oprofile, x86: Add support for IBS periodic op counter extension

The count value for IBS op sampling has been extended by 7 bits. The
feature is reflected in bit 6 (OpCntExt) of the IBS capability
register (CPUID Fn8000_001B_EAX).

Signed-off-by: Robert Richter <robert.richter@amd.com>

2 files changed, 29 insertions, 12 deletions

diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 6e742cc4251b..550e26b1dbb3 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -111,17 +111,18 @@ union cpuid10_edx {
 #define X86_PMC_IDX_FIXED_BTS				(X86_PMC_IDX_FIXED + 16)
 
 /* IbsFetchCtl bits/masks */
-#define IBS_FETCH_RAND_EN		(1ULL<<57)
-#define IBS_FETCH_VAL			(1ULL<<49)
-#define IBS_FETCH_ENABLE		(1ULL<<48)
-#define IBS_FETCH_CNT			0xFFFF0000ULL
-#define IBS_FETCH_MAX_CNT		0x0000FFFFULL
+#define IBS_FETCH_RAND_EN	(1ULL<<57)
+#define IBS_FETCH_VAL		(1ULL<<49)
+#define IBS_FETCH_ENABLE	(1ULL<<48)
+#define IBS_FETCH_CNT		0xFFFF0000ULL
+#define IBS_FETCH_MAX_CNT	0x0000FFFFULL
 
 /* IbsOpCtl bits */
-#define IBS_OP_CNT_CTL			(1ULL<<19)
-#define IBS_OP_VAL			(1ULL<<18)
-#define IBS_OP_ENABLE			(1ULL<<17)
-#define IBS_OP_MAX_CNT			0x0000FFFFULL
+#define IBS_OP_CNT_CTL		(1ULL<<19)
+#define IBS_OP_VAL		(1ULL<<18)
+#define IBS_OP_ENABLE		(1ULL<<17)
+#define IBS_OP_MAX_CNT		0x0000FFFFULL
+#define IBS_OP_MAX_CNT_EXT	0x007FFFFFULL	/* not a register bit mask */
 
 #ifdef CONFIG_PERF_EVENTS
 extern void init_hw_perf_events(void);
diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c
index 9de33fa9531a..65f0a1eb6b86 100644
--- a/arch/x86/oprofile/op_model_amd.c
+++ b/arch/x86/oprofile/op_model_amd.c
@@ -83,6 +83,7 @@ static struct ibs_state ibs_state;
 #define IBS_CAPS_RDWROPCNT		(1U<<3)
 #define IBS_CAPS_OPCNT			(1U<<4)
 #define IBS_CAPS_BRNTRGT		(1U<<5)
+#define IBS_CAPS_OPCNTEXT		(1U<<6)
 
 #define IBS_CAPS_DEFAULT		(IBS_CAPS_AVAIL		\
 					 | IBS_CAPS_FETCHSAM	\
@@ -246,8 +247,16 @@ static inline void op_amd_start_ibs(void)
 
 	memset(&ibs_state, 0, sizeof(ibs_state));
 
+	/*
+	 * Note: Since the max count settings may out of range we
+	 * write back the actual used values so that userland can read
+	 * it.
+	 */
+
 	if (ibs_config.fetch_enabled) {
-		val = (ibs_config.max_cnt_fetch >> 4) & IBS_FETCH_MAX_CNT;
+		val = ibs_config.max_cnt_fetch >> 4;
+		val = min(val, IBS_FETCH_MAX_CNT);
+		ibs_config.max_cnt_fetch = val << 4;
 		val |= ibs_config.rand_en ? IBS_FETCH_RAND_EN : 0;
 		val |= IBS_FETCH_ENABLE;
 		wrmsrl(MSR_AMD64_IBSFETCHCTL, val);
@@ -261,6 +270,7 @@ static inline void op_amd_start_ibs(void)
 			 * op_amd_randomize_ibs_op() for details.
 			 */
 			val = clamp(val, 0x0081ULL, 0xFF80ULL);
+			ibs_config.max_cnt_op = val << 4;
 		} else {
 			/*
 			 * The start value is randomized with a
@@ -268,9 +278,15 @@ static inline void op_amd_start_ibs(void)
 			 * with the half of the randomized range. Also
 			 * avoid underflows.
 			 */
-			val = min(val + IBS_RANDOM_MAXCNT_OFFSET,
-				  IBS_OP_MAX_CNT);
+			val += IBS_RANDOM_MAXCNT_OFFSET;
+			if (ibs_caps & IBS_CAPS_OPCNTEXT)
+				val = min(val, IBS_OP_MAX_CNT_EXT);
+			else
+				val = min(val, IBS_OP_MAX_CNT);
+			ibs_config.max_cnt_op =
+				(val - IBS_RANDOM_MAXCNT_OFFSET) << 4;
 		}
+		val = ((val & ~IBS_OP_MAX_CNT) << 4) | (val & IBS_OP_MAX_CNT);
 		val |= ibs_config.dispatched_ops ? IBS_OP_CNT_CTL : 0;
 		val |= IBS_OP_ENABLE;
 		ibs_state.ibs_op_ctl = val;