* @file op_model_amd.c
* athlon / K7 / K8 / Family 10h model-specific MSR operations
*
- * @remark Copyright 2002-2008 OProfile authors
+ * @remark Copyright 2002-2009 OProfile authors
* @remark Read the file COPYING
*
* @author John Levon
* @author Philippe Elie
* @author Graydon Hoare
* @author Robert Richter <robert.richter@amd.com>
- * @author Barry Kasindorf
-*/
+ * @author Barry Kasindorf <barry.kasindorf@amd.com>
+ * @author Jason Yeh <jason.yeh@amd.com>
+ * @author Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
+ */
#include <linux/oprofile.h>
#include <linux/device.h>
#include <linux/pci.h>
+#include <linux/percpu.h>
#include <asm/ptrace.h>
#include <asm/msr.h>
#include <asm/nmi.h>
+#include <asm/apic.h>
+#include <asm/processor.h>
+#include <asm/cpufeature.h>
#include "op_x86_model.h"
#include "op_counter.h"
#define NUM_COUNTERS 4
#define NUM_CONTROLS 4
+#ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX
+#define NUM_VIRT_COUNTERS 32
+#define NUM_VIRT_CONTROLS 32
+#else
+#define NUM_VIRT_COUNTERS NUM_COUNTERS
+#define NUM_VIRT_CONTROLS NUM_CONTROLS
+#endif
+
+#define OP_EVENT_MASK 0x0FFF
+#define OP_CTR_OVERFLOW (1ULL<<31)
+
+#define MSR_AMD_EVENTSEL_RESERVED ((0xFFFFFCF0ULL<<32)|(1ULL<<21))
-#define CTR_IS_RESERVED(msrs, c) (msrs->counters[(c)].addr ? 1 : 0)
-#define CTR_READ(l, h, msrs, c) do {rdmsr(msrs->counters[(c)].addr, (l), (h)); } while (0)
-#define CTR_WRITE(l, msrs, c) do {wrmsr(msrs->counters[(c)].addr, -(unsigned int)(l), -1); } while (0)
-#define CTR_OVERFLOWED(n) (!((n) & (1U<<31)))
-
-#define CTRL_IS_RESERVED(msrs, c) (msrs->controls[(c)].addr ? 1 : 0)
-#define CTRL_READ(l, h, msrs, c) do {rdmsr(msrs->controls[(c)].addr, (l), (h)); } while (0)
-#define CTRL_WRITE(l, h, msrs, c) do {wrmsr(msrs->controls[(c)].addr, (l), (h)); } while (0)
-#define CTRL_SET_ACTIVE(n) (n |= (1<<22))
-#define CTRL_SET_INACTIVE(n) (n &= ~(1<<22))
-#define CTRL_CLEAR_LO(x) (x &= (1<<21))
-#define CTRL_CLEAR_HI(x) (x &= 0xfffffcf0)
-#define CTRL_SET_ENABLE(val) (val |= 1<<20)
-#define CTRL_SET_USR(val, u) (val |= ((u & 1) << 16))
-#define CTRL_SET_KERN(val, k) (val |= ((k & 1) << 17))
-#define CTRL_SET_UM(val, m) (val |= (m << 8))
-#define CTRL_SET_EVENT_LOW(val, e) (val |= (e & 0xff))
-#define CTRL_SET_EVENT_HIGH(val, e) (val |= ((e >> 8) & 0xf))
-#define CTRL_SET_HOST_ONLY(val, h) (val |= ((h & 1) << 9))
-#define CTRL_SET_GUEST_ONLY(val, h) (val |= ((h & 1) << 8))
-
-static unsigned long reset_value[NUM_COUNTERS];
-
-#ifdef CONFIG_OPROFILE_IBS
+static unsigned long reset_value[NUM_VIRT_COUNTERS];
/* IbsFetchCtl bits/masks */
-#define IBS_FETCH_HIGH_VALID_BIT (1UL << 17) /* bit 49 */
-#define IBS_FETCH_HIGH_ENABLE (1UL << 16) /* bit 48 */
-#define IBS_FETCH_LOW_MAX_CNT_MASK 0x0000FFFFUL /* MaxCnt mask */
-
-/*IbsOpCtl bits */
-#define IBS_OP_LOW_VALID_BIT (1ULL<<18) /* bit 18 */
-#define IBS_OP_LOW_ENABLE (1ULL<<17) /* bit 17 */
-
-/* Codes used in cpu_buffer.c */
-/* This produces duplicate code, need to be fixed */
-#define IBS_FETCH_BEGIN 3
-#define IBS_OP_BEGIN 4
-
-/* The function interface needs to be fixed, something like add
- data. Should then be added to linux/oprofile.h. */
-extern void
-oprofile_add_ibs_sample(struct pt_regs *const regs,
- unsigned int * const ibs_sample, int ibs_code);
-
-struct ibs_fetch_sample {
- /* MSRC001_1031 IBS Fetch Linear Address Register */
- unsigned int ibs_fetch_lin_addr_low;
- unsigned int ibs_fetch_lin_addr_high;
- /* MSRC001_1030 IBS Fetch Control Register */
- unsigned int ibs_fetch_ctl_low;
- unsigned int ibs_fetch_ctl_high;
- /* MSRC001_1032 IBS Fetch Physical Address Register */
- unsigned int ibs_fetch_phys_addr_low;
- unsigned int ibs_fetch_phys_addr_high;
-};
+#define IBS_FETCH_RAND_EN (1ULL<<57)
+#define IBS_FETCH_VAL (1ULL<<49)
+#define IBS_FETCH_ENABLE (1ULL<<48)
+#define IBS_FETCH_CNT_MASK 0xFFFF0000ULL
-struct ibs_op_sample {
- /* MSRC001_1034 IBS Op Logical Address Register (IbsRIP) */
- unsigned int ibs_op_rip_low;
- unsigned int ibs_op_rip_high;
- /* MSRC001_1035 IBS Op Data Register */
- unsigned int ibs_op_data1_low;
- unsigned int ibs_op_data1_high;
- /* MSRC001_1036 IBS Op Data 2 Register */
- unsigned int ibs_op_data2_low;
- unsigned int ibs_op_data2_high;
- /* MSRC001_1037 IBS Op Data 3 Register */
- unsigned int ibs_op_data3_low;
- unsigned int ibs_op_data3_high;
- /* MSRC001_1038 IBS DC Linear Address Register (IbsDcLinAd) */
- unsigned int ibs_dc_linear_low;
- unsigned int ibs_dc_linear_high;
- /* MSRC001_1039 IBS DC Physical Address Register (IbsDcPhysAd) */
- unsigned int ibs_dc_phys_low;
- unsigned int ibs_dc_phys_high;
-};
+/* IbsOpCtl bits */
+#define IBS_OP_CNT_CTL (1ULL<<19)
+#define IBS_OP_VAL (1ULL<<18)
+#define IBS_OP_ENABLE (1ULL<<17)
-/*
- * unitialize the APIC for the IBS interrupts if needed on AMD Family10h+
-*/
-static void clear_ibs_nmi(void);
+#define IBS_FETCH_SIZE 6
+#define IBS_OP_SIZE 12
-static int ibs_allowed; /* AMD Family10h and later */
+static u32 ibs_caps;
struct op_ibs_config {
unsigned long op_enabled;
};
static struct op_ibs_config ibs_config;
+static u64 ibs_op_ctl;
+
+/*
+ * IBS cpuid feature detection
+ */
+
+#define IBS_CPUID_FEATURES 0x8000001b
+
+/*
+ * Same bit mask as for IBS cpuid feature flags (Fn8000_001B_EAX), but
+ * bit 0 is used to indicate the existence of IBS.
+ */
+#define IBS_CAPS_AVAIL (1LL<<0)
+#define IBS_CAPS_RDWROPCNT (1LL<<3)
+#define IBS_CAPS_OPCNT (1LL<<4)
+
+/*
+ * IBS randomization macros
+ */
+#define IBS_RANDOM_BITS 12
+#define IBS_RANDOM_MASK ((1ULL << IBS_RANDOM_BITS) - 1)
+#define IBS_RANDOM_MAXCNT_OFFSET (1ULL << (IBS_RANDOM_BITS - 5))
+
+static u32 get_ibs_caps(void)
+{
+ u32 ibs_caps;
+ unsigned int max_level;
+
+ if (!boot_cpu_has(X86_FEATURE_IBS))
+ return 0;
+
+ /* check IBS cpuid feature flags */
+ max_level = cpuid_eax(0x80000000);
+ if (max_level < IBS_CPUID_FEATURES)
+ return IBS_CAPS_AVAIL;
+
+ ibs_caps = cpuid_eax(IBS_CPUID_FEATURES);
+ if (!(ibs_caps & IBS_CAPS_AVAIL))
+ /* cpuid flags not valid */
+ return IBS_CAPS_AVAIL;
+
+ return ibs_caps;
+}
+
+#ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX
+
+static void op_mux_switch_ctrl(struct op_x86_model_spec const *model,
+ struct op_msrs const * const msrs)
+{
+ u64 val;
+ int i;
+
+ /* enable active counters */
+ for (i = 0; i < NUM_COUNTERS; ++i) {
+ int virt = op_x86_phys_to_virt(i);
+ if (!counter_config[virt].enabled)
+ continue;
+ rdmsrl(msrs->controls[i].addr, val);
+ val &= model->reserved;
+ val |= op_x86_get_ctrl(model, &counter_config[virt]);
+ wrmsrl(msrs->controls[i].addr, val);
+ }
+}
#endif
}
}
-
-static void op_amd_setup_ctrs(struct op_msrs const * const msrs)
+static void op_amd_setup_ctrs(struct op_x86_model_spec const *model,
+ struct op_msrs const * const msrs)
{
- unsigned int low, high;
+ u64 val;
int i;
+ /* setup reset_value */
+ for (i = 0; i < NUM_VIRT_COUNTERS; ++i) {
+ if (counter_config[i].enabled)
+ reset_value[i] = counter_config[i].count;
+ else
+ reset_value[i] = 0;
+ }
+
/* clear all counters */
- for (i = 0 ; i < NUM_CONTROLS; ++i) {
- if (unlikely(!CTRL_IS_RESERVED(msrs, i)))
+ for (i = 0; i < NUM_CONTROLS; ++i) {
+ if (unlikely(!msrs->controls[i].addr)) {
+ if (counter_config[i].enabled && !smp_processor_id())
+ /*
+ * counter is reserved, this is on all
+ * cpus, so report only for cpu #0
+ */
+ op_x86_warn_reserved(i);
continue;
- CTRL_READ(low, high, msrs, i);
- CTRL_CLEAR_LO(low);
- CTRL_CLEAR_HI(high);
- CTRL_WRITE(low, high, msrs, i);
+ }
+ rdmsrl(msrs->controls[i].addr, val);
+ if (val & ARCH_PERFMON_EVENTSEL0_ENABLE)
+ op_x86_warn_in_use(i);
+ val &= model->reserved;
+ wrmsrl(msrs->controls[i].addr, val);
}
/* avoid a false detection of ctr overflows in NMI handler */
for (i = 0; i < NUM_COUNTERS; ++i) {
- if (unlikely(!CTR_IS_RESERVED(msrs, i)))
+ if (unlikely(!msrs->counters[i].addr))
continue;
- CTR_WRITE(1, msrs, i);
+ wrmsrl(msrs->counters[i].addr, -1LL);
}
/* enable active counters */
for (i = 0; i < NUM_COUNTERS; ++i) {
- if ((counter_config[i].enabled) && (CTR_IS_RESERVED(msrs, i))) {
- reset_value[i] = counter_config[i].count;
+ int virt = op_x86_phys_to_virt(i);
+ if (!counter_config[virt].enabled)
+ continue;
+ if (!msrs->counters[i].addr)
+ continue;
- CTR_WRITE(counter_config[i].count, msrs, i);
-
- CTRL_READ(low, high, msrs, i);
- CTRL_CLEAR_LO(low);
- CTRL_CLEAR_HI(high);
- CTRL_SET_ENABLE(low);
- CTRL_SET_USR(low, counter_config[i].user);
- CTRL_SET_KERN(low, counter_config[i].kernel);
- CTRL_SET_UM(low, counter_config[i].unit_mask);
- CTRL_SET_EVENT_LOW(low, counter_config[i].event);
- CTRL_SET_EVENT_HIGH(high, counter_config[i].event);
- CTRL_SET_HOST_ONLY(high, 0);
- CTRL_SET_GUEST_ONLY(high, 0);
-
- CTRL_WRITE(low, high, msrs, i);
- } else {
- reset_value[i] = 0;
- }
+ /* setup counter registers */
+ wrmsrl(msrs->counters[i].addr, -(u64)reset_value[virt]);
+
+ /* setup control registers */
+ rdmsrl(msrs->controls[i].addr, val);
+ val &= model->reserved;
+ val |= op_x86_get_ctrl(model, &counter_config[virt]);
+ wrmsrl(msrs->controls[i].addr, val);
}
}
-#ifdef CONFIG_OPROFILE_IBS
+/*
+ * 16-bit Linear Feedback Shift Register (LFSR)
+ *
+ * 16 14 13 11
+ * Feedback polynomial = X + X + X + X + 1
+ */
+static unsigned int lfsr_random(void)
+{
+ static unsigned int lfsr_value = 0xF00D;
+ unsigned int bit;
+
+ /* Compute next bit to shift in */
+ bit = ((lfsr_value >> 0) ^
+ (lfsr_value >> 2) ^
+ (lfsr_value >> 3) ^
+ (lfsr_value >> 5)) & 0x0001;
+
+ /* Advance to next register value */
+ lfsr_value = (lfsr_value >> 1) | (bit << 15);
+
+ return lfsr_value;
+}
+
+/*
+ * IBS software randomization
+ *
+ * The IBS periodic op counter is randomized in software. The lower 12
+ * bits of the 20 bit counter are randomized. IbsOpCurCnt is
+ * initialized with a 12 bit random value.
+ */
+static inline u64 op_amd_randomize_ibs_op(u64 val)
+{
+ unsigned int random = lfsr_random();
+
+ if (!(ibs_caps & IBS_CAPS_RDWROPCNT))
+ /*
+ * Work around if the hw can not write to IbsOpCurCnt
+ *
+ * Randomize the lower 8 bits of the 16 bit
+ * IbsOpMaxCnt [15:0] value in the range of -128 to
+ * +127 by adding/subtracting an offset to the
+ * maximum count (IbsOpMaxCnt).
+ *
+ * To avoid over or underflows and protect upper bits
+ * starting at bit 16, the initial value for
+ * IbsOpMaxCnt must fit in the range from 0x0081 to
+ * 0xff80.
+ */
+ val += (s8)(random >> 4);
+ else
+ val |= (u64)(random & IBS_RANDOM_MASK) << 32;
+
+ return val;
+}
-static inline int
+static inline void
op_amd_handle_ibs(struct pt_regs * const regs,
struct op_msrs const * const msrs)
{
- unsigned int low, high;
- struct ibs_fetch_sample ibs_fetch;
- struct ibs_op_sample ibs_op;
+ u64 val, ctl;
+ struct op_entry entry;
- if (!ibs_allowed)
- return 1;
+ if (!ibs_caps)
+ return;
if (ibs_config.fetch_enabled) {
- rdmsr(MSR_AMD64_IBSFETCHCTL, low, high);
- if (high & IBS_FETCH_HIGH_VALID_BIT) {
- ibs_fetch.ibs_fetch_ctl_high = high;
- ibs_fetch.ibs_fetch_ctl_low = low;
- rdmsr(MSR_AMD64_IBSFETCHLINAD, low, high);
- ibs_fetch.ibs_fetch_lin_addr_high = high;
- ibs_fetch.ibs_fetch_lin_addr_low = low;
- rdmsr(MSR_AMD64_IBSFETCHPHYSAD, low, high);
- ibs_fetch.ibs_fetch_phys_addr_high = high;
- ibs_fetch.ibs_fetch_phys_addr_low = low;
-
- oprofile_add_ibs_sample(regs,
- (unsigned int *)&ibs_fetch,
- IBS_FETCH_BEGIN);
-
- /*reenable the IRQ */
- rdmsr(MSR_AMD64_IBSFETCHCTL, low, high);
- high &= ~IBS_FETCH_HIGH_VALID_BIT;
- high |= IBS_FETCH_HIGH_ENABLE;
- low &= IBS_FETCH_LOW_MAX_CNT_MASK;
- wrmsr(MSR_AMD64_IBSFETCHCTL, low, high);
+ rdmsrl(MSR_AMD64_IBSFETCHCTL, ctl);
+ if (ctl & IBS_FETCH_VAL) {
+ rdmsrl(MSR_AMD64_IBSFETCHLINAD, val);
+ oprofile_write_reserve(&entry, regs, val,
+ IBS_FETCH_CODE, IBS_FETCH_SIZE);
+ oprofile_add_data64(&entry, val);
+ oprofile_add_data64(&entry, ctl);
+ rdmsrl(MSR_AMD64_IBSFETCHPHYSAD, val);
+ oprofile_add_data64(&entry, val);
+ oprofile_write_commit(&entry);
+
+ /* reenable the IRQ */
+ ctl &= ~(IBS_FETCH_VAL | IBS_FETCH_CNT_MASK);
+ ctl |= IBS_FETCH_ENABLE;
+ wrmsrl(MSR_AMD64_IBSFETCHCTL, ctl);
}
}
if (ibs_config.op_enabled) {
- rdmsr(MSR_AMD64_IBSOPCTL, low, high);
- if (low & IBS_OP_LOW_VALID_BIT) {
- rdmsr(MSR_AMD64_IBSOPRIP, low, high);
- ibs_op.ibs_op_rip_low = low;
- ibs_op.ibs_op_rip_high = high;
- rdmsr(MSR_AMD64_IBSOPDATA, low, high);
- ibs_op.ibs_op_data1_low = low;
- ibs_op.ibs_op_data1_high = high;
- rdmsr(MSR_AMD64_IBSOPDATA2, low, high);
- ibs_op.ibs_op_data2_low = low;
- ibs_op.ibs_op_data2_high = high;
- rdmsr(MSR_AMD64_IBSOPDATA3, low, high);
- ibs_op.ibs_op_data3_low = low;
- ibs_op.ibs_op_data3_high = high;
- rdmsr(MSR_AMD64_IBSDCLINAD, low, high);
- ibs_op.ibs_dc_linear_low = low;
- ibs_op.ibs_dc_linear_high = high;
- rdmsr(MSR_AMD64_IBSDCPHYSAD, low, high);
- ibs_op.ibs_dc_phys_low = low;
- ibs_op.ibs_dc_phys_high = high;
+ 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_add_data64(&entry, val);
+ rdmsrl(MSR_AMD64_IBSOPDATA, val);
+ oprofile_add_data64(&entry, val);
+ rdmsrl(MSR_AMD64_IBSOPDATA2, val);
+ oprofile_add_data64(&entry, val);
+ rdmsrl(MSR_AMD64_IBSOPDATA3, val);
+ oprofile_add_data64(&entry, val);
+ rdmsrl(MSR_AMD64_IBSDCLINAD, val);
+ oprofile_add_data64(&entry, val);
+ rdmsrl(MSR_AMD64_IBSDCPHYSAD, val);
+ oprofile_add_data64(&entry, val);
+ oprofile_write_commit(&entry);
/* reenable the IRQ */
- oprofile_add_ibs_sample(regs,
- (unsigned int *)&ibs_op,
- IBS_OP_BEGIN);
- rdmsr(MSR_AMD64_IBSOPCTL, low, high);
- high = 0;
- low &= ~IBS_OP_LOW_VALID_BIT;
- low |= IBS_OP_LOW_ENABLE;
- wrmsr(MSR_AMD64_IBSOPCTL, low, high);
+ ctl = op_amd_randomize_ibs_op(ibs_op_ctl);
+ wrmsrl(MSR_AMD64_IBSOPCTL, ctl);
}
}
+}
- return 1;
+static inline void op_amd_start_ibs(void)
+{
+ u64 val;
+
+ if (!ibs_caps)
+ return;
+
+ if (ibs_config.fetch_enabled) {
+ val = (ibs_config.max_cnt_fetch >> 4) & 0xFFFF;
+ 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;
+ 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);
+ } else {
+ /*
+ * The start value is randomized with a
+ * positive offset, we need to compensate it
+ * with the half of the randomized range. Also
+ * avoid underflows.
+ */
+ ibs_op_ctl = min(ibs_op_ctl + IBS_RANDOM_MAXCNT_OFFSET,
+ 0xFFFFULL);
+ }
+ 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);
+ wrmsrl(MSR_AMD64_IBSOPCTL, val);
+ }
}
-#endif
+static void op_amd_stop_ibs(void)
+{
+ if (!ibs_caps)
+ return;
+
+ if (ibs_config.fetch_enabled)
+ /* clear max count and enable */
+ wrmsrl(MSR_AMD64_IBSFETCHCTL, 0);
+
+ if (ibs_config.op_enabled)
+ /* clear max count and enable */
+ wrmsrl(MSR_AMD64_IBSOPCTL, 0);
+}
static int op_amd_check_ctrs(struct pt_regs * const regs,
struct op_msrs const * const msrs)
{
- unsigned int low, high;
+ u64 val;
int i;
- for (i = 0 ; i < NUM_COUNTERS; ++i) {
- if (!reset_value[i])
+ for (i = 0; i < NUM_COUNTERS; ++i) {
+ int virt = op_x86_phys_to_virt(i);
+ if (!reset_value[virt])
continue;
- CTR_READ(low, high, msrs, i);
- if (CTR_OVERFLOWED(low)) {
- oprofile_add_sample(regs, i);
- CTR_WRITE(reset_value[i], msrs, i);
- }
+ rdmsrl(msrs->counters[i].addr, val);
+ /* bit is clear if overflowed: */
+ if (val & OP_CTR_OVERFLOW)
+ continue;
+ oprofile_add_sample(regs, virt);
+ wrmsrl(msrs->counters[i].addr, -(u64)reset_value[virt]);
}
-#ifdef CONFIG_OPROFILE_IBS
op_amd_handle_ibs(regs, msrs);
-#endif
/* See op_model_ppro.c */
return 1;
static void op_amd_start(struct op_msrs const * const msrs)
{
- unsigned int low, high;
+ u64 val;
int i;
- for (i = 0 ; i < NUM_COUNTERS ; ++i) {
- if (reset_value[i]) {
- CTRL_READ(low, high, msrs, i);
- CTRL_SET_ACTIVE(low);
- CTRL_WRITE(low, high, msrs, i);
- }
- }
-#ifdef CONFIG_OPROFILE_IBS
- if (ibs_allowed && ibs_config.fetch_enabled) {
- low = (ibs_config.max_cnt_fetch >> 4) & 0xFFFF;
- high = IBS_FETCH_HIGH_ENABLE;
- wrmsr(MSR_AMD64_IBSFETCHCTL, low, high);
+ for (i = 0; i < NUM_COUNTERS; ++i) {
+ if (!reset_value[op_x86_phys_to_virt(i)])
+ continue;
+ rdmsrl(msrs->controls[i].addr, val);
+ val |= ARCH_PERFMON_EVENTSEL0_ENABLE;
+ wrmsrl(msrs->controls[i].addr, val);
}
- if (ibs_allowed && ibs_config.op_enabled) {
- low = ((ibs_config.max_cnt_op >> 4) & 0xFFFF) + IBS_OP_LOW_ENABLE;
- high = 0;
- wrmsr(MSR_AMD64_IBSOPCTL, low, high);
- }
-#endif
+ op_amd_start_ibs();
}
-
static void op_amd_stop(struct op_msrs const * const msrs)
{
- unsigned int low, high;
+ u64 val;
int i;
- /* Subtle: stop on all counters to avoid race with
- * setting our pm callback */
- for (i = 0 ; i < NUM_COUNTERS ; ++i) {
- if (!reset_value[i])
+ /*
+ * Subtle: stop on all counters to avoid race with setting our
+ * pm callback
+ */
+ for (i = 0; i < NUM_COUNTERS; ++i) {
+ if (!reset_value[op_x86_phys_to_virt(i)])
continue;
- CTRL_READ(low, high, msrs, i);
- CTRL_SET_INACTIVE(low);
- CTRL_WRITE(low, high, msrs, i);
- }
-
-#ifdef CONFIG_OPROFILE_IBS
- if (ibs_allowed && ibs_config.fetch_enabled) {
- low = 0; /* clear max count and enable */
- high = 0;
- wrmsr(MSR_AMD64_IBSFETCHCTL, low, high);
+ rdmsrl(msrs->controls[i].addr, val);
+ val &= ~ARCH_PERFMON_EVENTSEL0_ENABLE;
+ wrmsrl(msrs->controls[i].addr, val);
}
- if (ibs_allowed && ibs_config.op_enabled) {
- low = 0; /* clear max count and enable */
- high = 0;
- wrmsr(MSR_AMD64_IBSOPCTL, low, high);
- }
-#endif
+ op_amd_stop_ibs();
}
static void op_amd_shutdown(struct op_msrs const * const msrs)
{
int i;
- for (i = 0 ; i < NUM_COUNTERS ; ++i) {
- if (CTR_IS_RESERVED(msrs, i))
+ for (i = 0; i < NUM_COUNTERS; ++i) {
+ if (msrs->counters[i].addr)
release_perfctr_nmi(MSR_K7_PERFCTR0 + i);
}
- for (i = 0 ; i < NUM_CONTROLS ; ++i) {
- if (CTRL_IS_RESERVED(msrs, i))
+ for (i = 0; i < NUM_CONTROLS; ++i) {
+ if (msrs->controls[i].addr)
release_evntsel_nmi(MSR_K7_EVNTSEL0 + i);
}
}
-#ifndef CONFIG_OPROFILE_IBS
-
-/* no IBS support */
-
-static int op_amd_init(struct oprofile_operations *ops)
-{
- return 0;
-}
-
-static void op_amd_exit(void) {}
-
-#else
-
static u8 ibs_eilvt_off;
static inline void apic_init_ibs_nmi_per_cpu(void *arg)
setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_FIX, 1);
}
-static int pfm_amd64_setup_eilvt(void)
+static int init_ibs_nmi(void)
{
#define IBSCTL_LVTOFFSETVAL (1 << 8)
#define IBSCTL 0x1cc
| IBSCTL_LVTOFFSETVAL);
pci_read_config_dword(cpu_cfg, IBSCTL, &value);
if (value != (ibs_eilvt_off | IBSCTL_LVTOFFSETVAL)) {
+ pci_dev_put(cpu_cfg);
printk(KERN_DEBUG "Failed to setup IBS LVT offset, "
"IBSCTL = 0x%08x", value);
return 1;
return 1;
}
-#ifdef CONFIG_NUMA
- /* Sanity check */
- /* Works only for 64bit with proper numa implementation. */
- if (nodes != num_possible_nodes()) {
- printk(KERN_DEBUG "Failed to setup CPU node(s) for IBS, "
- "found: %d, expected %d",
- nodes, num_possible_nodes());
- return 1;
- }
-#endif
return 0;
}
-/*
- * initialize the APIC for the IBS interrupts
- * if available (AMD Family10h rev B0 and later)
- */
-static void setup_ibs(void)
+/* uninitialize the APIC for the IBS interrupts if needed */
+static void clear_ibs_nmi(void)
+{
+ if (ibs_caps)
+ on_each_cpu(apic_clear_ibs_nmi_per_cpu, NULL, 1);
+}
+
+/* initialize the APIC for the IBS interrupts if available */
+static void ibs_init(void)
{
- ibs_allowed = boot_cpu_has(X86_FEATURE_IBS);
+ ibs_caps = get_ibs_caps();
- if (!ibs_allowed)
+ if (!ibs_caps)
return;
- if (pfm_amd64_setup_eilvt()) {
- ibs_allowed = 0;
+ if (init_ibs_nmi()) {
+ ibs_caps = 0;
return;
}
- printk(KERN_INFO "oprofile: AMD IBS detected\n");
+ printk(KERN_INFO "oprofile: AMD IBS detected (0x%08x)\n",
+ (unsigned)ibs_caps);
}
-
-/*
- * unitialize the APIC for the IBS interrupts if needed on AMD Family10h
- * rev B0 and later */
-static void clear_ibs_nmi(void)
+static void ibs_exit(void)
{
- if (ibs_allowed)
- on_each_cpu(apic_clear_ibs_nmi_per_cpu, NULL, 1);
+ if (!ibs_caps)
+ return;
+
+ clear_ibs_nmi();
}
-static int (*create_arch_files)(struct super_block * sb, struct dentry * root);
+static int (*create_arch_files)(struct super_block *sb, struct dentry *root);
-static int setup_ibs_files(struct super_block * sb, struct dentry * root)
+static int setup_ibs_files(struct super_block *sb, struct dentry *root)
{
- char buf[12];
struct dentry *dir;
int ret = 0;
if (ret)
return ret;
- if (!ibs_allowed)
+ if (!ibs_caps)
return ret;
/* model specific files */
ibs_config.fetch_enabled = 0;
ibs_config.max_cnt_op = 250000;
ibs_config.op_enabled = 0;
- ibs_config.dispatched_ops = 1;
- snprintf(buf, sizeof(buf), "ibs_fetch");
- dir = oprofilefs_mkdir(sb, root, buf);
- oprofilefs_create_ulong(sb, dir, "rand_enable",
- &ibs_config.rand_en);
+ ibs_config.dispatched_ops = 0;
+
+ dir = oprofilefs_mkdir(sb, root, "ibs_fetch");
oprofilefs_create_ulong(sb, dir, "enable",
- &ibs_config.fetch_enabled);
+ &ibs_config.fetch_enabled);
oprofilefs_create_ulong(sb, dir, "max_count",
- &ibs_config.max_cnt_fetch);
- snprintf(buf, sizeof(buf), "ibs_uops");
- dir = oprofilefs_mkdir(sb, root, buf);
+ &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);
+ &ibs_config.op_enabled);
oprofilefs_create_ulong(sb, dir, "max_count",
- &ibs_config.max_cnt_op);
- oprofilefs_create_ulong(sb, dir, "dispatched_ops",
- &ibs_config.dispatched_ops);
+ &ibs_config.max_cnt_op);
+ if (ibs_caps & IBS_CAPS_OPCNT)
+ oprofilefs_create_ulong(sb, dir, "dispatched_ops",
+ &ibs_config.dispatched_ops);
return 0;
}
static int op_amd_init(struct oprofile_operations *ops)
{
- setup_ibs();
+ ibs_init();
create_arch_files = ops->create_files;
ops->create_files = setup_ibs_files;
return 0;
static void op_amd_exit(void)
{
- clear_ibs_nmi();
+ ibs_exit();
}
+struct op_x86_model_spec op_amd_spec = {
+ .num_counters = NUM_COUNTERS,
+ .num_controls = NUM_CONTROLS,
+ .num_virt_counters = NUM_VIRT_COUNTERS,
+ .reserved = MSR_AMD_EVENTSEL_RESERVED,
+ .event_mask = OP_EVENT_MASK,
+ .init = op_amd_init,
+ .exit = op_amd_exit,
+ .fill_in_addresses = &op_amd_fill_in_addresses,
+ .setup_ctrs = &op_amd_setup_ctrs,
+ .check_ctrs = &op_amd_check_ctrs,
+ .start = &op_amd_start,
+ .stop = &op_amd_stop,
+ .shutdown = &op_amd_shutdown,
+#ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX
+ .switch_ctrl = &op_mux_switch_ctrl,
#endif
-
-struct op_x86_model_spec const op_amd_spec = {
- .init = op_amd_init,
- .exit = op_amd_exit,
- .num_counters = NUM_COUNTERS,
- .num_controls = NUM_CONTROLS,
- .fill_in_addresses = &op_amd_fill_in_addresses,
- .setup_ctrs = &op_amd_setup_ctrs,
- .check_ctrs = &op_amd_check_ctrs,
- .start = &op_amd_start,
- .stop = &op_amd_stop,
- .shutdown = &op_amd_shutdown
};