diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 9b1df43dadbb..e0571a24d582 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -486,13 +486,7 @@ static __always_inline __pure bool __static_cpu_has(u16 bit)
 static __always_inline __pure bool _static_cpu_has_safe(u16 bit)
 {
 #ifdef CC_HAVE_ASM_GOTO
-/*
- * We need to spell the jumps to the compiler because, depending on the offset,
- * the replacement jump can be bigger than the original jump, and this we cannot
- * have. Thus, we force the jump to the widest, 4-byte, signed relative
- * offset even though the last would often fit in less bytes.
- */
-		asm_volatile_goto("1: .byte 0xe9\n .long %l[t_dynamic] - 2f\n"
+		asm_volatile_goto("1: jmp %l[t_dynamic]\n"
 			 "2:\n"
 			 ".skip -(((5f-4f) - (2b-1b)) > 0) * "
 			         "((5f-4f) - (2b-1b)),0x90\n"
@@ -506,7 +500,7 @@ static __always_inline __pure bool _static_cpu_has_safe(u16 bit)
 			 " .byte 3b - 2b\n"		/* pad len */
 			 ".previous\n"
 			 ".section .altinstr_replacement,\"ax\"\n"
-			 "4: .byte 0xe9\n .long %l[t_no] - 2b\n"
+			 "4: jmp %l[t_no]\n"
 			 "5:\n"
 			 ".previous\n"
 			 ".section .altinstructions,\"a\"\n"
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index c99b0f13a90e..715af37bf008 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -58,6 +58,21 @@ do {									\
 		printk(KERN_DEBUG "%s: " fmt "\n", __func__, ##args);	\
 } while (0)
 
+#define DUMP_BYTES(buf, len, fmt, args...)				\
+do {									\
+	if (unlikely(debug_alternative)) {				\
+		int j;							\
+									\
+		if (!(len))						\
+			break;						\
+									\
+		printk(KERN_DEBUG fmt, ##args);				\
+		for (j = 0; j < (len) - 1; j++)				\
+			printk(KERN_CONT "%02hhx ", buf[j]);		\
+		printk(KERN_CONT "%02hhx\n", buf[j]);			\
+	}								\
+} while (0)
+
 /*
  * Each GENERIC_NOPX is of X bytes, and defined as an array of bytes
  * that correspond to that nop. Getting from one nop to the next, we
@@ -243,6 +258,71 @@ extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
 extern s32 __smp_locks[], __smp_locks_end[];
 void *text_poke_early(void *addr, const void *opcode, size_t len);
 
+/*
+ * Are we looking at a near JMP with a 1 or 4-byte displacement.
+ */
+static inline bool is_jmp(const u8 opcode)
+{
+	return opcode == 0xeb || opcode == 0xe9;
+}
+
+static void __init_or_module
+recompute_jump(struct alt_instr *a, u8 *orig_insn, u8 *repl_insn, u8 *insnbuf)
+{
+	u8 *next_rip, *tgt_rip;
+	s32 n_dspl, o_dspl;
+	int repl_len;
+
+	if (a->replacementlen != 5)
+		return;
+
+	o_dspl = *(s32 *)(insnbuf + 1);
+
+	/* next_rip of the replacement JMP */
+	next_rip = repl_insn + a->replacementlen;
+	/* target rip of the replacement JMP */
+	tgt_rip  = next_rip + o_dspl;
+	n_dspl = tgt_rip - orig_insn;
+
+	DPRINTK("target RIP: %p, new_displ: 0x%x", tgt_rip, n_dspl);
+
+	if (tgt_rip - orig_insn >= 0) {
+		if (n_dspl - 2 <= 127)
+			goto two_byte_jmp;
+		else
+			goto five_byte_jmp;
+	/* negative offset */
+	} else {
+		if (((n_dspl - 2) & 0xff) == (n_dspl - 2))
+			goto two_byte_jmp;
+		else
+			goto five_byte_jmp;
+	}
+
+two_byte_jmp:
+	n_dspl -= 2;
+
+	insnbuf[0] = 0xeb;
+	insnbuf[1] = (s8)n_dspl;
+	add_nops(insnbuf + 2, 3);
+
+	repl_len = 2;
+	goto done;
+
+five_byte_jmp:
+	n_dspl -= 5;
+
+	insnbuf[0] = 0xe9;
+	*(s32 *)&insnbuf[1] = n_dspl;
+
+	repl_len = 5;
+
+done:
+
+	DPRINTK("final displ: 0x%08x, JMP 0x%lx",
+		n_dspl, (unsigned long)orig_insn + n_dspl + repl_len);
+}
+
 /*
  * Replace instructions with better alternatives for this CPU type. This runs
  * before SMP is initialized to avoid SMP problems with self modifying code.
@@ -268,6 +348,8 @@ void __init_or_module apply_alternatives(struct alt_instr *start,
 	 * order.
 	 */
 	for (a = start; a < end; a++) {
+		int insnbuf_sz = 0;
+
 		instr = (u8 *)&a->instr_offset + a->instr_offset;
 		replacement = (u8 *)&a->repl_offset + a->repl_offset;
 		BUG_ON(a->instrlen > sizeof(insnbuf));
@@ -281,24 +363,35 @@ void __init_or_module apply_alternatives(struct alt_instr *start,
 			instr, a->instrlen,
 			replacement, a->replacementlen);
 
+		DUMP_BYTES(instr, a->instrlen, "%p: old_insn: ", instr);
+		DUMP_BYTES(replacement, a->replacementlen, "%p: rpl_insn: ", replacement);
+
 		memcpy(insnbuf, replacement, a->replacementlen);
+		insnbuf_sz = a->replacementlen;
 
 		/* 0xe8 is a relative jump; fix the offset. */
 		if (*insnbuf == 0xe8 && a->replacementlen == 5) {
 			*(s32 *)(insnbuf + 1) += replacement - instr;
-			DPRINTK("Fix CALL offset: 0x%x", *(s32 *)(insnbuf + 1));
+			DPRINTK("Fix CALL offset: 0x%x, CALL 0x%lx",
+				*(s32 *)(insnbuf + 1),
+				(unsigned long)instr + *(s32 *)(insnbuf + 1) + 5);
 		}
 
-		if (a->instrlen > a->replacementlen)
+		if (a->replacementlen && is_jmp(replacement[0]))
+			recompute_jump(a, instr, replacement, insnbuf);
+
+		if (a->instrlen > a->replacementlen) {
 			add_nops(insnbuf + a->replacementlen,
 				 a->instrlen - a->replacementlen);
+			insnbuf_sz += a->instrlen - a->replacementlen;
+		}
+		DUMP_BYTES(insnbuf, insnbuf_sz, "%p: final_insn: ", instr);
 
-		text_poke_early(instr, insnbuf, a->instrlen);
+		text_poke_early(instr, insnbuf, insnbuf_sz);
 	}
 }
 
 #ifdef CONFIG_SMP
-
 static void alternatives_smp_lock(const s32 *start, const s32 *end,
 				  u8 *text, u8 *text_end)
 {
@@ -449,7 +542,7 @@ int alternatives_text_reserved(void *start, void *end)
 
 	return 0;
 }
-#endif
+#endif /* CONFIG_SMP */
 
 #ifdef CONFIG_PARAVIRT
 void __init_or_module apply_paravirt(struct paravirt_patch_site *start,
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index a9aedd6aa7f7..dad718ce805c 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -25,14 +25,13 @@
  */
 	.macro ALTERNATIVE_JUMP feature1,feature2,orig,alt1,alt2
 0:
-	.byte 0xe9	/* 32bit jump */
-	.long \orig-1f	/* by default jump to orig */
+	jmp \orig
 1:
 	.section .altinstr_replacement,"ax"
-2:	.byte 0xe9			/* near jump with 32bit immediate */
-	.long \alt1-1b /* offset */   /* or alternatively to alt1 */
-3:	.byte 0xe9			/* near jump with 32bit immediate */
-	.long \alt2-1b /* offset */   /* or alternatively to alt2 */
+2:
+	jmp \alt1
+3:
+	jmp \alt2
 	.previous
 
 	.section .altinstructions,"a"