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
  ...

1 files changed, 46 insertions, 44 deletions

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 1e2050c4f94a..7ffb0cf3f997 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -458,29 +458,52 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 	return false;
 }
 
+static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
+{
+	if (c->phys_proc_id == o->phys_proc_id &&
+	    c->cpu_die_id == o->cpu_die_id)
+		return true;
+	return false;
+}
+
 /*
- * Define snc_cpu[] for SNC (Sub-NUMA Cluster) CPUs.
+ * Unlike the other levels, we do not enforce keeping a
+ * multicore group inside a NUMA node.  If this happens, we will
+ * discard the MC level of the topology later.
+ */
+static bool match_pkg(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
+{
+	if (c->phys_proc_id == o->phys_proc_id)
+		return true;
+	return false;
+}
+
+/*
+ * Define intel_cod_cpu[] for Intel COD (Cluster-on-Die) CPUs.
  *
- * These are Intel CPUs that enumerate an LLC that is shared by
- * multiple NUMA nodes. The LLC on these systems is shared for
- * off-package data access but private to the NUMA node (half
- * of the package) for on-package access.
+ * Any Intel CPU that has multiple nodes per package and does not
+ * match intel_cod_cpu[] has the SNC (Sub-NUMA Cluster) topology.
  *
- * CPUID (the source of the information about the LLC) can only
- * enumerate the cache as being shared *or* unshared, but not
- * this particular configuration. The CPU in this case enumerates
- * the cache to be shared across the entire package (spanning both
- * NUMA nodes).
+ * When in SNC mode, these CPUs enumerate an LLC that is shared
+ * by multiple NUMA nodes. The LLC is shared for off-package data
+ * access but private to the NUMA node (half of the package) for
+ * on-package access. CPUID (the source of the information about
+ * the LLC) can only enumerate the cache as shared or unshared,
+ * but not this particular configuration.
  */
 
-static const struct x86_cpu_id snc_cpu[] = {
-	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X, NULL),
+static const struct x86_cpu_id intel_cod_cpu[] = {
+	X86_MATCH_INTEL_FAM6_MODEL(HASWELL_X, 0),	/* COD */
+	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_X, 0),	/* COD */
+	X86_MATCH_INTEL_FAM6_MODEL(ANY, 1),		/* SNC */
 	{}
 };
 
 static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 {
+	const struct x86_cpu_id *id = x86_match_cpu(intel_cod_cpu);
 	int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
+	bool intel_snc = id && id->driver_data;
 
 	/* Do not match if we do not have a valid APICID for cpu: */
 	if (per_cpu(cpu_llc_id, cpu1) == BAD_APICID)
@@ -495,32 +518,12 @@ static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 	 * means 'c' does not share the LLC of 'o'. This will be
 	 * reflected to userspace.
 	 */
-	if (!topology_same_node(c, o) && x86_match_cpu(snc_cpu))
+	if (match_pkg(c, o) && !topology_same_node(c, o) && intel_snc)
 		return false;
 
 	return topology_sane(c, o, "llc");
 }
 
-/*
- * Unlike the other levels, we do not enforce keeping a
- * multicore group inside a NUMA node.  If this happens, we will
- * discard the MC level of the topology later.
- */
-static bool match_pkg(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
-{
-	if (c->phys_proc_id == o->phys_proc_id)
-		return true;
-	return false;
-}
-
-static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
-{
-	if ((c->phys_proc_id == o->phys_proc_id) &&
-		(c->cpu_die_id == o->cpu_die_id))
-		return true;
-	return false;
-}
-
 
 #if defined(CONFIG_SCHED_SMT) || defined(CONFIG_SCHED_MC)
 static inline int x86_sched_itmt_flags(void)
@@ -592,14 +595,23 @@ void set_cpu_sibling_map(int cpu)
 	for_each_cpu(i, cpu_sibling_setup_mask) {
 		o = &cpu_data(i);
 
+		if (match_pkg(c, o) && !topology_same_node(c, o))
+			x86_has_numa_in_package = true;
+
 		if ((i == cpu) || (has_smt && match_smt(c, o)))
 			link_mask(topology_sibling_cpumask, cpu, i);
 
 		if ((i == cpu) || (has_mp && match_llc(c, o)))
 			link_mask(cpu_llc_shared_mask, cpu, i);
 
+		if ((i == cpu) || (has_mp && match_die(c, o)))
+			link_mask(topology_die_cpumask, cpu, i);
 	}
 
+	threads = cpumask_weight(topology_sibling_cpumask(cpu));
+	if (threads > __max_smt_threads)
+		__max_smt_threads = threads;
+
 	/*
 	 * This needs a separate iteration over the cpus because we rely on all
 	 * topology_sibling_cpumask links to be set-up.
@@ -613,8 +625,7 @@ void set_cpu_sibling_map(int cpu)
 			/*
 			 *  Does this new cpu bringup a new core?
 			 */
-			if (cpumask_weight(
-			    topology_sibling_cpumask(cpu)) == 1) {
+			if (threads == 1) {
 				/*
 				 * for each core in package, increment
 				 * the booted_cores for this new cpu
@@ -631,16 +642,7 @@ void set_cpu_sibling_map(int cpu)
 			} else if (i != cpu && !c->booted_cores)
 				c->booted_cores = cpu_data(i).booted_cores;
 		}
-		if (match_pkg(c, o) && !topology_same_node(c, o))
-			x86_has_numa_in_package = true;
-
-		if ((i == cpu) || (has_mp && match_die(c, o)))
-			link_mask(topology_die_cpumask, cpu, i);
 	}
-
-	threads = cpumask_weight(topology_sibling_cpumask(cpu));
-	if (threads > __max_smt_threads)
-		__max_smt_threads = threads;
 }
 
 /* maps the cpu to the sched domain representing multi-core */