[PATCH 10/32] x86/intel_rdt: Adds support to enable Code Data Prioritization

["Fenghua Yu" <fenghua.yu@intel.com>]

From: Vikas Shivappa <vikas.shivappa@linux.intel.com>

On Intel SKUs that support Code Data Prioritization(CDP), intel_rdt
operates in 2 modes - legacy cache allocation mode/default or CDP mode.

When CDP is enabled, the number of available CLOSids is halved. Hence the
enabling is done when less than half the number of CLOSids available are
used. When CDP is enabled each CLOSid maps to a
data cache mask and an instruction cache mask. The enabling itself is done
by writing to the IA32_PQOS_CFG MSR and can dynamically be enabled or
disabled.

CDP is disabled when for each (dcache_cbm,icache_cbm) pair, the
dcache_cbm = icache_cbm.

Signed-off-by: Vikas Shivappa <vikas.shivappa@linux.intel.com>
Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
---
 arch/x86/include/asm/intel_rdt.h |  7 +++++
 arch/x86/kernel/cpu/intel_rdt.c  | 66 ++++++++++++++++++++++++++--------------
 2 files changed, 51 insertions(+), 22 deletions(-)

diff --git a/arch/x86/include/asm/intel_rdt.h b/arch/x86/include/asm/intel_rdt.h
index 6e20314..f2cb91d 100644
--- a/arch/x86/include/asm/intel_rdt.h
+++ b/arch/x86/include/asm/intel_rdt.h
@@ -8,6 +8,7 @@
 #define MAX_CBM_LENGTH			32
 #define IA32_L3_CBM_BASE		0xc90
 #define CBM_FROM_INDEX(x)		(IA32_L3_CBM_BASE + x)
+#define MSR_IA32_PQOS_CFG		0xc81
 
 extern struct static_key rdt_enable_key;
 void __intel_rdt_sched_in(void *dummy);
@@ -17,6 +18,12 @@ struct clos_cbm_table {
 	unsigned int clos_refcnt;
 };
 
+struct clos_config {
+	unsigned long *closmap;
+	u32 max_closid;
+	u32 closids_used;
+};
+
 /*
  * intel_rdt_sched_in() - Writes the task's CLOSid to IA32_PQR_MSR
  *
diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
index 5fa0f9d..14b9011 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -34,10 +34,6 @@
  */
 static struct clos_cbm_table *cctable;
 /*
- * closid availability bit map.
- */
-unsigned long *closmap;
-/*
  * Minimum bits required in Cache bitmask.
  */
 static unsigned int min_bitmask_len = 1;
@@ -52,6 +48,11 @@ static cpumask_t rdt_cpumask;
 static cpumask_t tmp_cpumask;
 static DEFINE_MUTEX(rdt_group_mutex);
 struct static_key __read_mostly rdt_enable_key = STATIC_KEY_INIT_FALSE;
+static struct clos_config cconfig;
+static bool cdp_enabled;
+
+#define __DCBM_TABLE_INDEX(x)	(x << 1)
+#define __ICBM_TABLE_INDEX(x)	((x << 1) + 1)
 
 struct rdt_remote_data {
 	int msr;
@@ -147,22 +148,28 @@ static int closid_alloc(u32 *closid)
 
 	lockdep_assert_held(&rdt_group_mutex);
 
-	maxid = boot_cpu_data.x86_cache_max_closid;
-	id = find_first_zero_bit(closmap, maxid);
+	maxid = cconfig.max_closid;
+	id = find_first_zero_bit(cconfig.closmap, maxid);
 	if (id == maxid)
 		return -ENOSPC;
 
-	set_bit(id, closmap);
+	set_bit(id, cconfig.closmap);
 	closid_get(id);
 	*closid = id;
+	cconfig.closids_used++;
 
 	return 0;
 }
 
 static inline void closid_free(u32 closid)
 {
-	clear_bit(closid, closmap);
+	clear_bit(closid, cconfig.closmap);
 	cctable[closid].l3_cbm = 0;
+
+	if (WARN_ON(!cconfig.closids_used))
+		return;
+
+	cconfig.closids_used--;
 }
 
 static void closid_put(u32 closid)
@@ -199,45 +206,45 @@ static bool cbm_validate(unsigned long var)
 	return true;
 }
 
-static int clos_cbm_table_read(u32 closid, unsigned long *l3_cbm)
+static int clos_cbm_table_read(u32 index, unsigned long *l3_cbm)
 {
-	u32 maxid = boot_cpu_data.x86_cache_max_closid;
+	u32 orig_maxid = boot_cpu_data.x86_cache_max_closid;
 
 	lockdep_assert_held(&rdt_group_mutex);
 
-	if (closid >= maxid)
+	if (index >= orig_maxid)
 		return -EINVAL;
 
-	*l3_cbm = cctable[closid].l3_cbm;
+	*l3_cbm = cctable[index].l3_cbm;
 
 	return 0;
 }
 
 /*
  * clos_cbm_table_update() - Update a clos cbm table entry.
- * @closid: the closid whose cbm needs to be updated
+ * @index: index of the table entry whose cbm needs to be updated
  * @cbm: the new cbm value that has to be updated
  *
  * This assumes the cbm is validated as per the interface requirements
  * and the cache allocation requirements(through the cbm_validate).
  */
-static int clos_cbm_table_update(u32 closid, unsigned long cbm)
+static int clos_cbm_table_update(u32 index, unsigned long cbm)
 {
-	u32 maxid = boot_cpu_data.x86_cache_max_closid;
+	u32 orig_maxid = boot_cpu_data.x86_cache_max_closid;
 
 	lockdep_assert_held(&rdt_group_mutex);
 
-	if (closid >= maxid)
+	if (index >= orig_maxid)
 		return -EINVAL;
 
-	cctable[closid].l3_cbm = cbm;
+	cctable[index].l3_cbm = cbm;
 
 	return 0;
 }
 
 static bool cbm_search(unsigned long cbm, u32 *closid)
 {
-	u32 maxid = boot_cpu_data.x86_cache_max_closid;
+	u32 maxid = cconfig.max_closid;
 	u32 i;
 
 	for (i = 0; i < maxid; i++) {
@@ -281,6 +288,21 @@ static inline void msr_update_all(int msr, u64 val)
 	on_each_cpu_mask(&rdt_cpumask, msr_cpu_update, &info, 1);
 }
 
+static bool code_data_mask_equal(void)
+{
+	int i, dindex, iindex;
+
+	for (i = 0; i < cconfig.max_closid; i++) {
+		dindex = __DCBM_TABLE_INDEX(i);
+		iindex = __ICBM_TABLE_INDEX(i);
+		if (cctable[dindex].clos_refcnt &&
+		     (cctable[dindex].l3_cbm != cctable[iindex].l3_cbm))
+			return false;
+	}
+
+	return true;
+}
+
 static inline bool rdt_cpumask_update(int cpu)
 {
 	cpumask_and(&tmp_cpumask, &rdt_cpumask, topology_core_cpumask(cpu));
@@ -298,7 +320,7 @@ static inline bool rdt_cpumask_update(int cpu)
  */
 static void cbm_update_msrs(void *dummy)
 {
-	int maxid = boot_cpu_data.x86_cache_max_closid;
+	int maxid = cconfig.max_closid;
 	struct rdt_remote_data info;
 	unsigned int i;
 
@@ -306,7 +328,7 @@ static void cbm_update_msrs(void *dummy)
 		if (cctable[i].clos_refcnt) {
 			info.msr = CBM_FROM_INDEX(i);
 			info.val = cctable[i].l3_cbm;
-			msr_cpu_update(&info);
+			msr_cpu_update((void *) &info);
 		}
 	}
 }
@@ -381,8 +403,8 @@ static int __init intel_rdt_late_init(void)
 	}
 
 	size = BITS_TO_LONGS(maxid) * sizeof(long);
-	closmap = kzalloc(size, GFP_KERNEL);
-	if (!closmap) {
+	cconfig.closmap = kzalloc(size, GFP_KERNEL);
+	if (!cconfig.closmap) {
 		kfree(cctable);
 		err = -ENOMEM;
 		goto out_err;
-- 
2.5.0