Merge branch 'x86' of git://git.kernel.org/pub/scm/linux/kernel/git/rric/oprofile into perf/urgent

4 files changed, 100 insertions, 46 deletions

diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 986f779..91ba8e6 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -121,6 +121,7 @@
 #define MSR_AMD64_IBSDCLINAD		0xc0011038
 #define MSR_AMD64_IBSDCPHYSAD		0xc0011039
 #define MSR_AMD64_IBSCTL		0xc001103a
+#define MSR_AMD64_IBSBRTARGET		0xc001103b
 
 /* Fam 10h MSRs */
 #define MSR_FAM10H_MMIO_CONF_BASE	0xc0010058
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 6e742cc..550e26b1 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/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index bd1489c..4e8baad 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -726,6 +726,12 @@ int __init op_nmi_init(struct oprofile_operations *ops)
 		case 0x11:
 			cpu_type = "x86-64/family11h";
 			break;
+		case 0x12:
+			cpu_type = "x86-64/family12h";
+			break;
+		case 0x14:
+			cpu_type = "x86-64/family14h";
+			break;
 		default:
 			return -ENODEV;
 		}
diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c
index 68759e7..a011bcc 100644
--- a/arch/x86/oprofile/op_model_amd.c
+++ b/arch/x86/oprofile/op_model_amd.c
@@ -48,17 +48,24 @@ static unsigned long reset_value[NUM_VIRT_COUNTERS];
 
 static u32 ibs_caps;
 
-struct op_ibs_config {
+struct ibs_config {
 	unsigned long op_enabled;
 	unsigned long fetch_enabled;
 	unsigned long max_cnt_fetch;
 	unsigned long max_cnt_op;
 	unsigned long rand_en;
 	unsigned long dispatched_ops;
+	unsigned long branch_target;
 };
 
-static struct op_ibs_config ibs_config;
-static u64 ibs_op_ctl;
+struct ibs_state {
+	u64		ibs_op_ctl;
+	int		branch_target;
+	unsigned long	sample_size;
+};
+
+static struct ibs_config ibs_config;
+static struct ibs_state ibs_state;
 
 /*
  * IBS cpuid feature detection
@@ -71,8 +78,16 @@ static u64 ibs_op_ctl;
  * bit 0 is used to indicate the existence of IBS.
  */
 #define IBS_CAPS_AVAIL			(1U<<0)
+#define IBS_CAPS_FETCHSAM		(1U<<1)
+#define IBS_CAPS_OPSAM			(1U<<2)
 #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	\
+					 | IBS_CAPS_OPSAM)
 
 /*
  * IBS APIC setup
@@ -99,12 +114,12 @@ static u32 get_ibs_caps(void)
 	/* check IBS cpuid feature flags */
 	max_level = cpuid_eax(0x80000000);
 	if (max_level < IBS_CPUID_FEATURES)
-		return IBS_CAPS_AVAIL;
+		return IBS_CAPS_DEFAULT;
 
 	ibs_caps = cpuid_eax(IBS_CPUID_FEATURES);
 	if (!(ibs_caps & IBS_CAPS_AVAIL))
 		/* cpuid flags not valid */
-		return IBS_CAPS_AVAIL;
+		return IBS_CAPS_DEFAULT;
 
 	return ibs_caps;
 }
@@ -197,8 +212,8 @@ op_amd_handle_ibs(struct pt_regs * const regs,
 		rdmsrl(MSR_AMD64_IBSOPCTL, ctl);
 		if (ctl & IBS_OP_VAL) {
 			rdmsrl(MSR_AMD64_IBSOPRIP, val);
-			oprofile_write_reserve(&entry, regs, val,
-					       IBS_OP_CODE, IBS_OP_SIZE);
+			oprofile_write_reserve(&entry, regs, val, IBS_OP_CODE,
+					       ibs_state.sample_size);
 			oprofile_add_data64(&entry, val);
 			rdmsrl(MSR_AMD64_IBSOPDATA, val);
 			oprofile_add_data64(&entry, val);
@@ -210,10 +225,14 @@ op_amd_handle_ibs(struct pt_regs * const regs,
 			oprofile_add_data64(&entry, val);
 			rdmsrl(MSR_AMD64_IBSDCPHYSAD, val);
 			oprofile_add_data64(&entry, val);
+			if (ibs_state.branch_target) {
+				rdmsrl(MSR_AMD64_IBSBRTARGET, val);
+				oprofile_add_data(&entry, (unsigned long)val);
+			}
 			oprofile_write_commit(&entry);
 
 			/* reenable the IRQ */
-			ctl = op_amd_randomize_ibs_op(ibs_op_ctl);
+			ctl = op_amd_randomize_ibs_op(ibs_state.ibs_op_ctl);
 			wrmsrl(MSR_AMD64_IBSOPCTL, ctl);
 		}
 	}
@@ -226,21 +245,32 @@ static inline void op_amd_start_ibs(void)
 	if (!ibs_caps)
 		return;
 
+	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);
 	}
 
 	if (ibs_config.op_enabled) {
-		ibs_op_ctl = ibs_config.max_cnt_op >> 4;
+		val = ibs_config.max_cnt_op >> 4;
 		if (!(ibs_caps & IBS_CAPS_RDWROPCNT)) {
 			/*
 			 * IbsOpCurCnt not supported.  See
 			 * op_amd_randomize_ibs_op() for details.
 			 */
-			ibs_op_ctl = clamp(ibs_op_ctl, 0x0081ULL, 0xFF80ULL);
+			val = clamp(val, 0x0081ULL, 0xFF80ULL);
+			ibs_config.max_cnt_op = val << 4;
 		} else {
 			/*
 			 * The start value is randomized with a
@@ -248,13 +278,24 @@ static inline void op_amd_start_ibs(void)
 			 * with the half of the randomized range. Also
 			 * avoid underflows.
 			 */
-			ibs_op_ctl = min(ibs_op_ctl + 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;
+		ibs_state.sample_size = IBS_OP_SIZE;
+		if (ibs_config.branch_target) {
+			ibs_state.branch_target = 1;
+			ibs_state.sample_size++;
 		}
-		if (ibs_caps & IBS_CAPS_OPCNT && ibs_config.dispatched_ops)
-			ibs_op_ctl |= IBS_OP_CNT_CTL;
-		ibs_op_ctl |= IBS_OP_ENABLE;
-		val = op_amd_randomize_ibs_op(ibs_op_ctl);
+		val = op_amd_randomize_ibs_op(ibs_state.ibs_op_ctl);
 		wrmsrl(MSR_AMD64_IBSOPCTL, val);
 	}
 }
@@ -626,28 +667,33 @@ static int setup_ibs_files(struct super_block *sb, struct dentry *root)
 	/* model specific files */
 
 	/* setup some reasonable defaults */
+	memset(&ibs_config, 0, sizeof(ibs_config));
 	ibs_config.max_cnt_fetch = 250000;
-	ibs_config.fetch_enabled = 0;
 	ibs_config.max_cnt_op = 250000;
-	ibs_config.op_enabled = 0;
-	ibs_config.dispatched_ops = 0;
-
-	dir = oprofilefs_mkdir(sb, root, "ibs_fetch");
-	oprofilefs_create_ulong(sb, dir, "enable",
-				&ibs_config.fetch_enabled);
-	oprofilefs_create_ulong(sb, dir, "max_count",
-				&ibs_config.max_cnt_fetch);
-	oprofilefs_create_ulong(sb, dir, "rand_enable",
-				&ibs_config.rand_en);
-
-	dir = oprofilefs_mkdir(sb, root, "ibs_op");
-	oprofilefs_create_ulong(sb, dir, "enable",
-				&ibs_config.op_enabled);
-	oprofilefs_create_ulong(sb, dir, "max_count",
-				&ibs_config.max_cnt_op);
-	if (ibs_caps & IBS_CAPS_OPCNT)
-		oprofilefs_create_ulong(sb, dir, "dispatched_ops",
-					&ibs_config.dispatched_ops);
+
+	if (ibs_caps & IBS_CAPS_FETCHSAM) {
+		dir = oprofilefs_mkdir(sb, root, "ibs_fetch");
+		oprofilefs_create_ulong(sb, dir, "enable",
+					&ibs_config.fetch_enabled);
+		oprofilefs_create_ulong(sb, dir, "max_count",
+					&ibs_config.max_cnt_fetch);
+		oprofilefs_create_ulong(sb, dir, "rand_enable",
+					&ibs_config.rand_en);
+	}
+
+	if (ibs_caps & IBS_CAPS_OPSAM) {
+		dir = oprofilefs_mkdir(sb, root, "ibs_op");
+		oprofilefs_create_ulong(sb, dir, "enable",
+					&ibs_config.op_enabled);
+		oprofilefs_create_ulong(sb, dir, "max_count",
+					&ibs_config.max_cnt_op);
+		if (ibs_caps & IBS_CAPS_OPCNT)
+			oprofilefs_create_ulong(sb, dir, "dispatched_ops",
+						&ibs_config.dispatched_ops);
+		if (ibs_caps & IBS_CAPS_BRNTRGT)
+			oprofilefs_create_ulong(sb, dir, "branch_target",
+						&ibs_config.branch_target);
+	}
 
 	return 0;
 }