[PATCH 9/9] x86/intel_rdt: Intel haswell Cache Allocation enumeration

[Vikas Shivappa <vikas.shivappa@linux.intel.com>]

This patch is specific to Intel haswell (hsw) server SKUs. Cache
Allocation on hsw server needs to be enumerated separately as HSW does
not have support for CPUID enumeration for Cache Allocation. This patch
does a probe by writing a CLOSid (Class of service id) into high 32 bits
of IA32_PQR_MSR and see if the bits stick. The probe is only done after
confirming that the CPU is HSW server. Other hardcoded values are:

 - L3 cache bit mask must be at least two bits.
 - Maximum CLOSids supported is always 4.
 - Maximum bits support in cache bit mask is always 20.

Signed-off-by: Vikas Shivappa <vikas.shivappa@linux.intel.com>
---
 arch/x86/kernel/cpu/intel_rdt.c | 59 +++++++++++++++++++++++++++++++++++++++--
 1 file changed, 57 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
index f151200..fda31c2 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -38,6 +38,11 @@ struct intel_rdt rdt_root_group;
 struct static_key __read_mostly rdt_enable_key = STATIC_KEY_INIT_FALSE;
 
 /*
+ * Minimum bits required in Cache bitmask.
+ */
+static unsigned int min_bitmask_len = 1;
+
+/*
  * Mask of CPUs for writing CBM values. We only need one CPU per-socket.
  */
 static cpumask_t rdt_cpumask;
@@ -50,6 +55,56 @@ static cpumask_t tmp_cpumask;
 #define rdt_for_each_child(pos_css, parent_ir)		\
 	css_for_each_child((pos_css), &(parent_ir)->css)
 
+/*
+ * cache_alloc_hsw_probe() - Have to probe for Intel haswell server CPUs
+ * as it does not have CPUID enumeration support for Cache allocation.
+ *
+ * Probes by writing to the high 32 bits(CLOSid) of the IA32_PQR_MSR and
+ * testing if the bits stick. Max CLOSids is always 4 and max cbm length
+ * is always 20 on hsw server parts. The minimum cache bitmask length
+ * allowed for HSW server is always 2 bits. Hardcode all of them.
+ */
+static inline bool cache_alloc_hsw_probe(void)
+{
+	u32 l, h_old, h_new, h_tmp;
+
+	if (rdmsr_safe(MSR_IA32_PQR_ASSOC, &l, &h_old))
+		return false;
+
+	/*
+	 * Default value is always 0 if feature is present.
+	 */
+	h_tmp = h_old ^ 0x1U;
+	if (wrmsr_safe(MSR_IA32_PQR_ASSOC, l, h_tmp) ||
+	    rdmsr_safe(MSR_IA32_PQR_ASSOC, &l, &h_new))
+		return false;
+
+	if (h_tmp != h_new)
+		return false;
+
+	wrmsr_safe(MSR_IA32_PQR_ASSOC, l, h_old);
+
+	boot_cpu_data.x86_cache_max_closid = 4;
+	boot_cpu_data.x86_cache_max_cbm_len = 20;
+	min_bitmask_len = 2;
+
+	return true;
+}
+
+static inline bool cache_alloc_supported(struct cpuinfo_x86 *c)
+{
+	if (cpu_has(c, X86_FEATURE_CAT_L3))
+		return true;
+
+	/*
+	 * Probe for Haswell server CPUs.
+	 */
+	if (c->x86 == 0x6 && c->x86_model == 0x3f)
+		return cache_alloc_hsw_probe();
+
+	return false;
+}
+
 static inline void closid_get(u32 closid)
 {
 	struct clos_cbm_table *cct = &cctable[closid];
@@ -160,7 +215,7 @@ static inline bool cbm_is_contiguous(unsigned long var)
 	unsigned long maxcbm = MAX_CBM_LENGTH;
 	unsigned long first_bit, zero_bit;
 
-	if (!var)
+	if (bitmap_weight(&var, maxcbm) < min_bitmask_len)
 		return false;
 
 	first_bit = find_first_bit(&var, maxcbm);
@@ -406,7 +461,7 @@ static int __init intel_rdt_late_init(void)
 	u32 maxid, max_cbm_len;
 	int err = 0, size, i;
 
-	if (!cpu_has(c, X86_FEATURE_CAT_L3)) {
+	if (!cache_alloc_supported(c)) {
 		rdt_root_group.css.ss->disabled = 1;
 		return -ENODEV;
 	}
-- 
1.9.1