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
  ...

5 files changed, 9 insertions, 18 deletions

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 347a956f71ca..2d11384dc9ab 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -628,11 +628,6 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 
 	early_init_amd_mc(c);
 
-#ifdef CONFIG_X86_32
-	if (c->x86 == 6)
-		set_cpu_cap(c, X86_FEATURE_K7);
-#endif
-
 	if (c->x86 >= 0xf)
 		set_cpu_cap(c, X86_FEATURE_K8);
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 99e1656b326e..6bdb69a9a7dc 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -161,7 +161,6 @@ DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
 
 	[GDT_ENTRY_ESPFIX_SS]		= GDT_ENTRY_INIT(0xc092, 0, 0xfffff),
 	[GDT_ENTRY_PERCPU]		= GDT_ENTRY_INIT(0xc092, 0, 0xfffff),
-	GDT_STACK_CANARY_INIT
 #endif
 } };
 EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
@@ -599,7 +598,6 @@ void load_percpu_segment(int cpu)
 	__loadsegment_simple(gs, 0);
 	wrmsrl(MSR_GS_BASE, cpu_kernelmode_gs_base(cpu));
 #endif
-	load_stack_canary_segment();
 }
 
 #ifdef CONFIG_X86_32
@@ -1798,7 +1796,8 @@ DEFINE_PER_CPU(unsigned long, cpu_current_top_of_stack) =
 EXPORT_PER_CPU_SYMBOL(cpu_current_top_of_stack);
 
 #ifdef CONFIG_STACKPROTECTOR
-DEFINE_PER_CPU_ALIGNED(struct stack_canary, stack_canary);
+DEFINE_PER_CPU(unsigned long, __stack_chk_guard);
+EXPORT_PER_CPU_SYMBOL(__stack_chk_guard);
 #endif
 
 #endif	/* CONFIG_X86_64 */
diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c
index ae59115d18f9..0bd6c74e3ba1 100644
--- a/arch/x86/kernel/cpu/hygon.c
+++ b/arch/x86/kernel/cpu/hygon.c
@@ -215,12 +215,12 @@ static void bsp_init_hygon(struct cpuinfo_x86 *c)
 		u32 ecx;
 
 		ecx = cpuid_ecx(0x8000001e);
-		nodes_per_socket = ((ecx >> 8) & 7) + 1;
+		__max_die_per_package = nodes_per_socket = ((ecx >> 8) & 7) + 1;
 	} else if (boot_cpu_has(X86_FEATURE_NODEID_MSR)) {
 		u64 value;
 
 		rdmsrl(MSR_FAM10H_NODE_ID, value);
-		nodes_per_socket = ((value >> 3) & 7) + 1;
+		__max_die_per_package = nodes_per_socket = ((value >> 3) & 7) + 1;
 	}
 
 	if (!boot_cpu_has(X86_FEATURE_AMD_SSBD) &&
diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c
index e309476743b7..acfd5d9f93c6 100644
--- a/arch/x86/kernel/cpu/mce/intel.c
+++ b/arch/x86/kernel/cpu/mce/intel.c
@@ -486,6 +486,7 @@ static void intel_ppin_init(struct cpuinfo_x86 *c)
 	case INTEL_FAM6_BROADWELL_X:
 	case INTEL_FAM6_SKYLAKE_X:
 	case INTEL_FAM6_ICELAKE_X:
+	case INTEL_FAM6_SAPPHIRERAPIDS_X:
 	case INTEL_FAM6_XEON_PHI_KNL:
 	case INTEL_FAM6_XEON_PHI_KNM:
 
diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c
index 55ffa84d30d6..17e631443116 100644
--- a/arch/x86/kernel/cpu/mce/severity.c
+++ b/arch/x86/kernel/cpu/mce/severity.c
@@ -218,15 +218,15 @@ static struct severity {
 static bool is_copy_from_user(struct pt_regs *regs)
 {
 	u8 insn_buf[MAX_INSN_SIZE];
-	struct insn insn;
 	unsigned long addr;
+	struct insn insn;
+	int ret;
 
 	if (copy_from_kernel_nofault(insn_buf, (void *)regs->ip, MAX_INSN_SIZE))
 		return false;
 
-	kernel_insn_init(&insn, insn_buf, MAX_INSN_SIZE);
-	insn_get_opcode(&insn);
-	if (!insn.opcode.got)
+	ret = insn_decode_kernel(&insn, insn_buf);
+	if (ret < 0)
 		return false;
 
 	switch (insn.opcode.value) {
@@ -234,10 +234,6 @@ static bool is_copy_from_user(struct pt_regs *regs)
 	case 0x8A: case 0x8B:
 	/* MOVZ mem,reg */
 	case 0xB60F: case 0xB70F:
-		insn_get_modrm(&insn);
-		insn_get_sib(&insn);
-		if (!insn.modrm.got || !insn.sib.got)
-			return false;
 		addr = (unsigned long)insn_get_addr_ref(&insn, regs);
 		break;
 	/* REP MOVS */