x86/cacheinfo: Delete global num_cache_leaves

Linux remembers cpu_cachinfo::num_leaves per CPU, but x86 initializes all
CPUs from the same global "num_cache_leaves".

This is erroneous on systems such as Meteor Lake, where each CPU has a
distinct num_leaves value. Delete the global "num_cache_leaves" and
initialize num_leaves on each CPU.

init_cache_level() no longer needs to set num_leaves. Also, it never had to
set num_levels as it is unnecessary in x86. Keep checking for zero cache
leaves. Such condition indicates a bug.

  [ bp: Cleanup. ]

Signed-off-by: Ricardo Neri <[email protected]>
Signed-off-by: Borislav Petkov (AMD) <[email protected]>
Cc: [email protected] # 6.3+
Link: https://lore.kernel.org/r/[email protected]

Author: ricardon

arch/x86/kernel/cpu/cacheinfo.c

@@ -178,8 +178,6 @@ struct _cpuid4_info_regs {
 	struct amd_northbridge *nb;
 };
 
-static unsigned short num_cache_leaves;
-
 /* AMD doesn't have CPUID4. Emulate it here to report the same
    information to the user.  This makes some assumptions about the machine:
    L2 not shared, no SMT etc. that is currently true on AMD CPUs.
@@ -717,20 +715,23 @@ void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c)
 
 void init_amd_cacheinfo(struct cpuinfo_x86 *c)
 {
+	struct cpu_cacheinfo *ci = get_cpu_cacheinfo(c->cpu_index);
 
 	if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
-		num_cache_leaves = find_num_cache_leaves(c);
+		ci->num_leaves = find_num_cache_leaves(c);
 	} else if (c->extended_cpuid_level >= 0x80000006) {
 		if (cpuid_edx(0x80000006) & 0xf000)
-			num_cache_leaves = 4;
+			ci->num_leaves = 4;
 		else
-			num_cache_leaves = 3;
+			ci->num_leaves = 3;
 	}
 }
 
 void init_hygon_cacheinfo(struct cpuinfo_x86 *c)
 {
-	num_cache_leaves = find_num_cache_leaves(c);
+	struct cpu_cacheinfo *ci = get_cpu_cacheinfo(c->cpu_index);
+
+	ci->num_leaves = find_num_cache_leaves(c);
 }
 
 void init_intel_cacheinfo(struct cpuinfo_x86 *c)
@@ -740,21 +741,21 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c)
 	unsigned int new_l1d = 0, new_l1i = 0; /* Cache sizes from cpuid(4) */
 	unsigned int new_l2 = 0, new_l3 = 0, i; /* Cache sizes from cpuid(4) */
 	unsigned int l2_id = 0, l3_id = 0, num_threads_sharing, index_msb;
+	struct cpu_cacheinfo *ci = get_cpu_cacheinfo(c->cpu_index);
 
 	if (c->cpuid_level > 3) {
-		static int is_initialized;
-
-		if (is_initialized == 0) {
-			/* Init num_cache_leaves from boot CPU */
-			num_cache_leaves = find_num_cache_leaves(c);
-			is_initialized++;
-		}
+		/*
+		 * There should be at least one leaf. A non-zero value means
+		 * that the number of leaves has been initialized.
+		 */
+		if (!ci->num_leaves)
+			ci->num_leaves = find_num_cache_leaves(c);
 
 		/*
 		 * Whenever possible use cpuid(4), deterministic cache
 		 * parameters cpuid leaf to find the cache details
 		 */
-		for (i = 0; i < num_cache_leaves; i++) {
+		for (i = 0; i < ci->num_leaves; i++) {
 			struct _cpuid4_info_regs this_leaf = {};
 			int retval;
 
@@ -790,14 +791,14 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c)
 	 * Don't use cpuid2 if cpuid4 is supported. For P4, we use cpuid2 for
 	 * trace cache
 	 */
-	if ((num_cache_leaves == 0 || c->x86 == 15) && c->cpuid_level > 1) {
+	if ((!ci->num_leaves || c->x86 == 15) && c->cpuid_level > 1) {
 		/* supports eax=2  call */
 		int j, n;
 		unsigned int regs[4];
 		unsigned char *dp = (unsigned char *)regs;
 		int only_trace = 0;
 
-		if (num_cache_leaves != 0 && c->x86 == 15)
+		if (ci->num_leaves && c->x86 == 15)
 			only_trace = 1;
 
 		/* Number of times to iterate */
@@ -991,14 +992,12 @@ static void ci_leaf_init(struct cacheinfo *this_leaf,
 
 int init_cache_level(unsigned int cpu)
 {
-	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+	struct cpu_cacheinfo *ci = get_cpu_cacheinfo(cpu);
 
-	if (!num_cache_leaves)
+	/* There should be at least one leaf. */
+	if (!ci->num_leaves)
 		return -ENOENT;
-	if (!this_cpu_ci)
-		return -EINVAL;
-	this_cpu_ci->num_levels = 3;
-	this_cpu_ci->num_leaves = num_cache_leaves;
+
 	return 0;
 }