Commit c6536676 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

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
  ...
parents e7c6e405 2c88d45e

arch/x86/Kconfig

+2 −5
Original line number Diff line number Diff line
@@ -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

+8 −0
Original line number Diff line number Diff line
@@ -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

+5 −6
Original line number Diff line number Diff line
@@ -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

+4 −91
Original line number Diff line number Diff line
@@ -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

+5 −6
Original line number Diff line number Diff line
@@ -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;