1 files changed, 97 insertions, 204 deletions

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 8d778e46725d..6974b5174495 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -28,6 +28,7 @@
 #include <asm/insn.h>
 #include <asm/io.h>
 #include <asm/fixmap.h>
+#include <asm/paravirt.h>
 
 int __read_mostly alternatives_patched;
 
@@ -74,186 +75,30 @@ do {									\
 	}								\
 } 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
- * add to the array the offset that is equal to the sum of all sizes of
- * nops preceding the one we are after.
- *
- * Note: The GENERIC_NOP5_ATOMIC is at the end, as it breaks the
- * nice symmetry of sizes of the previous nops.
- */
-#if defined(GENERIC_NOP1) && !defined(CONFIG_X86_64)
-static const unsigned char intelnops[] =
-{
-	GENERIC_NOP1,
-	GENERIC_NOP2,
-	GENERIC_NOP3,
-	GENERIC_NOP4,
-	GENERIC_NOP5,
-	GENERIC_NOP6,
-	GENERIC_NOP7,
-	GENERIC_NOP8,
-	GENERIC_NOP5_ATOMIC
-};
-static const unsigned char * const intel_nops[ASM_NOP_MAX+2] =
+const unsigned char x86nops[] =
 {
-	NULL,
-	intelnops,
-	intelnops + 1,
-	intelnops + 1 + 2,
-	intelnops + 1 + 2 + 3,
-	intelnops + 1 + 2 + 3 + 4,
-	intelnops + 1 + 2 + 3 + 4 + 5,
-	intelnops + 1 + 2 + 3 + 4 + 5 + 6,
-	intelnops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
-	intelnops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8,
+	BYTES_NOP1,
+	BYTES_NOP2,
+	BYTES_NOP3,
+	BYTES_NOP4,
+	BYTES_NOP5,
+	BYTES_NOP6,
+	BYTES_NOP7,
+	BYTES_NOP8,
 };
-#endif
 
-#ifdef K8_NOP1
-static const unsigned char k8nops[] =
-{
-	K8_NOP1,
-	K8_NOP2,
-	K8_NOP3,
-	K8_NOP4,
-	K8_NOP5,
-	K8_NOP6,
-	K8_NOP7,
-	K8_NOP8,
-	K8_NOP5_ATOMIC
-};
-static const unsigned char * const k8_nops[ASM_NOP_MAX+2] =
+const unsigned char * const x86_nops[ASM_NOP_MAX+1] =
 {
 	NULL,
-	k8nops,
-	k8nops + 1,
-	k8nops + 1 + 2,
-	k8nops + 1 + 2 + 3,
-	k8nops + 1 + 2 + 3 + 4,
-	k8nops + 1 + 2 + 3 + 4 + 5,
-	k8nops + 1 + 2 + 3 + 4 + 5 + 6,
-	k8nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
-	k8nops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8,
+	x86nops,
+	x86nops + 1,
+	x86nops + 1 + 2,
+	x86nops + 1 + 2 + 3,
+	x86nops + 1 + 2 + 3 + 4,
+	x86nops + 1 + 2 + 3 + 4 + 5,
+	x86nops + 1 + 2 + 3 + 4 + 5 + 6,
+	x86nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
 };
-#endif
-
-#if defined(K7_NOP1) && !defined(CONFIG_X86_64)
-static const unsigned char k7nops[] =
-{
-	K7_NOP1,
-	K7_NOP2,
-	K7_NOP3,
-	K7_NOP4,
-	K7_NOP5,
-	K7_NOP6,
-	K7_NOP7,
-	K7_NOP8,
-	K7_NOP5_ATOMIC
-};
-static const unsigned char * const k7_nops[ASM_NOP_MAX+2] =
-{
-	NULL,
-	k7nops,
-	k7nops + 1,
-	k7nops + 1 + 2,
-	k7nops + 1 + 2 + 3,
-	k7nops + 1 + 2 + 3 + 4,
-	k7nops + 1 + 2 + 3 + 4 + 5,
-	k7nops + 1 + 2 + 3 + 4 + 5 + 6,
-	k7nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
-	k7nops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8,
-};
-#endif
-
-#ifdef P6_NOP1
-static const unsigned char p6nops[] =
-{
-	P6_NOP1,
-	P6_NOP2,
-	P6_NOP3,
-	P6_NOP4,
-	P6_NOP5,
-	P6_NOP6,
-	P6_NOP7,
-	P6_NOP8,
-	P6_NOP5_ATOMIC
-};
-static const unsigned char * const p6_nops[ASM_NOP_MAX+2] =
-{
-	NULL,
-	p6nops,
-	p6nops + 1,
-	p6nops + 1 + 2,
-	p6nops + 1 + 2 + 3,
-	p6nops + 1 + 2 + 3 + 4,
-	p6nops + 1 + 2 + 3 + 4 + 5,
-	p6nops + 1 + 2 + 3 + 4 + 5 + 6,
-	p6nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
-	p6nops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8,
-};
-#endif
-
-/* Initialize these to a safe default */
-#ifdef CONFIG_X86_64
-const unsigned char * const *ideal_nops = p6_nops;
-#else
-const unsigned char * const *ideal_nops = intel_nops;
-#endif
-
-void __init arch_init_ideal_nops(void)
-{
-	switch (boot_cpu_data.x86_vendor) {
-	case X86_VENDOR_INTEL:
-		/*
-		 * Due to a decoder implementation quirk, some
-		 * specific Intel CPUs actually perform better with
-		 * the "k8_nops" than with the SDM-recommended NOPs.
-		 */
-		if (boot_cpu_data.x86 == 6 &&
-		    boot_cpu_data.x86_model >= 0x0f &&
-		    boot_cpu_data.x86_model != 0x1c &&
-		    boot_cpu_data.x86_model != 0x26 &&
-		    boot_cpu_data.x86_model != 0x27 &&
-		    boot_cpu_data.x86_model < 0x30) {
-			ideal_nops = k8_nops;
-		} else if (boot_cpu_has(X86_FEATURE_NOPL)) {
-			   ideal_nops = p6_nops;
-		} else {
-#ifdef CONFIG_X86_64
-			ideal_nops = k8_nops;
-#else
-			ideal_nops = intel_nops;
-#endif
-		}
-		break;
-
-	case X86_VENDOR_HYGON:
-		ideal_nops = p6_nops;
-		return;
-
-	case X86_VENDOR_AMD:
-		if (boot_cpu_data.x86 > 0xf) {
-			ideal_nops = p6_nops;
-			return;
-		}
-
-		fallthrough;
-
-	default:
-#ifdef CONFIG_X86_64
-		ideal_nops = k8_nops;
-#else
-		if (boot_cpu_has(X86_FEATURE_K8))
-			ideal_nops = k8_nops;
-		else if (boot_cpu_has(X86_FEATURE_K7))
-			ideal_nops = k7_nops;
-		else
-			ideal_nops = intel_nops;
-#endif
-	}
-}
 
 /* Use this to add nops to a buffer, then text_poke the whole buffer. */
 static void __init_or_module add_nops(void *insns, unsigned int len)
@@ -262,7 +107,7 @@ static void __init_or_module add_nops(void *insns, unsigned int len)
 		unsigned int noplen = len;
 		if (noplen > ASM_NOP_MAX)
 			noplen = ASM_NOP_MAX;
-		memcpy(insns, ideal_nops[noplen], noplen);
+		memcpy(insns, x86_nops[noplen], noplen);
 		insns += noplen;
 		len -= noplen;
 	}
@@ -344,19 +189,35 @@ done:
 static void __init_or_module noinline optimize_nops(struct alt_instr *a, u8 *instr)
 {
 	unsigned long flags;
-	int i;
+	struct insn insn;
+	int nop, i = 0;
+
+	/*
+	 * Jump over the non-NOP insns, the remaining bytes must be single-byte
+	 * NOPs, optimize them.
+	 */
+	for (;;) {
+		if (insn_decode_kernel(&insn, &instr[i]))
+			return;
+
+		if (insn.length == 1 && insn.opcode.bytes[0] == 0x90)
+			break;
+
+		if ((i += insn.length) >= a->instrlen)
+			return;
+	}
 
-	for (i = 0; i < a->padlen; i++) {
-		if (instr[i] != 0x90)
+	for (nop = i; i < a->instrlen; i++) {
+		if (WARN_ONCE(instr[i] != 0x90, "Not a NOP at 0x%px\n", &instr[i]))
 			return;
 	}
 
 	local_irq_save(flags);
-	add_nops(instr + (a->instrlen - a->padlen), a->padlen);
+	add_nops(instr + nop, i - nop);
 	local_irq_restore(flags);
 
 	DUMP_BYTES(instr, a->instrlen, "%px: [%d:%d) optimized NOPs: ",
-		   instr, a->instrlen - a->padlen, a->padlen);
+		   instr, nop, a->instrlen);
 }
 
 /*
@@ -388,23 +249,29 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 	 */
 	for (a = start; a < end; a++) {
 		int insn_buff_sz = 0;
+		/* Mask away "NOT" flag bit for feature to test. */
+		u16 feature = a->cpuid & ~ALTINSTR_FLAG_INV;
 
 		instr = (u8 *)&a->instr_offset + a->instr_offset;
 		replacement = (u8 *)&a->repl_offset + a->repl_offset;
 		BUG_ON(a->instrlen > sizeof(insn_buff));
-		BUG_ON(a->cpuid >= (NCAPINTS + NBUGINTS) * 32);
-		if (!boot_cpu_has(a->cpuid)) {
-			if (a->padlen > 1)
-				optimize_nops(a, instr);
+		BUG_ON(feature >= (NCAPINTS + NBUGINTS) * 32);
 
-			continue;
-		}
+		/*
+		 * Patch if either:
+		 * - feature is present
+		 * - feature not present but ALTINSTR_FLAG_INV is set to mean,
+		 *   patch if feature is *NOT* present.
+		 */
+		if (!boot_cpu_has(feature) == !(a->cpuid & ALTINSTR_FLAG_INV))
+			goto next;
 
-		DPRINTK("feat: %d*32+%d, old: (%pS (%px) len: %d), repl: (%px, len: %d), pad: %d",
-			a->cpuid >> 5,
-			a->cpuid & 0x1f,
+		DPRINTK("feat: %s%d*32+%d, old: (%pS (%px) len: %d), repl: (%px, len: %d)",
+			(a->cpuid & ALTINSTR_FLAG_INV) ? "!" : "",
+			feature >> 5,
+			feature & 0x1f,
 			instr, instr, a->instrlen,
-			replacement, a->replacementlen, a->padlen);
+			replacement, a->replacementlen);
 
 		DUMP_BYTES(instr, a->instrlen, "%px: old_insn: ", instr);
 		DUMP_BYTES(replacement, a->replacementlen, "%px: rpl_insn: ", replacement);
@@ -428,14 +295,15 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 		if (a->replacementlen && is_jmp(replacement[0]))
 			recompute_jump(a, instr, replacement, insn_buff);
 
-		if (a->instrlen > a->replacementlen) {
-			add_nops(insn_buff + a->replacementlen,
-				 a->instrlen - a->replacementlen);
-			insn_buff_sz += a->instrlen - a->replacementlen;
-		}
+		for (; insn_buff_sz < a->instrlen; insn_buff_sz++)
+			insn_buff[insn_buff_sz] = 0x90;
+
 		DUMP_BYTES(insn_buff, insn_buff_sz, "%px: final_insn: ", instr);
 
 		text_poke_early(instr, insn_buff, insn_buff_sz);
+
+next:
+		optimize_nops(a, instr);
 	}
 }
 
@@ -605,7 +473,7 @@ void __init_or_module apply_paravirt(struct paravirt_patch_site *start,
 		BUG_ON(p->len > MAX_PATCH_LEN);
 		/* prep the buffer with the original instructions */
 		memcpy(insn_buff, p->instr, p->len);
-		used = pv_ops.init.patch(p->type, insn_buff, (unsigned long)p->instr, p->len);
+		used = paravirt_patch(p->type, insn_buff, (unsigned long)p->instr, p->len);
 
 		BUG_ON(used > p->len);
 
@@ -723,6 +591,33 @@ void __init alternative_instructions(void)
 	 * patching.
 	 */
 
+	/*
+	 * Paravirt patching and alternative patching can be combined to
+	 * replace a function call with a short direct code sequence (e.g.
+	 * by setting a constant return value instead of doing that in an
+	 * external function).
+	 * In order to make this work the following sequence is required:
+	 * 1. set (artificial) features depending on used paravirt
+	 *    functions which can later influence alternative patching
+	 * 2. apply paravirt patching (generally replacing an indirect
+	 *    function call with a direct one)
+	 * 3. apply alternative patching (e.g. replacing a direct function
+	 *    call with a custom code sequence)
+	 * Doing paravirt patching after alternative patching would clobber
+	 * the optimization of the custom code with a function call again.
+	 */
+	paravirt_set_cap();
+
+	/*
+	 * First patch paravirt functions, such that we overwrite the indirect
+	 * call with the direct call.
+	 */
+	apply_paravirt(__parainstructions, __parainstructions_end);
+
+	/*
+	 * Then patch alternatives, such that those paravirt calls that are in
+	 * alternatives can be overwritten by their immediate fragments.
+	 */
 	apply_alternatives(__alt_instructions, __alt_instructions_end);
 
 #ifdef CONFIG_SMP
@@ -741,8 +636,6 @@ void __init alternative_instructions(void)
 	}
 #endif
 
-	apply_paravirt(__parainstructions, __parainstructions_end);
-
 	restart_nmi();
 	alternatives_patched = 1;
 }
@@ -813,7 +706,7 @@ static inline temp_mm_state_t use_temporary_mm(struct mm_struct *mm)
 	 * with a stale address space WITHOUT being in lazy mode after
 	 * restoring the previous mm.
 	 */
-	if (this_cpu_read(cpu_tlbstate.is_lazy))
+	if (this_cpu_read(cpu_tlbstate_shared.is_lazy))
 		leave_mm(smp_processor_id());
 
 	temp_state.mm = this_cpu_read(cpu_tlbstate.loaded_mm);
@@ -1274,15 +1167,15 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
 			       const void *opcode, size_t len, const void *emulate)
 {
 	struct insn insn;
+	int ret;
 
 	memcpy((void *)tp->text, opcode, len);
 	if (!emulate)
 		emulate = opcode;
 
-	kernel_insn_init(&insn, emulate, MAX_INSN_SIZE);
-	insn_get_length(&insn);
+	ret = insn_decode_kernel(&insn, emulate);
 
-	BUG_ON(!insn_complete(&insn));
+	BUG_ON(ret < 0);
 	BUG_ON(len != insn.length);
 
 	tp->rel_addr = addr - (void *)_stext;
@@ -1302,13 +1195,13 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
 	default: /* assume NOP */
 		switch (len) {
 		case 2: /* NOP2 -- emulate as JMP8+0 */
-			BUG_ON(memcmp(emulate, ideal_nops[len], len));
+			BUG_ON(memcmp(emulate, x86_nops[len], len));
 			tp->opcode = JMP8_INSN_OPCODE;
 			tp->rel32 = 0;
 			break;
 
 		case 5: /* NOP5 -- emulate as JMP32+0 */
-			BUG_ON(memcmp(emulate, ideal_nops[NOP_ATOMIC5], len));
+			BUG_ON(memcmp(emulate, x86_nops[len], len));
 			tp->opcode = JMP32_INSN_OPCODE;
 			tp->rel32 = 0;
 			break;