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
  ...

3 files changed, 102 insertions, 27 deletions

diff --git a/tools/arch/x86/include/asm/inat.h b/tools/arch/x86/include/asm/inat.h
index 877827b7c2c3..a61051400311 100644
--- a/tools/arch/x86/include/asm/inat.h
+++ b/tools/arch/x86/include/asm/inat.h
@@ -6,7 +6,7 @@
  *
  * Written by Masami Hiramatsu <mhiramat@redhat.com>
  */
-#include "inat_types.h"
+#include "inat_types.h" /* __ignore_sync_check__ */
 
 /*
  * Internal bits. Don't use bitmasks directly, because these bits are
diff --git a/tools/arch/x86/include/asm/insn.h b/tools/arch/x86/include/asm/insn.h
index cc777c185212..dc632b41f135 100644
--- a/tools/arch/x86/include/asm/insn.h
+++ b/tools/arch/x86/include/asm/insn.h
@@ -9,7 +9,7 @@
 
 #include <asm/byteorder.h>
 /* insn_attr_t is defined in inat.h */
-#include "inat.h"
+#include "inat.h" /* __ignore_sync_check__ */
 
 #if defined(__BYTE_ORDER) ? __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN)
 
@@ -132,13 +132,25 @@ struct insn {
 #define X86_VEX_M_MAX	0x1f			/* VEX3.M Maximum value */
 
 extern void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64);
-extern void insn_get_prefixes(struct insn *insn);
-extern void insn_get_opcode(struct insn *insn);
-extern void insn_get_modrm(struct insn *insn);
-extern void insn_get_sib(struct insn *insn);
-extern void insn_get_displacement(struct insn *insn);
-extern void insn_get_immediate(struct insn *insn);
-extern void insn_get_length(struct insn *insn);
+extern int insn_get_prefixes(struct insn *insn);
+extern int insn_get_opcode(struct insn *insn);
+extern int insn_get_modrm(struct insn *insn);
+extern int insn_get_sib(struct insn *insn);
+extern int insn_get_displacement(struct insn *insn);
+extern int insn_get_immediate(struct insn *insn);
+extern int insn_get_length(struct insn *insn);
+
+enum insn_mode {
+	INSN_MODE_32,
+	INSN_MODE_64,
+	/* Mode is determined by the current kernel build. */
+	INSN_MODE_KERN,
+	INSN_NUM_MODES,
+};
+
+extern int insn_decode(struct insn *insn, const void *kaddr, int buf_len, enum insn_mode m);
+
+#define insn_decode_kernel(_insn, _ptr) insn_decode((_insn), (_ptr), MAX_INSN_SIZE, INSN_MODE_KERN)
 
 /* Attribute will be determined after getting ModRM (for opcode groups) */
 static inline void insn_get_attribute(struct insn *insn)
@@ -149,17 +161,6 @@ static inline void insn_get_attribute(struct insn *insn)
 /* Instruction uses RIP-relative addressing */
 extern int insn_rip_relative(struct insn *insn);
 
-/* Init insn for kernel text */
-static inline void kernel_insn_init(struct insn *insn,
-				    const void *kaddr, int buf_len)
-{
-#ifdef CONFIG_X86_64
-	insn_init(insn, kaddr, buf_len, 1);
-#else /* CONFIG_X86_32 */
-	insn_init(insn, kaddr, buf_len, 0);
-#endif
-}
-
 static inline int insn_is_avx(struct insn *insn)
 {
 	if (!insn->prefixes.got)
@@ -179,13 +180,6 @@ static inline int insn_has_emulate_prefix(struct insn *insn)
 	return !!insn->emulate_prefix_size;
 }
 
-/* Ensure this instruction is decoded completely */
-static inline int insn_complete(struct insn *insn)
-{
-	return insn->opcode.got && insn->modrm.got && insn->sib.got &&
-		insn->displacement.got && insn->immediate.got;
-}
-
 static inline insn_byte_t insn_vex_m_bits(struct insn *insn)
 {
 	if (insn->vex_prefix.nbytes == 2)	/* 2 bytes VEX */
diff --git a/tools/arch/x86/include/asm/nops.h b/tools/arch/x86/include/asm/nops.h
new file mode 100644
index 000000000000..c1e5e818ba16
--- /dev/null
+++ b/tools/arch/x86/include/asm/nops.h
@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_NOPS_H
+#define _ASM_X86_NOPS_H
+
+/*
+ * Define nops for use with alternative() and for tracing.
+ */
+
+#ifndef CONFIG_64BIT
+
+/*
+ * Generic 32bit nops from GAS:
+ *
+ * 1: nop
+ * 2: movl %esi,%esi
+ * 3: leal 0x0(%esi),%esi
+ * 4: leal 0x0(%esi,%eiz,1),%esi
+ * 5: leal %ds:0x0(%esi,%eiz,1),%esi
+ * 6: leal 0x0(%esi),%esi
+ * 7: leal 0x0(%esi,%eiz,1),%esi
+ * 8: leal %ds:0x0(%esi,%eiz,1),%esi
+ *
+ * Except 5 and 8, which are DS prefixed 4 and 7 resp, where GAS would emit 2
+ * nop instructions.
+ */
+#define BYTES_NOP1	0x90
+#define BYTES_NOP2	0x89,0xf6
+#define BYTES_NOP3	0x8d,0x76,0x00
+#define BYTES_NOP4	0x8d,0x74,0x26,0x00
+#define BYTES_NOP5	0x3e,BYTES_NOP4
+#define BYTES_NOP6	0x8d,0xb6,0x00,0x00,0x00,0x00
+#define BYTES_NOP7	0x8d,0xb4,0x26,0x00,0x00,0x00,0x00
+#define BYTES_NOP8	0x3e,BYTES_NOP7
+
+#else
+
+/*
+ * Generic 64bit nops from GAS:
+ *
+ * 1: nop
+ * 2: osp nop
+ * 3: nopl (%eax)
+ * 4: nopl 0x00(%eax)
+ * 5: nopl 0x00(%eax,%eax,1)
+ * 6: osp nopl 0x00(%eax,%eax,1)
+ * 7: nopl 0x00000000(%eax)
+ * 8: nopl 0x00000000(%eax,%eax,1)
+ */
+#define BYTES_NOP1	0x90
+#define BYTES_NOP2	0x66,BYTES_NOP1
+#define BYTES_NOP3	0x0f,0x1f,0x00
+#define BYTES_NOP4	0x0f,0x1f,0x40,0x00
+#define BYTES_NOP5	0x0f,0x1f,0x44,0x00,0x00
+#define BYTES_NOP6	0x66,BYTES_NOP5
+#define BYTES_NOP7	0x0f,0x1f,0x80,0x00,0x00,0x00,0x00
+#define BYTES_NOP8	0x0f,0x1f,0x84,0x00,0x00,0x00,0x00,0x00
+
+#endif /* CONFIG_64BIT */
+
+#ifdef __ASSEMBLY__
+#define _ASM_MK_NOP(x) .byte x
+#else
+#define _ASM_MK_NOP(x) ".byte " __stringify(x) "\n"
+#endif
+
+#define ASM_NOP1 _ASM_MK_NOP(BYTES_NOP1)
+#define ASM_NOP2 _ASM_MK_NOP(BYTES_NOP2)
+#define ASM_NOP3 _ASM_MK_NOP(BYTES_NOP3)
+#define ASM_NOP4 _ASM_MK_NOP(BYTES_NOP4)
+#define ASM_NOP5 _ASM_MK_NOP(BYTES_NOP5)
+#define ASM_NOP6 _ASM_MK_NOP(BYTES_NOP6)
+#define ASM_NOP7 _ASM_MK_NOP(BYTES_NOP7)
+#define ASM_NOP8 _ASM_MK_NOP(BYTES_NOP8)
+
+#define ASM_NOP_MAX 8
+
+#ifndef __ASSEMBLY__
+extern const unsigned char * const x86_nops[];
+#endif
+
+#endif /* _ASM_X86_NOPS_H */