[PATCH v2 12/33] x86/intel_rdt: Intel haswell Cache Allocation enumeration

[Fenghua Yu]

From: Vikas Shivappa <vikas.shivappa@xxxxxxxxxxxxxxx>

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@xxxxxxxxxxxxxxx>
Signed-off-by: Fenghua Yu <fenghua.yu@xxxxxxxxx>
Reviewed-by: Tony Luck <tony.luck@xxxxxxxxx>
---
 arch/x86/kernel/cpu/intel_rdt.c | 43 ++++++++++++++++++++++++++++++++++++++---
 1 file changed, 40 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
index 4537658..fb5a9a9 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -35,6 +35,10 @@ static struct clos_cbm_table *cctable;
  */
 unsigned long *closmap;
 /*
+ * Minimum bits required in Cache bitmask.
+ */
+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;
@@ -51,6 +55,42 @@ struct rdt_remote_data {
 	u64 val;
 };
 
+/*
+ * 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;
+}
+
 void __intel_rdt_sched_in(void *dummy)
 {
 	struct intel_pqr_state *state = this_cpu_ptr(&pqr_state);
@@ -225,9 +265,6 @@ static int __init intel_rdt_late_init(void)
 	u32 maxid;
 	int err = 0, size, i;
 
-	if (!cpu_has(c, X86_FEATURE_CAT_L3))
-		return -ENODEV;
-
 	maxid = c->x86_cache_max_closid;
 
 	size = maxid * sizeof(struct clos_cbm_table);
-- 
2.5.0