[PATCH v4 1/4] x86: Support enable CDP by boot parameter and add get CDP status

[He Chen <he.chen@linux.intel.com>]

Add boot parameter `psr=cdp` to enable CDP at boot time.
Intel Code/Data Prioritization(CDP) feature is based on CAT. Note that
cos_max would be half when CDP is on. struct psr_cat_cbm is extended to
support CDP operation. Extend psr_get_cat_l3_info sysctl to get CDP
status.

Signed-off-by: He Chen <he.chen@linux.intel.com>
---
 docs/misc/xen-command-line.markdown | 11 ++++-
 xen/arch/x86/psr.c                  | 84 ++++++++++++++++++++++++++++++-------
 xen/arch/x86/sysctl.c               |  5 ++-
 xen/include/asm-x86/msr-index.h     |  3 ++
 xen/include/asm-x86/psr.h           | 11 ++++-
 xen/include/public/sysctl.h         |  4 +-
 6 files changed, 98 insertions(+), 20 deletions(-)

diff --git a/docs/misc/xen-command-line.markdown b/docs/misc/xen-command-line.markdown
index a2e427c..d92e323 100644
--- a/docs/misc/xen-command-line.markdown
+++ b/docs/misc/xen-command-line.markdown
@@ -1165,9 +1165,9 @@ This option can be specified more than once (up to 8 times at present).
 > `= <integer>`
 
 ### psr (Intel)
-> `= List of ( cmt:<boolean> | rmid_max:<integer> | cat:<boolean> | cos_max:<integer> )`
+> `= List of ( cmt:<boolean> | rmid_max:<integer> | cat:<boolean> | cos_max:<integer> | cdp:<boolean> )`
 
-> Default: `psr=cmt:0,rmid_max:255,cat:0,cos_max:255`
+> Default: `psr=cmt:0,rmid_max:255,cat:0,cos_max:255,cdp:0`
 
 Platform Shared Resource(PSR) Services.  Intel Haswell and later server
 platforms offer information about the sharing of resources.
@@ -1197,6 +1197,13 @@ The following resources are available:
   the cache allocation.
   * `cat` instructs Xen to enable/disable Cache Allocation Technology.
   * `cos_max` indicates the max value for COS ID.
+* Code and Data Prioritization Technology (Broadwell and later). Information
+  regarding the code cache and the data cache allocation. CDP is based on CAT.
+  * `cdp` instructs Xen to enable/disable Code and Data Prioritization. Note
+    that `cos_max` of CDP is a little different from `cos_max` of CAT. With
+    CDP, one COS will corespond two CBMs other than one with CAT, due to the
+    sum of CBMs is fixed, that means actual `cos_max` in use will automatically
+    reduce to half when CDP is enabled.
 
 ### reboot
 > `= t[riple] | k[bd] | a[cpi] | p[ci] | P[ower] | e[fi] | n[o] [, [w]arm | [c]old]`
diff --git a/xen/arch/x86/psr.c b/xen/arch/x86/psr.c
index c0daa2e..e44ed8b 100644
--- a/xen/arch/x86/psr.c
+++ b/xen/arch/x86/psr.c
@@ -21,9 +21,16 @@
 
 #define PSR_CMT        (1<<0)
 #define PSR_CAT        (1<<1)
+#define PSR_CDP        (1<<2)
 
 struct psr_cat_cbm {
-    uint64_t cbm;
+    union {
+        uint64_t cbm;
+        struct {
+            uint64_t code;
+            uint64_t data;
+        };
+    } u;
     unsigned int ref;
 };
 
@@ -43,6 +50,7 @@ struct psr_cmt *__read_mostly psr_cmt;
 
 static unsigned long *__read_mostly cat_socket_enable;
 static struct psr_cat_socket_info *__read_mostly cat_socket_info;
+static unsigned long *__read_mostly cdp_socket_enable;
 
 static unsigned int __initdata opt_psr;
 static unsigned int __initdata opt_rmid_max = 255;
@@ -94,6 +102,7 @@ static void __init parse_psr_param(char *s)
 
         parse_psr_bool(s, val_str, "cmt", PSR_CMT);
         parse_psr_bool(s, val_str, "cat", PSR_CAT);
+        parse_psr_bool(s, val_str, "cdp", PSR_CDP);
 
         if ( val_str && !strcmp(s, "rmid_max") )
             opt_rmid_max = simple_strtoul(val_str, NULL, 0);
@@ -261,8 +270,14 @@ static struct psr_cat_socket_info *get_cat_socket_info(unsigned int socket)
     return cat_socket_info + socket;
 }
 
+static inline bool_t cdp_is_enabled(unsigned int socket,
+                                    unsigned long *cdp_socket_enable)
+{
+    return (cdp_socket_enable && test_bit(socket, cdp_socket_enable));
+}
+
 int psr_get_cat_l3_info(unsigned int socket, uint32_t *cbm_len,
-                        uint32_t *cos_max)
+                        uint32_t *cos_max, uint32_t *flags)
 {
     struct psr_cat_socket_info *info = get_cat_socket_info(socket);
 
@@ -272,6 +287,10 @@ int psr_get_cat_l3_info(unsigned int socket, uint32_t *cbm_len,
     *cbm_len = info->cbm_len;
     *cos_max = info->cos_max;
 
+    *flags = 0;
+    if ( cdp_is_enabled(socket, cdp_socket_enable) )
+        *flags |= PSR_CAT_FLAG_L3_CDP;
+
     return 0;
 }
 
@@ -282,7 +301,7 @@ int psr_get_l3_cbm(struct domain *d, unsigned int socket, uint64_t *cbm)
     if ( IS_ERR(info) )
         return PTR_ERR(info);
 
-    *cbm = info->cos_to_cbm[d->arch.psr_cos_ids[socket]].cbm;
+    *cbm = info->cos_to_cbm[d->arch.psr_cos_ids[socket]].u.cbm;
 
     return 0;
 }
@@ -313,19 +332,34 @@ static bool_t psr_check_cbm(unsigned int cbm_len, uint64_t cbm)
 struct cos_cbm_info
 {
     unsigned int cos;
-    uint64_t cbm;
+    uint64_t cbm_code;
+    uint64_t cbm_data;
+    bool_t cdp;
 };
 
 static void do_write_l3_cbm(void *data)
 {
     struct cos_cbm_info *info = data;
 
-    wrmsrl(MSR_IA32_PSR_L3_MASK(info->cos), info->cbm);
+    if ( info->cdp )
+    {
+        wrmsrl(MSR_IA32_PSR_L3_MASK_CODE(info->cos), info->cbm_code);
+        wrmsrl(MSR_IA32_PSR_L3_MASK_DATA(info->cos), info->cbm_data);
+    }
+    else
+        wrmsrl(MSR_IA32_PSR_L3_MASK(info->cos), info->cbm_code);
 }
 
-static int write_l3_cbm(unsigned int socket, unsigned int cos, uint64_t cbm)
+static int write_l3_cbm(unsigned int socket, unsigned int cos,
+                        uint64_t cbm_code, uint64_t cbm_data, bool_t cdp)
 {
-    struct cos_cbm_info info = { .cos = cos, .cbm = cbm };
+    struct cos_cbm_info info =
+    {
+      .cos = cos,
+      .cbm_code = cbm_code,
+      .cbm_data = cbm_data,
+      .cdp = cdp,
+    };
 
     if ( socket == cpu_to_socket(smp_processor_id()) )
         do_write_l3_cbm(&info);
@@ -363,7 +397,7 @@ int psr_set_l3_cbm(struct domain *d, unsigned int socket, uint64_t cbm)
         /* If still not found, then keep unused one. */
         if ( !found && cos != 0 && map[cos].ref == 0 )
             found = map + cos;
-        else if ( map[cos].cbm == cbm )
+        else if ( map[cos].u.cbm == cbm )
         {
             if ( unlikely(cos == old_cos) )
             {
@@ -387,16 +421,16 @@ int psr_set_l3_cbm(struct domain *d, unsigned int socket, uint64_t cbm)
     }
 
     cos = found - map;
-    if ( found->cbm != cbm )
+    if ( found->u.cbm != cbm )
     {
-        int ret = write_l3_cbm(socket, cos, cbm);
+        int ret = write_l3_cbm(socket, cos, cbm, 0, 0);
 
         if ( ret )
         {
             spin_unlock(&info->cbm_lock);
             return ret;
         }
-        found->cbm = cbm;
+        found->u.cbm = cbm;
     }
 
     found->ref++;
@@ -470,6 +504,7 @@ static void cat_cpu_init(void)
     struct psr_cat_socket_info *info;
     unsigned int socket;
     unsigned int cpu = smp_processor_id();
+    uint64_t val;
     const struct cpuinfo_x86 *c = cpu_data + cpu;
 
     if ( !cpu_has(c, X86_FEATURE_CAT) || c->cpuid_level < PSR_CPUID_LEVEL_CAT )
@@ -490,13 +525,32 @@ static void cat_cpu_init(void)
         info->cos_to_cbm = temp_cos_to_cbm;
         temp_cos_to_cbm = NULL;
         /* cos=0 is reserved as default cbm(all ones). */
-        info->cos_to_cbm[0].cbm = (1ull << info->cbm_len) - 1;
+        info->cos_to_cbm[0].u.cbm = (1ull << info->cbm_len) - 1;
 
         spin_lock_init(&info->cbm_lock);
 
         set_bit(socket, cat_socket_enable);
-        printk(XENLOG_INFO "CAT: enabled on socket %u, cos_max:%u, cbm_len:%u\n",
-               socket, info->cos_max, info->cbm_len);
+
+        if ( (ecx & PSR_CAT_CDP_CAPABILITY) && (opt_psr & PSR_CDP) &&
+             cdp_socket_enable && !test_bit(socket, cdp_socket_enable) )
+        {
+            rdmsrl(MSR_IA32_PSR_L3_QOS_CFG, val);
+            wrmsrl(MSR_IA32_PSR_L3_QOS_CFG, val | (1 << PSR_L3_QOS_CDP_ENABLE_BIT));
+
+            info->cos_to_cbm[0].u.code = (1ull << info->cbm_len) - 1;
+            info->cos_to_cbm[0].u.data = (1ull << info->cbm_len) - 1;
+
+            /* We only write mask1 since mask0 is always all ones by default. */
+            wrmsrl(MSR_IA32_PSR_L3_MASK(1), (1ull << info->cbm_len) - 1);
+
+            /* Cut half of cos_max when CDP is enabled. */
+            info->cos_max >>= 1;
+
+            set_bit(socket, cdp_socket_enable);
+        }
+        printk(XENLOG_INFO "CAT: enabled on socket %u, cos_max:%u, cbm_len:%u, CDP:%s\n",
+               socket, info->cos_max, info->cbm_len,
+               cdp_is_enabled(socket, cdp_socket_enable) ? "on" : "off");
     }
 }
 
@@ -513,6 +567,7 @@ static void cat_cpu_fini(unsigned int cpu)
             xfree(info->cos_to_cbm);
             info->cos_to_cbm = NULL;
         }
+        clear_bit(socket, cdp_socket_enable);
         clear_bit(socket, cat_socket_enable);
     }
 }
@@ -535,6 +590,7 @@ static void __init init_psr_cat(void)
 
     cat_socket_enable = xzalloc_array(unsigned long, BITS_TO_LONGS(nr_sockets));
     cat_socket_info = xzalloc_array(struct psr_cat_socket_info, nr_sockets);
+    cdp_socket_enable = xzalloc_array(unsigned long, BITS_TO_LONGS(nr_sockets));
 
     if ( !cat_socket_enable || !cat_socket_info )
         psr_cat_free();
diff --git a/xen/arch/x86/sysctl.c b/xen/arch/x86/sysctl.c
index f36b52f..e42c5e7 100644
--- a/xen/arch/x86/sysctl.c
+++ b/xen/arch/x86/sysctl.c
@@ -177,12 +177,13 @@ long arch_do_sysctl(
         case XEN_SYSCTL_PSR_CAT_get_l3_info:
             ret = psr_get_cat_l3_info(sysctl->u.psr_cat_op.target,
                                       &sysctl->u.psr_cat_op.u.l3_info.cbm_len,
-                                      &sysctl->u.psr_cat_op.u.l3_info.cos_max);
+                                      &sysctl->u.psr_cat_op.u.l3_info.cos_max,
+                                      &sysctl->u.psr_cat_op.u.l3_info.flags);
 
             if ( !ret && __copy_field_to_guest(u_sysctl, sysctl, u.psr_cat_op) )
                 ret = -EFAULT;
-
             break;
+
         default:
             ret = -EOPNOTSUPP;
             break;
diff --git a/xen/include/asm-x86/msr-index.h b/xen/include/asm-x86/msr-index.h
index e9c4723..65c1d02 100644
--- a/xen/include/asm-x86/msr-index.h
+++ b/xen/include/asm-x86/msr-index.h
@@ -328,7 +328,10 @@
 #define MSR_IA32_CMT_EVTSEL		0x00000c8d
 #define MSR_IA32_CMT_CTR		0x00000c8e
 #define MSR_IA32_PSR_ASSOC		0x00000c8f
+#define MSR_IA32_PSR_L3_QOS_CFG	0x00000c81
 #define MSR_IA32_PSR_L3_MASK(n)	(0x00000c90 + (n))
+#define MSR_IA32_PSR_L3_MASK_CODE(n)	(0x00000c90 + (n) * 2 + 1)
+#define MSR_IA32_PSR_L3_MASK_DATA(n)	(0x00000c90 + (n) * 2)
 
 /* Intel Model 6 */
 #define MSR_P6_PERFCTR(n)		(0x000000c1 + (n))
diff --git a/xen/include/asm-x86/psr.h b/xen/include/asm-x86/psr.h
index 081750f..422b053 100644
--- a/xen/include/asm-x86/psr.h
+++ b/xen/include/asm-x86/psr.h
@@ -27,6 +27,15 @@
 /* L3 Monitoring Features */
 #define PSR_CMT_L3_OCCUPANCY           0x1
 
+/* CDP Capability */
+#define PSR_CAT_CDP_CAPABILITY       (1u << 2)
+
+/* L3 CDP Enable bit*/
+#define PSR_L3_QOS_CDP_ENABLE_BIT       0x0
+
+/* L3 CDP flag bit */
+#define PSR_CAT_FLAG_L3_CDP       (1u << 0)
+
 struct psr_cmt_l3 {
     unsigned int features;
     unsigned int upscaling_factor;
@@ -52,7 +61,7 @@ void psr_free_rmid(struct domain *d);
 void psr_ctxt_switch_to(struct domain *d);
 
 int psr_get_cat_l3_info(unsigned int socket, uint32_t *cbm_len,
-                        uint32_t *cos_max);
+                        uint32_t *cos_max, uint32_t *flags);
 int psr_get_l3_cbm(struct domain *d, unsigned int socket, uint64_t *cbm);
 int psr_set_l3_cbm(struct domain *d, unsigned int socket, uint64_t cbm);
 
diff --git a/xen/include/public/sysctl.h b/xen/include/public/sysctl.h
index 58c9be2..0e2834f 100644
--- a/xen/include/public/sysctl.h
+++ b/xen/include/public/sysctl.h
@@ -35,7 +35,7 @@
 #include "domctl.h"
 #include "physdev.h"
 
-#define XEN_SYSCTL_INTERFACE_VERSION 0x0000000C
+#define XEN_SYSCTL_INTERFACE_VERSION 0x0000000D
 
 /*
  * Read console content from Xen buffer ring.
@@ -704,6 +704,8 @@ struct xen_sysctl_psr_cat_op {
         struct {
             uint32_t cbm_len;   /* OUT: CBM length */
             uint32_t cos_max;   /* OUT: Maximum COS */
+            #define XEN_SYSCTL_PSR_CAT_L3_CDP       (1u << 0)
+            uint32_t flags;     /* OUT: CAT flags */
         } l3_info;
     } u;
 };
-- 
1.9.1