Merge tag 'x86_core_for_v5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 updates from Borislav Petkov:

 - Turn the stack canary into a normal __percpu variable on 32-bit which
   gets rid of the LAZY_GS stuff and a lot of code.

 - Add an insn_decode() API which all users of the instruction decoder
   should preferrably use. Its goal is to keep the details of the
   instruction decoder away from its users and simplify and streamline
   how one decodes insns in the kernel. Convert its users to it.

 - kprobes improvements and fixes

 - Set the maximum DIE per package variable on Hygon

 - Rip out the dynamic NOP selection and simplify all the machinery
   around selecting NOPs. Use the simplified NOPs in objtool now too.

 - Add Xeon Sapphire Rapids to list of CPUs that support PPIN

 - Simplify the retpolines by folding the entire thing into an
   alternative now that objtool can handle alternatives with stack ops.
   Then, have objtool rewrite the call to the retpoline with the
   alternative which then will get patched at boot time.

 - Document Intel uarch per models in intel-family.h

 - Make Sub-NUMA Clustering topology the default and Cluster-on-Die the
   exception on Intel.

* tag 'x86_core_for_v5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (53 commits)
  x86, sched: Treat Intel SNC topology as default, COD as exception
  x86/cpu: Comment Skylake server stepping too
  x86/cpu: Resort and comment Intel models
  objtool/x86: Rewrite retpoline thunk calls
  objtool: Skip magical retpoline .altinstr_replacement
  objtool: Cache instruction relocs
  objtool: Keep track of retpoline call sites
  objtool: Add elf_create_undef_symbol()
  objtool: Extract elf_symbol_add()
  objtool: Extract elf_strtab_concat()
  objtool: Create reloc sections implicitly
  objtool: Add elf_create_reloc() helper
  objtool: Rework the elf_rebuild_reloc_section() logic
  objtool: Fix static_call list generation
  objtool: Handle per arch retpoline naming
  objtool: Correctly handle retpoline thunk calls
  x86/retpoline: Simplify retpolines
  x86/alternatives: Optimize optimize_nops()
  x86: Add insn_decode_kernel()
  x86/kprobes: Move 'inline' to the beginning of the kprobe_is_ss() declaration
  ...

Author: torvalds

arch/x86/Kconfig

@@ -361,10 +361,6 @@ config X86_64_SMP
 	def_bool y
 	depends on X86_64 && SMP
 
-config X86_32_LAZY_GS
-	def_bool y
-	depends on X86_32 && !STACKPROTECTOR
-
 config ARCH_SUPPORTS_UPROBES
 	def_bool y
 
@@ -387,7 +383,8 @@ config CC_HAS_SANE_STACKPROTECTOR
 	default $(success,$(srctree)/scripts/gcc-x86_32-has-stack-protector.sh $(CC))
 	help
 	   We have to make sure stack protector is unconditionally disabled if
-	   the compiler produces broken code.
+	   the compiler produces broken code or if it does not let us control
+	   the segment on 32-bit kernels.
 
 menu "Processor type and features"
 

arch/x86/Makefile

@@ -80,6 +80,14 @@ ifeq ($(CONFIG_X86_32),y)
 
         # temporary until string.h is fixed
         KBUILD_CFLAGS += -ffreestanding
+
+	ifeq ($(CONFIG_STACKPROTECTOR),y)
+		ifeq ($(CONFIG_SMP),y)
+			KBUILD_CFLAGS += -mstack-protector-guard-reg=fs -mstack-protector-guard-symbol=__stack_chk_guard
+		else
+			KBUILD_CFLAGS += -mstack-protector-guard=global
+		endif
+	endif
 else
         BITS := 64
         UTS_MACHINE := x86_64

arch/x86/boot/compressed/sev-es.c

@@ -78,16 +78,15 @@ static inline void sev_es_wr_ghcb_msr(u64 val)
 static enum es_result vc_decode_insn(struct es_em_ctxt *ctxt)
 {
 	char buffer[MAX_INSN_SIZE];
-	enum es_result ret;
+	int ret;
 
 	memcpy(buffer, (unsigned char *)ctxt->regs->ip, MAX_INSN_SIZE);
 
-	insn_init(&ctxt->insn, buffer, MAX_INSN_SIZE, 1);
-	insn_get_length(&ctxt->insn);
+	ret = insn_decode(&ctxt->insn, buffer, MAX_INSN_SIZE, INSN_MODE_64);
+	if (ret < 0)
+		return ES_DECODE_FAILED;
 
-	ret = ctxt->insn.immediate.got ? ES_OK : ES_DECODE_FAILED;
-
-	return ret;
+	return ES_OK;
 }
 
 static enum es_result vc_write_mem(struct es_em_ctxt *ctxt,

arch/x86/entry/entry_32.S

@@ -20,7 +20,7 @@
  *	1C(%esp) - %ds
  *	20(%esp) - %es
  *	24(%esp) - %fs
- *	28(%esp) - %gs		saved iff !CONFIG_X86_32_LAZY_GS
+ *	28(%esp) - unused -- was %gs on old stackprotector kernels
  *	2C(%esp) - orig_eax
  *	30(%esp) - %eip
  *	34(%esp) - %cs
@@ -53,83 +53,6 @@
 
 #define PTI_SWITCH_MASK         (1 << PAGE_SHIFT)
 
-/*
- * User gs save/restore
- *
- * %gs is used for userland TLS and kernel only uses it for stack
- * canary which is required to be at %gs:20 by gcc.  Read the comment
- * at the top of stackprotector.h for more info.
- *
- * Local labels 98 and 99 are used.
- */
-#ifdef CONFIG_X86_32_LAZY_GS
-
- /* unfortunately push/pop can't be no-op */
-.macro PUSH_GS
-	pushl	$0
-.endm
-.macro POP_GS pop=0
-	addl	$(4 + \pop), %esp
-.endm
-.macro POP_GS_EX
-.endm
-
- /* all the rest are no-op */
-.macro PTGS_TO_GS
-.endm
-.macro PTGS_TO_GS_EX
-.endm
-.macro GS_TO_REG reg
-.endm
-.macro REG_TO_PTGS reg
-.endm
-.macro SET_KERNEL_GS reg
-.endm
-
-#else	/* CONFIG_X86_32_LAZY_GS */
-
-.macro PUSH_GS
-	pushl	%gs
-.endm
-
-.macro POP_GS pop=0
-98:	popl	%gs
-  .if \pop <> 0
-	add	$\pop, %esp
-  .endif
-.endm
-.macro POP_GS_EX
-.pushsection .fixup, "ax"
-99:	movl	$0, (%esp)
-	jmp	98b
-.popsection
-	_ASM_EXTABLE(98b, 99b)
-.endm
-
-.macro PTGS_TO_GS
-98:	mov	PT_GS(%esp), %gs
-.endm
-.macro PTGS_TO_GS_EX
-.pushsection .fixup, "ax"
-99:	movl	$0, PT_GS(%esp)
-	jmp	98b
-.popsection
-	_ASM_EXTABLE(98b, 99b)
-.endm
-
-.macro GS_TO_REG reg
-	movl	%gs, \reg
-.endm
-.macro REG_TO_PTGS reg
-	movl	\reg, PT_GS(%esp)
-.endm
-.macro SET_KERNEL_GS reg
-	movl	$(__KERNEL_STACK_CANARY), \reg
-	movl	\reg, %gs
-.endm
-
-#endif /* CONFIG_X86_32_LAZY_GS */
-
 /* Unconditionally switch to user cr3 */
 .macro SWITCH_TO_USER_CR3 scratch_reg:req
 	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
@@ -282,7 +205,7 @@
 .macro SAVE_ALL pt_regs_ax=%eax switch_stacks=0 skip_gs=0 unwind_espfix=0
 	cld
 .if \skip_gs == 0
-	PUSH_GS
+	pushl	$0
 .endif
 	pushl	%fs
 
@@ -307,9 +230,6 @@
 	movl	$(__USER_DS), %edx
 	movl	%edx, %ds
 	movl	%edx, %es
-.if \skip_gs == 0
-	SET_KERNEL_GS %edx
-.endif
 	/* Switch to kernel stack if necessary */
 .if \switch_stacks > 0
 	SWITCH_TO_KERNEL_STACK
@@ -348,7 +268,7 @@
 1:	popl	%ds
 2:	popl	%es
 3:	popl	%fs
-	POP_GS \pop
+	addl	$(4 + \pop), %esp	/* pop the unused "gs" slot */
 	IRET_FRAME
 .pushsection .fixup, "ax"
 4:	movl	$0, (%esp)
@@ -361,7 +281,6 @@
 	_ASM_EXTABLE(1b, 4b)
 	_ASM_EXTABLE(2b, 5b)
 	_ASM_EXTABLE(3b, 6b)
-	POP_GS_EX
 .endm
 
 .macro RESTORE_ALL_NMI cr3_reg:req pop=0
@@ -779,7 +698,7 @@ SYM_CODE_START(__switch_to_asm)
 
 #ifdef CONFIG_STACKPROTECTOR
 	movl	TASK_stack_canary(%edx), %ebx
-	movl	%ebx, PER_CPU_VAR(stack_canary)+stack_canary_offset
+	movl	%ebx, PER_CPU_VAR(__stack_chk_guard)
 #endif
 
 #ifdef CONFIG_RETPOLINE
@@ -976,7 +895,6 @@ SYM_FUNC_START(entry_SYSENTER_32)
 	movl	PT_EIP(%esp), %edx	/* pt_regs->ip */
 	movl	PT_OLDESP(%esp), %ecx	/* pt_regs->sp */
 1:	mov	PT_FS(%esp), %fs
-	PTGS_TO_GS
 
 	popl	%ebx			/* pt_regs->bx */
 	addl	$2*4, %esp		/* skip pt_regs->cx and pt_regs->dx */
@@ -1012,7 +930,6 @@ SYM_FUNC_START(entry_SYSENTER_32)
 	jmp	1b
 .popsection
 	_ASM_EXTABLE(1b, 2b)
-	PTGS_TO_GS_EX
 
 .Lsysenter_fix_flags:
 	pushl	$X86_EFLAGS_FIXED
@@ -1154,11 +1071,7 @@ SYM_CODE_START_LOCAL_NOALIGN(handle_exception)
 	SAVE_ALL switch_stacks=1 skip_gs=1 unwind_espfix=1
 	ENCODE_FRAME_POINTER
 
-	/* fixup %gs */
-	GS_TO_REG %ecx
 	movl	PT_GS(%esp), %edi		# get the function address
-	REG_TO_PTGS %ecx
-	SET_KERNEL_GS %ecx
 
 	/* fixup orig %eax */
 	movl	PT_ORIG_EAX(%esp), %edx		# get the error code

arch/x86/events/intel/ds.c

@@ -1353,14 +1353,13 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
 		is_64bit = kernel_ip(to) || any_64bit_mode(regs);
 #endif
 		insn_init(&insn, kaddr, size, is_64bit);
-		insn_get_length(&insn);
+
 		/*
-		 * Make sure there was not a problem decoding the
-		 * instruction and getting the length.  This is
-		 * doubly important because we have an infinite
-		 * loop if insn.length=0.
+		 * Make sure there was not a problem decoding the instruction.
+		 * This is doubly important because we have an infinite loop if
+		 * insn.length=0.
 		 */
-		if (!insn.length)
+		if (insn_get_length(&insn))
 			break;
 
 		to += insn.length;

arch/x86/events/intel/lbr.c

@@ -1224,8 +1224,7 @@ static int branch_type(unsigned long from, unsigned long to, int abort)
 	is64 = kernel_ip((unsigned long)addr) || any_64bit_mode(current_pt_regs());
 #endif
 	insn_init(&insn, addr, bytes_read, is64);
-	insn_get_opcode(&insn);
-	if (!insn.opcode.got)
+	if (insn_get_opcode(&insn))
 		return X86_BR_ABORT;
 
 	switch (insn.opcode.bytes[0]) {
@@ -1262,8 +1261,7 @@ static int branch_type(unsigned long from, unsigned long to, int abort)
 		ret = X86_BR_INT;
 		break;
 	case 0xe8: /* call near rel */
-		insn_get_immediate(&insn);
-		if (insn.immediate1.value == 0) {
+		if (insn_get_immediate(&insn) || insn.immediate1.value == 0) {
 			/* zero length call */
 			ret = X86_BR_ZERO_CALL;
 			break;
@@ -1279,7 +1277,9 @@ static int branch_type(unsigned long from, unsigned long to, int abort)
 		ret = X86_BR_JMP;
 		break;
 	case 0xff: /* call near absolute, call far absolute ind */
-		insn_get_modrm(&insn);
+		if (insn_get_modrm(&insn))
+			return X86_BR_ABORT;
+
 		ext = (insn.modrm.bytes[0] >> 3) & 0x7;
 		switch (ext) {
 		case 2: /* near ind call */

arch/x86/include/asm/alternative.h

@@ -65,7 +65,6 @@ struct alt_instr {
 	u16 cpuid;		/* cpuid bit set for replacement */
 	u8  instrlen;		/* length of original instruction */
 	u8  replacementlen;	/* length of new instruction */
-	u8  padlen;		/* length of build-time padding */
 } __packed;
 
 /*
@@ -104,7 +103,6 @@ static inline int alternatives_text_reserved(void *start, void *end)
 
 #define alt_end_marker		"663"
 #define alt_slen		"662b-661b"
-#define alt_pad_len		alt_end_marker"b-662b"
 #define alt_total_slen		alt_end_marker"b-661b"
 #define alt_rlen(num)		e_replacement(num)"f-"b_replacement(num)"f"
 
@@ -151,8 +149,7 @@ static inline int alternatives_text_reserved(void *start, void *end)
 	" .long " b_replacement(num)"f - .\n"		/* new instruction */ \
 	" .word " __stringify(feature) "\n"		/* feature bit     */ \
 	" .byte " alt_total_slen "\n"			/* source len      */ \
-	" .byte " alt_rlen(num) "\n"			/* replacement len */ \
-	" .byte " alt_pad_len "\n"			/* pad len */
+	" .byte " alt_rlen(num) "\n"			/* replacement len */
 
 #define ALTINSTR_REPLACEMENT(newinstr, num)		/* replacement */	\
 	"# ALT: replacement " #num "\n"						\
@@ -224,9 +221,6 @@ static inline int alternatives_text_reserved(void *start, void *end)
  * Peculiarities:
  * No memory clobber here.
  * Argument numbers start with 1.
- * Best is to use constraints that are fixed size (like (%1) ... "r")
- * If you use variable sized constraints like "m" or "g" in the
- * replacement make sure to pad to the worst case length.
  * Leaving an unused argument 0 to keep API compatibility.
  */
 #define alternative_input(oldinstr, newinstr, feature, input...)	\
@@ -315,13 +309,12 @@ static inline int alternatives_text_reserved(void *start, void *end)
  * enough information for the alternatives patching code to patch an
  * instruction. See apply_alternatives().
  */
-.macro altinstruction_entry orig alt feature orig_len alt_len pad_len
+.macro altinstruction_entry orig alt feature orig_len alt_len
 	.long \orig - .
 	.long \alt - .
 	.word \feature
 	.byte \orig_len
 	.byte \alt_len
-	.byte \pad_len
 .endm
 
 /*
@@ -338,7 +331,7 @@ static inline int alternatives_text_reserved(void *start, void *end)
 142:
 
 	.pushsection .altinstructions,"a"
-	altinstruction_entry 140b,143f,\feature,142b-140b,144f-143f,142b-141b
+	altinstruction_entry 140b,143f,\feature,142b-140b,144f-143f
 	.popsection
 
 	.pushsection .altinstr_replacement,"ax"
@@ -375,8 +368,8 @@ static inline int alternatives_text_reserved(void *start, void *end)
 142:
 
 	.pushsection .altinstructions,"a"
-	altinstruction_entry 140b,143f,\feature1,142b-140b,144f-143f,142b-141b
-	altinstruction_entry 140b,144f,\feature2,142b-140b,145f-144f,142b-141b
+	altinstruction_entry 140b,143f,\feature1,142b-140b,144f-143f
+	altinstruction_entry 140b,144f,\feature2,142b-140b,145f-144f
 	.popsection
 
 	.pushsection .altinstr_replacement,"ax"

arch/x86/include/asm/asm-prototypes.h

@@ -19,18 +19,19 @@ extern void cmpxchg8b_emu(void);
 
 #ifdef CONFIG_RETPOLINE
 
-#define DECL_INDIRECT_THUNK(reg) \
+#undef GEN
+#define GEN(reg) \
 	extern asmlinkage void __x86_indirect_thunk_ ## reg (void);
-
-#define DECL_RETPOLINE(reg) \
-	extern asmlinkage void __x86_retpoline_ ## reg (void);
+#include <asm/GEN-for-each-reg.h>
 
 #undef GEN
-#define GEN(reg) DECL_INDIRECT_THUNK(reg)
+#define GEN(reg) \
+	extern asmlinkage void __x86_indirect_alt_call_ ## reg (void);
 #include <asm/GEN-for-each-reg.h>
 
 #undef GEN
-#define GEN(reg) DECL_RETPOLINE(reg)
+#define GEN(reg) \
+	extern asmlinkage void __x86_indirect_alt_jmp_ ## reg (void);
 #include <asm/GEN-for-each-reg.h>
 
 #endif /* CONFIG_RETPOLINE */

arch/x86/include/asm/cpufeatures.h

@@ -84,7 +84,7 @@
 
 /* CPU types for specific tunings: */
 #define X86_FEATURE_K8			( 3*32+ 4) /* "" Opteron, Athlon64 */
-#define X86_FEATURE_K7			( 3*32+ 5) /* "" Athlon */
+/* FREE, was #define X86_FEATURE_K7			( 3*32+ 5) "" Athlon */
 #define X86_FEATURE_P3			( 3*32+ 6) /* "" P3 */
 #define X86_FEATURE_P4			( 3*32+ 7) /* "" P4 */
 #define X86_FEATURE_CONSTANT_TSC	( 3*32+ 8) /* TSC ticks at a constant rate */

arch/x86/include/asm/inat.h

@@ -6,7 +6,7 @@
  *
  * Written by Masami Hiramatsu <[email protected]>
  */
-#include <asm/inat_types.h>
+#include <asm/inat_types.h> /* __ignore_sync_check__ */
 
 /*
  * Internal bits. Don't use bitmasks directly, because these bits are