1 files changed, 294 insertions, 126 deletions

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index ce1f86f245c9..00127abd89ee 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -11,6 +11,7 @@
 #include <linux/bpf.h>
 #include <linux/memory.h>
 #include <linux/sort.h>
+#include <linux/init.h>
 #include <asm/extable.h>
 #include <asm/set_memory.h>
 #include <asm/nospec-branch.h>
@@ -46,6 +47,12 @@ static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
 #define EMIT4_off32(b1, b2, b3, b4, off) \
 	do { EMIT4(b1, b2, b3, b4); EMIT(off, 4); } while (0)
 
+#ifdef CONFIG_X86_KERNEL_IBT
+#define EMIT_ENDBR()	EMIT(gen_endbr(), 4)
+#else
+#define EMIT_ENDBR()
+#endif
+
 static bool is_imm8(int value)
 {
 	return value <= 127 && value >= -128;
@@ -222,6 +229,11 @@ static void jit_fill_hole(void *area, unsigned int size)
 	memset(area, 0xcc, size);
 }
 
+int bpf_arch_text_invalidate(void *dst, size_t len)
+{
+	return IS_ERR_OR_NULL(text_poke_set(dst, 0xcc, len));
+}
+
 struct jit_context {
 	int cleanup_addr; /* Epilogue code offset */
 
@@ -241,7 +253,7 @@ struct jit_context {
 /* Number of bytes emit_patch() needs to generate instructions */
 #define X86_PATCH_SIZE		5
 /* Number of bytes that will be skipped on tailcall */
-#define X86_TAIL_CALL_OFFSET	11
+#define X86_TAIL_CALL_OFFSET	(11 + ENDBR_INSN_SIZE)
 
 static void push_callee_regs(u8 **pprog, bool *callee_regs_used)
 {
@@ -286,6 +298,7 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf,
 	/* BPF trampoline can be made to work without these nops,
 	 * but let's waste 5 bytes for now and optimize later
 	 */
+	EMIT_ENDBR();
 	memcpy(prog, x86_nops[5], X86_PATCH_SIZE);
 	prog += X86_PATCH_SIZE;
 	if (!ebpf_from_cbpf) {
@@ -296,6 +309,10 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf,
 	}
 	EMIT1(0x55);             /* push rbp */
 	EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
+
+	/* X86_TAIL_CALL_OFFSET is here */
+	EMIT_ENDBR();
+
 	/* sub rsp, rounded_stack_depth */
 	if (stack_depth)
 		EMIT3_off32(0x48, 0x81, 0xEC, round_up(stack_depth, 8));
@@ -330,8 +347,7 @@ static int emit_jump(u8 **pprog, void *func, void *ip)
 }
 
 static int __bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
-				void *old_addr, void *new_addr,
-				const bool text_live)
+				void *old_addr, void *new_addr)
 {
 	const u8 *nop_insn = x86_nops[5];
 	u8 old_insn[X86_PATCH_SIZE];
@@ -365,10 +381,7 @@ static int __bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 		goto out;
 	ret = 1;
 	if (memcmp(ip, new_insn, X86_PATCH_SIZE)) {
-		if (text_live)
-			text_poke_bp(ip, new_insn, X86_PATCH_SIZE, NULL);
-		else
-			memcpy(ip, new_insn, X86_PATCH_SIZE);
+		text_poke_bp(ip, new_insn, X86_PATCH_SIZE, NULL);
 		ret = 0;
 	}
 out:
@@ -376,6 +389,18 @@ out:
 	return ret;
 }
 
+int __init bpf_arch_init_dispatcher_early(void *ip)
+{
+	const u8 *nop_insn = x86_nops[5];
+
+	if (is_endbr(*(u32 *)ip))
+		ip += ENDBR_INSN_SIZE;
+
+	if (memcmp(ip, nop_insn, X86_PATCH_SIZE))
+		text_poke_early(ip, nop_insn, X86_PATCH_SIZE);
+	return 0;
+}
+
 int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 		       void *old_addr, void *new_addr)
 {
@@ -384,7 +409,14 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 		/* BPF poking in modules is not supported */
 		return -EINVAL;
 
-	return __bpf_arch_text_poke(ip, t, old_addr, new_addr, true);
+	/*
+	 * See emit_prologue(), for IBT builds the trampoline hook is preceded
+	 * with an ENDBR instruction.
+	 */
+	if (is_endbr(*(u32 *)ip))
+		ip += ENDBR_INSN_SIZE;
+
+	return __bpf_arch_text_poke(ip, t, old_addr, new_addr);
 }
 
 #define EMIT_LFENCE()	EMIT3(0x0F, 0xAE, 0xE8)
@@ -393,15 +425,32 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip)
 {
 	u8 *prog = *pprog;
 
-#ifdef CONFIG_RETPOLINE
-	if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_AMD)) {
+	if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) {
 		EMIT_LFENCE();
 		EMIT2(0xFF, 0xE0 + reg);
 	} else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) {
+		OPTIMIZER_HIDE_VAR(reg);
 		emit_jump(&prog, &__x86_indirect_thunk_array[reg], ip);
-	} else
-#endif
-	EMIT2(0xFF, 0xE0 + reg);
+	} else {
+		EMIT2(0xFF, 0xE0 + reg);	/* jmp *%\reg */
+		if (IS_ENABLED(CONFIG_RETPOLINE) || IS_ENABLED(CONFIG_SLS))
+			EMIT1(0xCC);		/* int3 */
+	}
+
+	*pprog = prog;
+}
+
+static void emit_return(u8 **pprog, u8 *ip)
+{
+	u8 *prog = *pprog;
+
+	if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) {
+		emit_jump(&prog, &__x86_return_thunk, ip);
+	} else {
+		EMIT1(0xC3);		/* ret */
+		if (IS_ENABLED(CONFIG_SLS))
+			EMIT1(0xCC);	/* int3 */
+	}
 
 	*pprog = prog;
 }
@@ -558,24 +607,15 @@ static void bpf_tail_call_direct_fixup(struct bpf_prog *prog)
 		mutex_lock(&array->aux->poke_mutex);
 		target = array->ptrs[poke->tail_call.key];
 		if (target) {
-			/* Plain memcpy is used when image is not live yet
-			 * and still not locked as read-only. Once poke
-			 * location is active (poke->tailcall_target_stable),
-			 * any parallel bpf_arch_text_poke() might occur
-			 * still on the read-write image until we finally
-			 * locked it as read-only. Both modifications on
-			 * the given image are under text_mutex to avoid
-			 * interference.
-			 */
 			ret = __bpf_arch_text_poke(poke->tailcall_target,
 						   BPF_MOD_JUMP, NULL,
 						   (u8 *)target->bpf_func +
-						   poke->adj_off, false);
+						   poke->adj_off);
 			BUG_ON(ret < 0);
 			ret = __bpf_arch_text_poke(poke->tailcall_bypass,
 						   BPF_MOD_JUMP,
 						   (u8 *)poke->tailcall_target +
-						   X86_PATCH_SIZE, NULL, false);
+						   X86_PATCH_SIZE, NULL);
 			BUG_ON(ret < 0);
 		}
 		WRITE_ONCE(poke->tailcall_target_stable, true);
@@ -637,7 +677,7 @@ static void emit_mov_imm64(u8 **pprog, u32 dst_reg,
 		 */
 		emit_mov_imm32(&prog, false, dst_reg, imm32_lo);
 	} else {
-		/* movabsq %rax, imm64 */
+		/* movabsq rax, imm64 */
 		EMIT2(add_1mod(0x48, dst_reg), add_1reg(0xB8, dst_reg));
 		EMIT(imm32_lo, 4);
 		EMIT(imm32_hi, 4);
@@ -787,7 +827,6 @@ static int emit_atomic(u8 **pprog, u8 atomic_op,
 	/* emit opcode */
 	switch (atomic_op) {
 	case BPF_ADD:
-	case BPF_SUB:
 	case BPF_AND:
 	case BPF_OR:
 	case BPF_XOR:
@@ -867,7 +906,7 @@ static void emit_nops(u8 **pprog, int len)
 
 #define INSN_SZ_DIFF (((addrs[i] - addrs[i - 1]) - (prog - temp)))
 
-static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
+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)
 {
 	bool tail_call_reachable = bpf_prog->aux->tail_call_reachable;
@@ -894,8 +933,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 	push_callee_regs(&prog, callee_regs_used);
 
 	ilen = prog - temp;
-	if (image)
-		memcpy(image + proglen, temp, ilen);
+	if (rw_image)
+		memcpy(rw_image + proglen, temp, ilen);
 	proglen += ilen;
 	addrs[0] = proglen;
 	prog = temp;
@@ -1324,9 +1363,12 @@ st:			if (is_imm8(insn->off))
 					pr_err("extable->insn doesn't fit into 32-bit\n");
 					return -EFAULT;
 				}
+				/* switch ex to rw buffer for writes */
+				ex = (void *)rw_image + ((void *)ex - (void *)image);
+
 				ex->insn = delta;
 
-				ex->type = EX_TYPE_BPF;
+				ex->data = EX_TYPE_BPF;
 
 				if (dst_reg > BPF_REG_9) {
 					pr_err("verifier error\n");
@@ -1407,8 +1449,9 @@ st:			if (is_imm8(insn->off))
 		case BPF_JMP | BPF_CALL:
 			func = (u8 *) __bpf_call_base + imm32;
 			if (tail_call_reachable) {
+				/* mov rax, qword ptr [rbp - rounded_stack_depth - 8] */
 				EMIT3_off32(0x48, 0x8B, 0x85,
-					    -(bpf_prog->aux->stack_depth + 8));
+					    -round_up(bpf_prog->aux->stack_depth, 8) - 8);
 				if (!imm32 || emit_call(&prog, func, image + addrs[i - 1] + 7))
 					return -EINVAL;
 			} else {
@@ -1672,7 +1715,7 @@ emit_jmp:
 			ctx->cleanup_addr = proglen;
 			pop_callee_regs(&prog, callee_regs_used);
 			EMIT1(0xC9);         /* leave */
-			EMIT1(0xC3);         /* ret */
+			emit_return(&prog, image + addrs[i - 1] + (prog - temp));
 			break;
 
 		default:
@@ -1706,7 +1749,7 @@ emit_jmp:
 				pr_err("bpf_jit: fatal error\n");
 				return -EFAULT;
 			}
-			memcpy(image + proglen, temp, ilen);
+			memcpy(rw_image + proglen, temp, ilen);
 		}
 		proglen += ilen;
 		addrs[i] = proglen;
@@ -1723,48 +1766,106 @@ emit_jmp:
 static void save_regs(const struct btf_func_model *m, u8 **prog, int nr_args,
 		      int stack_size)
 {
-	int i;
+	int i, j, arg_size, nr_regs;
 	/* Store function arguments to stack.
 	 * For a function that accepts two pointers the sequence will be:
 	 * mov QWORD PTR [rbp-0x10],rdi
 	 * mov QWORD PTR [rbp-0x8],rsi
 	 */
-	for (i = 0; i < min(nr_args, 6); i++)
-		emit_stx(prog, bytes_to_bpf_size(m->arg_size[i]),
-			 BPF_REG_FP,
-			 i == 5 ? X86_REG_R9 : BPF_REG_1 + i,
-			 -(stack_size - i * 8));
+	for (i = 0, j = 0; i < min(nr_args, 6); i++) {
+		if (m->arg_flags[i] & BTF_FMODEL_STRUCT_ARG) {
+			nr_regs = (m->arg_size[i] + 7) / 8;
+			arg_size = 8;
+		} else {
+			nr_regs = 1;
+			arg_size = m->arg_size[i];
+		}
+
+		while (nr_regs) {
+			emit_stx(prog, bytes_to_bpf_size(arg_size),
+				 BPF_REG_FP,
+				 j == 5 ? X86_REG_R9 : BPF_REG_1 + j,
+				 -(stack_size - j * 8));
+			nr_regs--;
+			j++;
+		}
+	}
 }
 
 static void restore_regs(const struct btf_func_model *m, u8 **prog, int nr_args,
 			 int stack_size)
 {
-	int i;
+	int i, j, arg_size, nr_regs;
 
 	/* Restore function arguments from stack.
 	 * For a function that accepts two pointers the sequence will be:
 	 * EMIT4(0x48, 0x8B, 0x7D, 0xF0); mov rdi,QWORD PTR [rbp-0x10]
 	 * EMIT4(0x48, 0x8B, 0x75, 0xF8); mov rsi,QWORD PTR [rbp-0x8]
 	 */
-	for (i = 0; i < min(nr_args, 6); i++)
-		emit_ldx(prog, bytes_to_bpf_size(m->arg_size[i]),
-			 i == 5 ? X86_REG_R9 : BPF_REG_1 + i,
-			 BPF_REG_FP,
-			 -(stack_size - i * 8));
+	for (i = 0, j = 0; i < min(nr_args, 6); i++) {
+		if (m->arg_flags[i] & BTF_FMODEL_STRUCT_ARG) {
+			nr_regs = (m->arg_size[i] + 7) / 8;
+			arg_size = 8;
+		} else {
+			nr_regs = 1;
+			arg_size = m->arg_size[i];
+		}
+
+		while (nr_regs) {
+			emit_ldx(prog, bytes_to_bpf_size(arg_size),
+				 j == 5 ? X86_REG_R9 : BPF_REG_1 + j,
+				 BPF_REG_FP,
+				 -(stack_size - j * 8));
+			nr_regs--;
+			j++;
+		}
+	}
 }
 
 static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
-			   struct bpf_prog *p, int stack_size, bool save_ret)
+			   struct bpf_tramp_link *l, int stack_size,
+			   int run_ctx_off, bool save_ret)
 {
+	void (*exit)(struct bpf_prog *prog, u64 start,
+		     struct bpf_tramp_run_ctx *run_ctx) = __bpf_prog_exit;
+	u64 (*enter)(struct bpf_prog *prog,
+		     struct bpf_tramp_run_ctx *run_ctx) = __bpf_prog_enter;
 	u8 *prog = *pprog;
 	u8 *jmp_insn;
+	int ctx_cookie_off = offsetof(struct bpf_tramp_run_ctx, bpf_cookie);
+	struct bpf_prog *p = l->link.prog;
+	u64 cookie = l->cookie;
+
+	/* mov rdi, cookie */
+	emit_mov_imm64(&prog, BPF_REG_1, (long) cookie >> 32, (u32) (long) cookie);
+
+	/* Prepare struct bpf_tramp_run_ctx.
+	 *
+	 * bpf_tramp_run_ctx is already preserved by
+	 * arch_prepare_bpf_trampoline().
+	 *
+	 * mov QWORD PTR [rbp - run_ctx_off + ctx_cookie_off], rdi
+	 */
+	emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_1, -run_ctx_off + ctx_cookie_off);
+
+	if (p->aux->sleepable) {
+		enter = __bpf_prog_enter_sleepable;
+		exit = __bpf_prog_exit_sleepable;
+	} else if (p->type == BPF_PROG_TYPE_STRUCT_OPS) {
+		enter = __bpf_prog_enter_struct_ops;
+		exit = __bpf_prog_exit_struct_ops;
+	} else if (p->expected_attach_type == BPF_LSM_CGROUP) {
+		enter = __bpf_prog_enter_lsm_cgroup;
+		exit = __bpf_prog_exit_lsm_cgroup;
+	}
 
 	/* arg1: mov rdi, progs[i] */
 	emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32, (u32) (long) p);
-	if (emit_call(&prog,
-		      p->aux->sleepable ? __bpf_prog_enter_sleepable :
-		      __bpf_prog_enter, prog))
-			return -EINVAL;
+	/* arg2: lea rsi, [rbp - ctx_cookie_off] */
+	EMIT4(0x48, 0x8D, 0x75, -run_ctx_off);
+
+	if (emit_call(&prog, enter, prog))
+		return -EINVAL;
 	/* remember prog start time returned by __bpf_prog_enter */
 	emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0);
 
@@ -1806,10 +1907,10 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 	emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32, (u32) (long) p);
 	/* arg2: mov rsi, rbx <- start time in nsec */
 	emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6);
-	if (emit_call(&prog,
-		      p->aux->sleepable ? __bpf_prog_exit_sleepable :
-		      __bpf_prog_exit, prog))
-			return -EINVAL;
+	/* arg3: lea rdx, [rbp - run_ctx_off] */
+	EMIT4(0x48, 0x8D, 0x55, -run_ctx_off);
+	if (emit_call(&prog, exit, prog))
+		return -EINVAL;
 
 	*pprog = prog;
 	return 0;
@@ -1842,15 +1943,15 @@ static int emit_cond_near_jump(u8 **pprog, void *func, void *ip, u8 jmp_cond)
 }
 
 static int invoke_bpf(const struct btf_func_model *m, u8 **pprog,
-		      struct bpf_tramp_progs *tp, int stack_size,
-		      bool save_ret)
+		      struct bpf_tramp_links *tl, int stack_size,
+		      int run_ctx_off, bool save_ret)
 {
 	int i;
 	u8 *prog = *pprog;
 
-	for (i = 0; i < tp->nr_progs; i++) {
-		if (invoke_bpf_prog(m, &prog, tp->progs[i], stack_size,
-				    save_ret))
+	for (i = 0; i < tl->nr_links; i++) {
+		if (invoke_bpf_prog(m, &prog, tl->links[i], stack_size,
+				    run_ctx_off, save_ret))
 			return -EINVAL;
 	}
 	*pprog = prog;
@@ -1858,8 +1959,8 @@ static int invoke_bpf(const struct btf_func_model *m, u8 **pprog,
 }
 
 static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog,
-			      struct bpf_tramp_progs *tp, int stack_size,
-			      u8 **branches)
+			      struct bpf_tramp_links *tl, int stack_size,
+			      int run_ctx_off, u8 **branches)
 {
 	u8 *prog = *pprog;
 	int i;
@@ -1869,8 +1970,8 @@ static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog,
 	 */
 	emit_mov_imm32(&prog, false, BPF_REG_0, 0);
 	emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8);
-	for (i = 0; i < tp->nr_progs; i++) {
-		if (invoke_bpf_prog(m, &prog, tp->progs[i], stack_size, true))
+	for (i = 0; i < tl->nr_links; i++) {
+		if (invoke_bpf_prog(m, &prog, tl->links[i], stack_size, run_ctx_off, true))
 			return -EINVAL;
 
 		/* mod_ret prog stored return value into [rbp - 8]. Emit:
@@ -1893,23 +1994,6 @@ static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog,
 	return 0;
 }
 
-static bool is_valid_bpf_tramp_flags(unsigned int flags)
-{
-	if ((flags & BPF_TRAMP_F_RESTORE_REGS) &&
-	    (flags & BPF_TRAMP_F_SKIP_FRAME))
-		return false;
-
-	/*
-	 * BPF_TRAMP_F_RET_FENTRY_RET is only used by bpf_struct_ops,
-	 * and it must be used alone.
-	 */
-	if ((flags & BPF_TRAMP_F_RET_FENTRY_RET) &&
-	    (flags & ~BPF_TRAMP_F_RET_FENTRY_RET))
-		return false;
-
-	return true;
-}
-
 /* Example:
  * __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev);
  * its 'struct btf_func_model' will be nr_args=2
@@ -1972,14 +2056,15 @@ static bool is_valid_bpf_tramp_flags(unsigned int flags)
  */
 int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end,
 				const struct btf_func_model *m, u32 flags,
-				struct bpf_tramp_progs *tprogs,
-				void *orig_call)
+				struct bpf_tramp_links *tlinks,
+				void *func_addr)
 {
-	int ret, i, nr_args = m->nr_args;
-	int regs_off, ip_off, args_off, stack_size = nr_args * 8;
-	struct bpf_tramp_progs *fentry = &tprogs[BPF_TRAMP_FENTRY];
-	struct bpf_tramp_progs *fexit = &tprogs[BPF_TRAMP_FEXIT];
-	struct bpf_tramp_progs *fmod_ret = &tprogs[BPF_TRAMP_MODIFY_RETURN];
+	int ret, i, nr_args = m->nr_args, extra_nregs = 0;
+	int regs_off, ip_off, args_off, stack_size = nr_args * 8, run_ctx_off;
+	struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY];
+	struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT];
+	struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN];
+	void *orig_call = func_addr;
 	u8 **branches = NULL;
 	u8 *prog;
 	bool save_ret;
@@ -1988,8 +2073,13 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 	if (nr_args > 6)
 		return -ENOTSUPP;
 
-	if (!is_valid_bpf_tramp_flags(flags))
-		return -EINVAL;
+	for (i = 0; i < MAX_BPF_FUNC_ARGS; i++) {
+		if (m->arg_flags[i] & BTF_FMODEL_STRUCT_ARG)
+			extra_nregs += (m->arg_size[i] + 7) / 8 - 1;
+	}
+	if (nr_args + extra_nregs > 6)
+		return -ENOTSUPP;
+	stack_size += extra_nregs * 8;
 
 	/* Generated trampoline stack layout:
 	 *
@@ -2003,9 +2093,11 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 	 *                 [ ...             ]
 	 * RBP - regs_off  [ reg_arg1        ]  program's ctx pointer
 	 *
-	 * RBP - args_off  [ args count      ]  always
+	 * RBP - args_off  [ arg regs count  ]  always
 	 *
 	 * RBP - ip_off    [ traced function ]  BPF_TRAMP_F_IP_ARG flag
+	 *
+	 * RBP - run_ctx_off [ bpf_tramp_run_ctx ]
 	 */
 
 	/* room for return value of orig_call or fentry prog */
@@ -2024,34 +2116,39 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 
 	ip_off = stack_size;
 
-	if (flags & BPF_TRAMP_F_SKIP_FRAME)
+	stack_size += (sizeof(struct bpf_tramp_run_ctx) + 7) & ~0x7;
+	run_ctx_off = stack_size;
+
+	if (flags & BPF_TRAMP_F_SKIP_FRAME) {
 		/* skip patched call instruction and point orig_call to actual
 		 * body of the kernel function.
 		 */
+		if (is_endbr(*(u32 *)orig_call))
+			orig_call += ENDBR_INSN_SIZE;
 		orig_call += X86_PATCH_SIZE;
+	}
 
 	prog = image;
 
+	EMIT_ENDBR();
 	EMIT1(0x55);		 /* push rbp */
 	EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
 	EMIT4(0x48, 0x83, 0xEC, stack_size); /* sub rsp, stack_size */
 	EMIT1(0x53);		 /* push rbx */
 
-	/* Store number of arguments of the traced function:
-	 *   mov rax, nr_args
+	/* Store number of argument registers of the traced function:
+	 *   mov rax, nr_args + extra_nregs
 	 *   mov QWORD PTR [rbp - args_off], rax
 	 */
-	emit_mov_imm64(&prog, BPF_REG_0, 0, (u32) nr_args);
+	emit_mov_imm64(&prog, BPF_REG_0, 0, (u32) nr_args + extra_nregs);
 	emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -args_off);
 
 	if (flags & BPF_TRAMP_F_IP_ARG) {
 		/* Store IP address of the traced function:
-		 * mov rax, QWORD PTR [rbp + 8]
-		 * sub rax, X86_PATCH_SIZE
+		 * movabsq rax, func_addr
 		 * mov QWORD PTR [rbp - ip_off], rax
 		 */
-		emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, 8);
-		EMIT4(0x48, 0x83, 0xe8, X86_PATCH_SIZE);
+		emit_mov_imm64(&prog, BPF_REG_0, (long) func_addr >> 32, (u32) (long) func_addr);
 		emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -ip_off);
 	}
 
@@ -2066,19 +2163,19 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 		}
 	}
 
-	if (fentry->nr_progs)
-		if (invoke_bpf(m, &prog, fentry, regs_off,
+	if (fentry->nr_links)
+		if (invoke_bpf(m, &prog, fentry, regs_off, run_ctx_off,
 			       flags & BPF_TRAMP_F_RET_FENTRY_RET))
 			return -EINVAL;
 
-	if (fmod_ret->nr_progs) {
-		branches = kcalloc(fmod_ret->nr_progs, sizeof(u8 *),
+	if (fmod_ret->nr_links) {
+		branches = kcalloc(fmod_ret->nr_links, sizeof(u8 *),
 				   GFP_KERNEL);
 		if (!branches)
 			return -ENOMEM;
 
 		if (invoke_bpf_mod_ret(m, &prog, fmod_ret, regs_off,
-				       branches)) {
+				       run_ctx_off, branches)) {
 			ret = -EINVAL;
 			goto cleanup;
 		}
@@ -2087,10 +2184,15 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 	if (flags & BPF_TRAMP_F_CALL_ORIG) {
 		restore_regs(m, &prog, nr_args, regs_off);
 
-		/* call original function */
-		if (emit_call(&prog, orig_call, prog)) {
-			ret = -EINVAL;
-			goto cleanup;
+		if (flags & BPF_TRAMP_F_ORIG_STACK) {
+			emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, 8);
+			EMIT2(0xff, 0xd0); /* call *rax */
+		} else {
+			/* call original function */
+			if (emit_call(&prog, orig_call, prog)) {
+				ret = -EINVAL;
+				goto cleanup;
+			}
 		}
 		/* remember return value in a stack for bpf prog to access */
 		emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8);
@@ -2099,7 +2201,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 		prog += X86_PATCH_SIZE;
 	}
 
-	if (fmod_ret->nr_progs) {
+	if (fmod_ret->nr_links) {
 		/* From Intel 64 and IA-32 Architectures Optimization
 		 * Reference Manual, 3.4.1.4 Code Alignment, Assembly/Compiler
 		 * Coding Rule 11: All branch targets should be 16-byte
@@ -2109,13 +2211,13 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 		/* Update the branches saved in invoke_bpf_mod_ret with the
 		 * aligned address of do_fexit.
 		 */
-		for (i = 0; i < fmod_ret->nr_progs; i++)
+		for (i = 0; i < fmod_ret->nr_links; i++)
 			emit_cond_near_jump(&branches[i], prog, branches[i],
 					    X86_JNE);
 	}
 
-	if (fexit->nr_progs)
-		if (invoke_bpf(m, &prog, fexit, regs_off, false)) {
+	if (fexit->nr_links)
+		if (invoke_bpf(m, &prog, fexit, regs_off, run_ctx_off, false)) {
 			ret = -EINVAL;
 			goto cleanup;
 		}
@@ -2145,7 +2247,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 	if (flags & BPF_TRAMP_F_SKIP_FRAME)
 		/* skip our return address and return to parent */
 		EMIT4(0x48, 0x83, 0xC4, 8); /* add rsp, 8 */
-	EMIT1(0xC3); /* ret */
+	emit_return(&prog, prog);
 	/* Make sure the trampoline generation logic doesn't overflow */
 	if (WARN_ON_ONCE(prog > (u8 *)image_end - BPF_INSN_SAFETY)) {
 		ret = -EFAULT;
@@ -2158,7 +2260,7 @@ cleanup:
 	return ret;
 }
 
-static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs)
+static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs, u8 *image, u8 *buf)
 {
 	u8 *jg_reloc, *prog = *pprog;
 	int pivot, err, jg_bytes = 1;
@@ -2174,12 +2276,12 @@ static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs)
 		EMIT2_off32(0x81, add_1reg(0xF8, BPF_REG_3),
 			    progs[a]);
 		err = emit_cond_near_jump(&prog,	/* je func */
-					  (void *)progs[a], prog,
+					  (void *)progs[a], image + (prog - buf),
 					  X86_JE);
 		if (err)
 			return err;
 
-		emit_indirect_jump(&prog, 2 /* rdx */, prog);
+		emit_indirect_jump(&prog, 2 /* rdx */, image + (prog - buf));
 
 		*pprog = prog;
 		return 0;
@@ -2204,7 +2306,7 @@ static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs)
 	jg_reloc = prog;
 
 	err = emit_bpf_dispatcher(&prog, a, a + pivot,	/* emit lower_part */
-				  progs);
+				  progs, image, buf);
 	if (err)
 		return err;
 
@@ -2218,7 +2320,7 @@ static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs)
 	emit_code(jg_reloc - jg_bytes, jg_offset, jg_bytes);
 
 	err = emit_bpf_dispatcher(&prog, a + pivot + 1,	/* emit upper_part */
-				  b, progs);
+				  b, progs, image, buf);
 	if (err)
 		return err;
 
@@ -2238,15 +2340,16 @@ static int cmp_ips(const void *a, const void *b)
 	return 0;
 }
 
-int arch_prepare_bpf_dispatcher(void *image, s64 *funcs, int num_funcs)
+int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_funcs)
 {
-	u8 *prog = image;
+	u8 *prog = buf;
 
 	sort(funcs, num_funcs, sizeof(funcs[0]), cmp_ips, NULL);
-	return emit_bpf_dispatcher(&prog, 0, num_funcs - 1, funcs);
+	return emit_bpf_dispatcher(&prog, 0, num_funcs - 1, funcs, image, buf);
 }
 
 struct x64_jit_data {
+	struct bpf_binary_header *rw_header;
 	struct bpf_binary_header *header;
 	int *addrs;
 	u8 *image;
@@ -2259,6 +2362,7 @@ struct x64_jit_data {
 
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 {
+	struct bpf_binary_header *rw_header = NULL;
 	struct bpf_binary_header *header = NULL;
 	struct bpf_prog *tmp, *orig_prog = prog;
 	struct x64_jit_data *jit_data;
@@ -2267,6 +2371,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	bool tmp_blinded = false;
 	bool extra_pass = false;
 	bool padding = false;
+	u8 *rw_image = NULL;
 	u8 *image = NULL;
 	int *addrs;
 	int pass;
@@ -2302,6 +2407,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		oldproglen = jit_data->proglen;
 		image = jit_data->image;
 		header = jit_data->header;
+		rw_header = jit_data->rw_header;
+		rw_image = (void *)rw_header + ((void *)image - (void *)header);
 		extra_pass = true;
 		padding = true;
 		goto skip_init_addrs;
@@ -2332,13 +2439,22 @@ skip_init_addrs:
 	for (pass = 0; pass < MAX_PASSES || image; pass++) {
 		if (!padding && pass >= PADDING_PASSES)
 			padding = true;
-		proglen = do_jit(prog, addrs, image, oldproglen, &ctx, padding);
+		proglen = do_jit(prog, addrs, image, rw_image, oldproglen, &ctx, padding);
 		if (proglen <= 0) {
 out_image:
 			image = NULL;
-			if (header)
-				bpf_jit_binary_free(header);
+			if (header) {
+				bpf_arch_text_copy(&header->size, &rw_header->size,
+						   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;
+				prog->jited_len = 0;
+			}
 			goto out_addrs;
 		}
 		if (image) {
@@ -2361,8 +2477,9 @@ out_image:
 				sizeof(struct exception_table_entry);
 
 			/* allocate module memory for x86 insns and extable */
-			header = bpf_jit_binary_alloc(roundup(proglen, align) + extable_size,
-						      &image, align, jit_fill_hole);
+			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;
 				goto out_addrs;
@@ -2378,14 +2495,27 @@ out_image:
 
 	if (image) {
 		if (!prog->is_func || extra_pass) {
+			/*
+			 * bpf_jit_binary_pack_finalize fails in two scenarios:
+			 *   1) header is not pointing to proper module memory;
+			 *   2) the arch doesn't support bpf_arch_text_copy().
+			 *
+			 * Both cases are serious bugs and justify WARN_ON.
+			 */
+			if (WARN_ON(bpf_jit_binary_pack_finalize(prog, header, rw_header))) {
+				/* header has been freed */
+				header = NULL;
+				goto out_image;
+			}
+
 			bpf_tail_call_direct_fixup(prog);
-			bpf_jit_binary_lock_ro(header);
 		} else {
 			jit_data->addrs = addrs;
 			jit_data->ctx = ctx;
 			jit_data->proglen = proglen;
 			jit_data->image = image;
 			jit_data->header = header;
+			jit_data->rw_header = rw_header;
 		}
 		prog->bpf_func = (void *)image;
 		prog->jited = 1;
@@ -2413,3 +2543,41 @@ bool bpf_jit_supports_kfunc_call(void)
 {
 	return true;
 }
+
+void *bpf_arch_text_copy(void *dst, void *src, size_t len)
+{
+	if (text_poke_copy(dst, src, len) == NULL)
+		return ERR_PTR(-EINVAL);
+	return dst;
+}
+
+/* Indicate the JIT backend supports mixing bpf2bpf and tailcalls. */
+bool bpf_jit_supports_subprog_tailcalls(void)
+{
+	return true;
+}
+
+void bpf_jit_free(struct bpf_prog *prog)
+{
+	if (prog->jited) {
+		struct x64_jit_data *jit_data = prog->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(prog, jit_data->header,
+						     jit_data->rw_header);
+			kvfree(jit_data->addrs);
+			kfree(jit_data);
+		}
+		hdr = bpf_jit_binary_pack_hdr(prog);
+		bpf_jit_binary_pack_free(hdr, NULL);
+		WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(prog));
+	}
+
+	bpf_prog_unlock_free(prog);
+}