Merge branch 'oprofile-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'oprofile-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
oprofile/x86: fix msr access to reserved counters
oprofile/x86: use kzalloc() instead of kmalloc()
oprofile/x86: fix perfctr nmi reservation for mulitplexing
oprofile/x86: add comment to counter-in-use warning
oprofile/x86: warn user if a counter is already active
oprofile/x86: implement randomization for IBS periodic op counter
oprofile/x86: implement lsfr pseudo-random number generator for IBS
oprofile/x86: implement IBS cpuid feature detection
oprofile/x86: remove node check in AMD IBS initialization
oprofile/x86: remove OPROFILE_IBS config option
oprofile: remove EXPERIMENTAL from the config option description
oprofile: remove tracing build dependency
diff --git a/arch/Kconfig b/arch/Kconfig
index 9d055b4..06a1372 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -3,11 +3,9 @@
#
config OPROFILE
- tristate "OProfile system profiling (EXPERIMENTAL)"
+ tristate "OProfile system profiling"
depends on PROFILING
depends on HAVE_OPROFILE
- depends on TRACING_SUPPORT
- select TRACING
select RING_BUFFER
select RING_BUFFER_ALLOW_SWAP
help
@@ -17,20 +15,6 @@
If unsure, say N.
-config OPROFILE_IBS
- bool "OProfile AMD IBS support (EXPERIMENTAL)"
- default n
- depends on OPROFILE && SMP && X86
- help
- Instruction-Based Sampling (IBS) is a new profiling
- technique that provides rich, precise program performance
- information. IBS is introduced by AMD Family10h processors
- (AMD Opteron Quad-Core processor "Barcelona") to overcome
- the limitations of conventional performance counter
- sampling.
-
- If unsure, say N.
-
config OPROFILE_EVENT_MULTIPLEX
bool "OProfile multiplexing support (EXPERIMENTAL)"
default n
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 3347f69..2c505ee 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -159,7 +159,7 @@
for_each_possible_cpu(i) {
per_cpu(cpu_msrs, i).multiplex =
- kmalloc(multiplex_size, GFP_KERNEL);
+ kzalloc(multiplex_size, GFP_KERNEL);
if (!per_cpu(cpu_msrs, i).multiplex)
return 0;
}
@@ -179,7 +179,6 @@
if (counter_config[i].enabled) {
multiplex[i].saved = -(u64)counter_config[i].count;
} else {
- multiplex[i].addr = 0;
multiplex[i].saved = 0;
}
}
@@ -189,25 +188,27 @@
static void nmi_cpu_save_mpx_registers(struct op_msrs *msrs)
{
+ struct op_msr *counters = msrs->counters;
struct op_msr *multiplex = msrs->multiplex;
int i;
for (i = 0; i < model->num_counters; ++i) {
int virt = op_x86_phys_to_virt(i);
- if (multiplex[virt].addr)
- rdmsrl(multiplex[virt].addr, multiplex[virt].saved);
+ if (counters[i].addr)
+ rdmsrl(counters[i].addr, multiplex[virt].saved);
}
}
static void nmi_cpu_restore_mpx_registers(struct op_msrs *msrs)
{
+ struct op_msr *counters = msrs->counters;
struct op_msr *multiplex = msrs->multiplex;
int i;
for (i = 0; i < model->num_counters; ++i) {
int virt = op_x86_phys_to_virt(i);
- if (multiplex[virt].addr)
- wrmsrl(multiplex[virt].addr, multiplex[virt].saved);
+ if (counters[i].addr)
+ wrmsrl(counters[i].addr, multiplex[virt].saved);
}
}
@@ -303,11 +304,11 @@
int i;
for_each_possible_cpu(i) {
- per_cpu(cpu_msrs, i).counters = kmalloc(counters_size,
+ per_cpu(cpu_msrs, i).counters = kzalloc(counters_size,
GFP_KERNEL);
if (!per_cpu(cpu_msrs, i).counters)
return 0;
- per_cpu(cpu_msrs, i).controls = kmalloc(controls_size,
+ per_cpu(cpu_msrs, i).controls = kzalloc(controls_size,
GFP_KERNEL);
if (!per_cpu(cpu_msrs, i).controls)
return 0;
diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c
index 39686c2..6a58256 100644
--- a/arch/x86/oprofile/op_model_amd.c
+++ b/arch/x86/oprofile/op_model_amd.c
@@ -22,6 +22,9 @@
#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"
@@ -43,15 +46,13 @@
static unsigned long reset_value[NUM_VIRT_COUNTERS];
-#ifdef CONFIG_OPROFILE_IBS
-
/* 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_MASK 0xFFFF0000ULL
-/*IbsOpCtl bits */
+/* IbsOpCtl bits */
#define IBS_OP_CNT_CTL (1ULL<<19)
#define IBS_OP_VAL (1ULL<<18)
#define IBS_OP_ENABLE (1ULL<<17)
@@ -59,7 +60,7 @@
#define IBS_FETCH_SIZE 6
#define IBS_OP_SIZE 12
-static int has_ibs; /* AMD Family10h and later */
+static u32 ibs_caps;
struct op_ibs_config {
unsigned long op_enabled;
@@ -71,24 +72,52 @@
};
static struct op_ibs_config ibs_config;
+static u64 ibs_op_ctl;
-#endif
+/*
+ * 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_fill_in_addresses(struct op_msrs * const msrs)
-{
- int i;
-
- for (i = 0; i < NUM_VIRT_COUNTERS; i++) {
- int hw_counter = op_x86_virt_to_phys(i);
- if (reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i))
- msrs->multiplex[i].addr = MSR_K7_PERFCTR0 + hw_counter;
- else
- msrs->multiplex[i].addr = 0;
- }
-}
-
static void op_mux_switch_ctrl(struct op_x86_model_spec const *model,
struct op_msrs const * const msrs)
{
@@ -98,7 +127,7 @@
/* enable active counters */
for (i = 0; i < NUM_COUNTERS; ++i) {
int virt = op_x86_phys_to_virt(i);
- if (!counter_config[virt].enabled)
+ if (!reset_value[virt])
continue;
rdmsrl(msrs->controls[i].addr, val);
val &= model->reserved;
@@ -107,10 +136,6 @@
}
}
-#else
-
-static inline void op_mux_fill_in_addresses(struct op_msrs * const msrs) { }
-
#endif
/* functions for op_amd_spec */
@@ -122,18 +147,12 @@
for (i = 0; i < NUM_COUNTERS; i++) {
if (reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i))
msrs->counters[i].addr = MSR_K7_PERFCTR0 + i;
- else
- msrs->counters[i].addr = 0;
}
for (i = 0; i < NUM_CONTROLS; i++) {
if (reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i))
msrs->controls[i].addr = MSR_K7_EVNTSEL0 + i;
- else
- msrs->controls[i].addr = 0;
}
-
- op_mux_fill_in_addresses(msrs);
}
static void op_amd_setup_ctrs(struct op_x86_model_spec const *model,
@@ -144,7 +163,8 @@
/* setup reset_value */
for (i = 0; i < NUM_VIRT_COUNTERS; ++i) {
- if (counter_config[i].enabled)
+ if (counter_config[i].enabled
+ && msrs->counters[op_x86_virt_to_phys(i)].addr)
reset_value[i] = counter_config[i].count;
else
reset_value[i] = 0;
@@ -152,9 +172,18 @@
/* clear all counters */
for (i = 0; i < NUM_CONTROLS; ++i) {
- if (unlikely(!msrs->controls[i].addr))
+ 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;
+ }
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);
}
@@ -169,9 +198,7 @@
/* enable active counters */
for (i = 0; i < NUM_COUNTERS; ++i) {
int virt = op_x86_phys_to_virt(i);
- if (!counter_config[virt].enabled)
- continue;
- if (!msrs->counters[i].addr)
+ if (!reset_value[virt])
continue;
/* setup counter registers */
@@ -185,7 +212,60 @@
}
}
-#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 void
op_amd_handle_ibs(struct pt_regs * const regs,
@@ -194,7 +274,7 @@
u64 val, ctl;
struct op_entry entry;
- if (!has_ibs)
+ if (!ibs_caps)
return;
if (ibs_config.fetch_enabled) {
@@ -236,8 +316,7 @@
oprofile_write_commit(&entry);
/* reenable the IRQ */
- ctl &= ~IBS_OP_VAL & 0xFFFFFFFF;
- ctl |= IBS_OP_ENABLE;
+ ctl = op_amd_randomize_ibs_op(ibs_op_ctl);
wrmsrl(MSR_AMD64_IBSOPCTL, ctl);
}
}
@@ -246,41 +325,57 @@
static inline void op_amd_start_ibs(void)
{
u64 val;
- if (has_ibs && ibs_config.fetch_enabled) {
+
+ 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 (has_ibs && ibs_config.op_enabled) {
- val = (ibs_config.max_cnt_op >> 4) & 0xFFFF;
- val |= ibs_config.dispatched_ops ? IBS_OP_CNT_CTL : 0;
- val |= IBS_OP_ENABLE;
+ 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);
}
}
static void op_amd_stop_ibs(void)
{
- if (has_ibs && ibs_config.fetch_enabled)
+ if (!ibs_caps)
+ return;
+
+ if (ibs_config.fetch_enabled)
/* clear max count and enable */
wrmsrl(MSR_AMD64_IBSFETCHCTL, 0);
- if (has_ibs && ibs_config.op_enabled)
+ if (ibs_config.op_enabled)
/* clear max count and enable */
wrmsrl(MSR_AMD64_IBSOPCTL, 0);
}
-#else
-
-static inline void op_amd_handle_ibs(struct pt_regs * const regs,
- struct op_msrs const * const msrs) { }
-static inline void op_amd_start_ibs(void) { }
-static inline void op_amd_stop_ibs(void) { }
-
-#endif
-
static int op_amd_check_ctrs(struct pt_regs * const regs,
struct op_msrs const * const msrs)
{
@@ -355,8 +450,6 @@
}
}
-#ifdef CONFIG_OPROFILE_IBS
-
static u8 ibs_eilvt_off;
static inline void apic_init_ibs_nmi_per_cpu(void *arg)
@@ -405,45 +498,36 @@
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;
}
/* uninitialize the APIC for the IBS interrupts if needed */
static void clear_ibs_nmi(void)
{
- if (has_ibs)
+ 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)
{
- has_ibs = boot_cpu_has(X86_FEATURE_IBS);
+ ibs_caps = get_ibs_caps();
- if (!has_ibs)
+ if (!ibs_caps)
return;
if (init_ibs_nmi()) {
- has_ibs = 0;
+ 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);
}
static void ibs_exit(void)
{
- if (!has_ibs)
+ if (!ibs_caps)
return;
clear_ibs_nmi();
@@ -463,7 +547,7 @@
if (ret)
return ret;
- if (!has_ibs)
+ if (!ibs_caps)
return ret;
/* model specific files */
@@ -473,7 +557,7 @@
ibs_config.fetch_enabled = 0;
ibs_config.max_cnt_op = 250000;
ibs_config.op_enabled = 0;
- ibs_config.dispatched_ops = 1;
+ ibs_config.dispatched_ops = 0;
dir = oprofilefs_mkdir(sb, root, "ibs_fetch");
oprofilefs_create_ulong(sb, dir, "enable",
@@ -488,8 +572,9 @@
&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);
+ if (ibs_caps & IBS_CAPS_OPCNT)
+ oprofilefs_create_ulong(sb, dir, "dispatched_ops",
+ &ibs_config.dispatched_ops);
return 0;
}
@@ -507,19 +592,6 @@
ibs_exit();
}
-#else
-
-/* no IBS support */
-
-static int op_amd_init(struct oprofile_operations *ops)
-{
- return 0;
-}
-
-static void op_amd_exit(void) {}
-
-#endif /* CONFIG_OPROFILE_IBS */
-
struct op_x86_model_spec op_amd_spec = {
.num_counters = NUM_COUNTERS,
.num_controls = NUM_CONTROLS,
diff --git a/arch/x86/oprofile/op_model_p4.c b/arch/x86/oprofile/op_model_p4.c
index ac6b354..e6a160a 100644
--- a/arch/x86/oprofile/op_model_p4.c
+++ b/arch/x86/oprofile/op_model_p4.c
@@ -394,12 +394,6 @@
setup_num_counters();
stag = get_stagger();
- /* initialize some registers */
- for (i = 0; i < num_counters; ++i)
- msrs->counters[i].addr = 0;
- for (i = 0; i < num_controls; ++i)
- msrs->controls[i].addr = 0;
-
/* the counter & cccr registers we pay attention to */
for (i = 0; i < num_counters; ++i) {
addr = p4_counters[VIRT_CTR(stag, i)].counter_address;
diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c
index 8eb0587..5d1727b 100644
--- a/arch/x86/oprofile/op_model_ppro.c
+++ b/arch/x86/oprofile/op_model_ppro.c
@@ -37,15 +37,11 @@
for (i = 0; i < num_counters; i++) {
if (reserve_perfctr_nmi(MSR_P6_PERFCTR0 + i))
msrs->counters[i].addr = MSR_P6_PERFCTR0 + i;
- else
- msrs->counters[i].addr = 0;
}
for (i = 0; i < num_counters; i++) {
if (reserve_evntsel_nmi(MSR_P6_EVNTSEL0 + i))
msrs->controls[i].addr = MSR_P6_EVNTSEL0 + i;
- else
- msrs->controls[i].addr = 0;
}
}
@@ -57,7 +53,7 @@
int i;
if (!reset_value) {
- reset_value = kmalloc(sizeof(reset_value[0]) * num_counters,
+ reset_value = kzalloc(sizeof(reset_value[0]) * num_counters,
GFP_ATOMIC);
if (!reset_value)
return;
@@ -82,9 +78,18 @@
/* clear all counters */
for (i = 0; i < num_counters; ++i) {
- if (unlikely(!msrs->controls[i].addr))
+ 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;
+ }
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);
}
diff --git a/arch/x86/oprofile/op_x86_model.h b/arch/x86/oprofile/op_x86_model.h
index 7b8e75d..ff82a75 100644
--- a/arch/x86/oprofile/op_x86_model.h
+++ b/arch/x86/oprofile/op_x86_model.h
@@ -57,6 +57,26 @@
struct op_counter_config;
+static inline void op_x86_warn_in_use(int counter)
+{
+ /*
+ * The warning indicates an already running counter. If
+ * oprofile doesn't collect data, then try using a different
+ * performance counter on your platform to monitor the desired
+ * event. Delete counter #%d from the desired event by editing
+ * the /usr/share/oprofile/%s/<cpu>/events file. If the event
+ * cannot be monitored by any other counter, contact your
+ * hardware or BIOS vendor.
+ */
+ pr_warning("oprofile: counter #%d on cpu #%d may already be used\n",
+ counter, smp_processor_id());
+}
+
+static inline void op_x86_warn_reserved(int counter)
+{
+ pr_warning("oprofile: counter #%d is already reserved\n", counter);
+}
+
extern u64 op_x86_get_ctrl(struct op_x86_model_spec const *model,
struct op_counter_config *counter_config);
extern int op_x86_phys_to_virt(int phys);
diff --git a/init/Kconfig b/init/Kconfig
index d038a57..207ae29 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1128,7 +1128,7 @@
See Documentation/nommu-mmap.txt for more information.
config PROFILING
- bool "Profiling support (EXPERIMENTAL)"
+ bool "Profiling support"
help
Say Y here to enable the extended profiling support mechanisms used
by profilers such as OProfile.
