	@fp: bpf_prog populated with BPF program
- *	@err: pointer to error variable
- *
- * Try to JIT eBPF program, if JIT is not available, use interpreter.
- * The BPF program will be executed via bpf_prog_run() function.
- *
- * Return: the &fp argument along with &err set to 0 for success or
- * a negative errno code on failure
- */
-struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
+static struct bpf_prog *bpf_prog_jit_compile(struct bpf_verifier_env *env, struct bpf_prog *prog)
+{
+#ifdef CONFIG_BPF_JIT
+	struct bpf_prog *orig_prog;
+	struct bpf_insn_aux_data *orig_insn_aux;
+
+	if (!bpf_prog_need_blind(prog))
+		return bpf_int_jit_compile(env, prog);
+
+	if (env) {
+		/*
+		 * If env is not NULL, we are called from the end of bpf_check(), at this
+		 * point, only insn_aux_data is used after failure, so it should be restored
+		 * on failure.
+		 */
+		orig_insn_aux = bpf_dup_insn_aux_data(env);
+		if (!orig_insn_aux)
+			return prog;
+	}
+
+	orig_prog = prog;
+	prog = bpf_jit_blind_constants(env, prog);
+	/*
+	 * If blinding was requested and we failed during blinding, we must fall
+	 * back to the interpreter.
+	 */
+	if (IS_ERR(prog))
+		goto out_restore;
+
+	prog = bpf_int_jit_compile(env, prog);
+	if (prog->jited) {
+		bpf_jit_prog_release_other(prog, orig_prog);
+		if (env)
+			vfree(orig_insn_aux);
+		return prog;
+	}
+
+	bpf_jit_prog_release_other(orig_prog, prog);
+
+out_restore:
+	prog = orig_prog;
+	if (env)
+		bpf_restore_insn_aux_data(env, orig_insn_aux);
+#endif
+	return prog;
+}
+
+struct bpf_prog *__bpf_prog_select_runtime(struct bpf_verifier_env *env, struct bpf_prog *fp,
+					   int *err)
 {
 	/* In case of BPF to BPF calls, verifier did all the prep
 	 * work with regards to JITing, etc.
@@ -2572,7 +2616,7 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
 		if (*err)
 			return fp;
 
-		fp = bpf_int_jit_compile(fp);
+		fp = bpf_prog_jit_compile(env, fp);
 		bpf_prog_jit_attempt_done(fp);
 		if (!fp->jited && jit_needed) {
 			*err = -ENOTSUPP;
@@ -2598,6 +2642,22 @@ finalize:
 
 	return fp;
 }
+
+/**
+ *	bpf_prog_select_runtime - select exec runtime for BPF program
+ *	@fp: bpf_prog populated with BPF program
+ *	@err: pointer to error variable
+ *
+ * Try to JIT eBPF program, if JIT is not available, use interpreter.
+ * The BPF program will be executed via bpf_prog_run() function.
+ *
+ * Return: the &fp argument along with &err set to 0 for success or
+ * a negative errno code on failure
+ */
+struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
+{
+	return __bpf_prog_select_runtime(NULL, fp, err);
+}
 EXPORT_SYMBOL_GPL(bpf_prog_select_runtime);
 
 static unsigned int __bpf_prog_ret1(const void *ctx,
@@ -3085,7 +3145,7 @@ const struct bpf_func_proto bpf_tail_call_proto = {
  * It is encouraged to implement bpf_int_jit_compile() instead, so that
  * eBPF and implicitly also cBPF can get JITed!
  */
-struct bpf_prog * __weak bpf_int_jit_compile(struct bpf_prog *prog)
+struct bpf_prog * __weak bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_prog *prog)
 {
 	return prog;
 }