Merge tag 'x86_urgent_for_v6.0' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fixes from Borislav Petkov:

 - Add the respective UP last level cache mask accessors in order not to
   cause segfaults when lscpu accesses their representation in sysfs

 - Fix for a race in the alternatives batch patching machinery when
   kprobes are set

* tag 'x86_urgent_for_v6.0' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/cacheinfo: Add a cpu_llc_shared_mask() UP variant
  x86/alternative: Fix race in try_get_desc()

Author: torvalds

arch/x86/include/asm/smp.h

@@ -21,16 +21,6 @@ DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id);
 DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_l2c_id);
 DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number);
 
-static inline struct cpumask *cpu_llc_shared_mask(int cpu)
-{
-	return per_cpu(cpu_llc_shared_map, cpu);
-}
-
-static inline struct cpumask *cpu_l2c_shared_mask(int cpu)
-{
-	return per_cpu(cpu_l2c_shared_map, cpu);
-}
-
 DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid);
 DECLARE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_acpiid);
 DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_bios_cpu_apicid);
@@ -172,13 +162,28 @@ extern int safe_smp_processor_id(void);
 # define safe_smp_processor_id()	smp_processor_id()
 #endif
 
+static inline struct cpumask *cpu_llc_shared_mask(int cpu)
+{
+	return per_cpu(cpu_llc_shared_map, cpu);
+}
+
+static inline struct cpumask *cpu_l2c_shared_mask(int cpu)
+{
+	return per_cpu(cpu_l2c_shared_map, cpu);
+}
+
 #else /* !CONFIG_SMP */
 #define wbinvd_on_cpu(cpu)     wbinvd()
 static inline int wbinvd_on_all_cpus(void)
 {
 	wbinvd();
 	return 0;
 }
+
+static inline struct cpumask *cpu_llc_shared_mask(int cpu)
+{
+	return (struct cpumask *)cpumask_of(0);
+}
 #endif /* CONFIG_SMP */
 
 extern unsigned disabled_cpus;

arch/x86/kernel/alternative.c

@@ -1319,22 +1319,23 @@ struct bp_patching_desc {
 	atomic_t refs;
 };
 
-static struct bp_patching_desc *bp_desc;
+static struct bp_patching_desc bp_desc;
 
 static __always_inline
-struct bp_patching_desc *try_get_desc(struct bp_patching_desc **descp)
+struct bp_patching_desc *try_get_desc(void)
 {
-	/* rcu_dereference */
-	struct bp_patching_desc *desc = __READ_ONCE(*descp);
+	struct bp_patching_desc *desc = &bp_desc;
 
-	if (!desc || !arch_atomic_inc_not_zero(&desc->refs))
+	if (!arch_atomic_inc_not_zero(&desc->refs))
 		return NULL;
 
 	return desc;
 }
 
-static __always_inline void put_desc(struct bp_patching_desc *desc)
+static __always_inline void put_desc(void)
 {
+	struct bp_patching_desc *desc = &bp_desc;
+
 	smp_mb__before_atomic();
 	arch_atomic_dec(&desc->refs);
 }
@@ -1367,15 +1368,15 @@ noinstr int poke_int3_handler(struct pt_regs *regs)
 
 	/*
 	 * Having observed our INT3 instruction, we now must observe
-	 * bp_desc:
+	 * bp_desc with non-zero refcount:
 	 *
-	 *	bp_desc = desc			INT3
+	 *	bp_desc.refs = 1		INT3
 	 *	WMB				RMB
-	 *	write INT3			if (desc)
+	 *	write INT3			if (bp_desc.refs != 0)
 	 */
 	smp_rmb();
 
-	desc = try_get_desc(&bp_desc);
+	desc = try_get_desc();
 	if (!desc)
 		return 0;
 
@@ -1429,7 +1430,7 @@ noinstr int poke_int3_handler(struct pt_regs *regs)
 	ret = 1;
 
 out_put:
-	put_desc(desc);
+	put_desc();
 	return ret;
 }
 
@@ -1460,18 +1461,20 @@ static int tp_vec_nr;
  */
 static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries)
 {
-	struct bp_patching_desc desc = {
-		.vec = tp,
-		.nr_entries = nr_entries,
-		.refs = ATOMIC_INIT(1),
-	};
 	unsigned char int3 = INT3_INSN_OPCODE;
 	unsigned int i;
 	int do_sync;
 
 	lockdep_assert_held(&text_mutex);
 
-	smp_store_release(&bp_desc, &desc); /* rcu_assign_pointer */
+	bp_desc.vec = tp;
+	bp_desc.nr_entries = nr_entries;
+
+	/*
+	 * Corresponds to the implicit memory barrier in try_get_desc() to
+	 * ensure reading a non-zero refcount provides up to date bp_desc data.
+	 */
+	atomic_set_release(&bp_desc.refs, 1);
 
 	/*
 	 * Corresponding read barrier in int3 notifier for making sure the
@@ -1559,12 +1562,10 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries
 		text_poke_sync();
 
 	/*
-	 * Remove and synchronize_rcu(), except we have a very primitive
-	 * refcount based completion.
+	 * Remove and wait for refs to be zero.
 	 */
-	WRITE_ONCE(bp_desc, NULL); /* RCU_INIT_POINTER */
-	if (!atomic_dec_and_test(&desc.refs))
-		atomic_cond_read_acquire(&desc.refs, !VAL);
+	if (!atomic_dec_and_test(&bp_desc.refs))
+		atomic_cond_read_acquire(&bp_desc.refs, !VAL);
 }
 
 static void text_poke_loc_init(struct text_poke_loc *tp, void *addr,