From 1a960b402a51d80abf54e3f8e4972374ffe5f22d Mon Sep 17 00:00:00 2001 From: Jason Yeh Date: Wed, 23 Jul 2008 23:05:53 +0200 Subject: Oprofile Multiplexing Patch This patch introduces multiplexing support for the Oprofile kernel module. It basically adds a new function pointer in oprofile_operator allowing each architecture to supply its callback to switch between different sets of event when the timer expires. Userspace tools can modify the time slice through /dev/oprofile/time_slice. It also modifies the number of counters exposed to the userspace through /dev/oprofile. For example, the number of counters for AMD CPUs are changed to 32 and multiplexed in the sets of 4. Signed-off-by: Jason Yeh Signed-off-by: Robert Richter Cc: oprofile-list Signed-off-by: Ingo Molnar --- arch/x86/oprofile/op_model_ppro.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/x86/oprofile/op_model_ppro.c') diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c index eff431f..e5811aa 100644 --- a/arch/x86/oprofile/op_model_ppro.c +++ b/arch/x86/oprofile/op_model_ppro.c @@ -183,6 +183,8 @@ static void ppro_shutdown(struct op_msrs const * const msrs) struct op_x86_model_spec const op_ppro_spec = { .num_counters = NUM_COUNTERS, .num_controls = NUM_CONTROLS, + .num_hardware_counters = NUM_COUNTERS, + .num_hardware_controls = NUM_CONTROLS, .fill_in_addresses = &ppro_fill_in_addresses, .setup_ctrs = &ppro_setup_ctrs, .check_ctrs = &ppro_check_ctrs, -- cgit v1.1 From 4c168eaf7ea39f25a45a3d8c7eebc3fedb633a1d Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Wed, 24 Sep 2008 11:08:52 +0200 Subject: Revert "Oprofile Multiplexing Patch" Reverting commit 1a960b402a51d80abf54e3f8e4972374ffe5f22d for the main branch. Multiplexing will be tracked on a separate feature branch. Conflicts: arch/x86/oprofile/nmi_int.c --- arch/x86/oprofile/op_model_ppro.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'arch/x86/oprofile/op_model_ppro.c') diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c index e5811aa..eff431f 100644 --- a/arch/x86/oprofile/op_model_ppro.c +++ b/arch/x86/oprofile/op_model_ppro.c @@ -183,8 +183,6 @@ static void ppro_shutdown(struct op_msrs const * const msrs) struct op_x86_model_spec const op_ppro_spec = { .num_counters = NUM_COUNTERS, .num_controls = NUM_CONTROLS, - .num_hardware_counters = NUM_COUNTERS, - .num_hardware_controls = NUM_CONTROLS, .fill_in_addresses = &ppro_fill_in_addresses, .setup_ctrs = &ppro_setup_ctrs, .check_ctrs = &ppro_check_ctrs, -- cgit v1.1 From b99170288421c79f0c2efa8b33e26e65f4bb7fb8 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Mon, 18 Aug 2008 14:50:31 +0200 Subject: oprofile: Implement Intel architectural perfmon support Newer Intel CPUs (Core1+) have support for architectural events described in CPUID 0xA. See the IA32 SDM Vol3b.18 for details. The advantage of this is that it can be done without knowing about the specific CPU, because the CPU describes by itself what performance events are supported. This is only a fallback because only a limited set of 6 events are supported. This allows to do profiling on Nehalem and on Atom systems (later not tested) This patch implements support for that in oprofile's Intel Family 6 profiling module. It also has the advantage of supporting an arbitary number of events now as reported by the CPU. Also allow arbitary counter widths >32bit while we're at it. Requires a patched oprofile userland to support the new architecture. v2: update for latest oprofile tree remove force_arch_perfmon Signed-off-by: Andi Kleen Signed-off-by: Robert Richter --- arch/x86/oprofile/op_model_ppro.c | 104 ++++++++++++++++++++++++++++++-------- 1 file changed, 82 insertions(+), 22 deletions(-) (limited to 'arch/x86/oprofile/op_model_ppro.c') diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c index eff431f..12e207a 100644 --- a/arch/x86/oprofile/op_model_ppro.c +++ b/arch/x86/oprofile/op_model_ppro.c @@ -1,32 +1,34 @@ /* * @file op_model_ppro.h - * pentium pro / P6 model-specific MSR operations + * Family 6 perfmon and architectural perfmon MSR operations * * @remark Copyright 2002 OProfile authors + * @remark Copyright 2008 Intel Corporation * @remark Read the file COPYING * * @author John Levon * @author Philippe Elie * @author Graydon Hoare + * @author Andi Kleen */ #include +#include #include #include #include #include +#include #include "op_x86_model.h" #include "op_counter.h" -#define NUM_COUNTERS 2 -#define NUM_CONTROLS 2 +static int num_counters = 2; +static int counter_width = 32; #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_32BIT_WRITE(l, msrs, c) \ - do {wrmsr(msrs->counters[(c)].addr, -(u32)(l), 0); } while (0) -#define CTR_OVERFLOWED(n) (!((n) & (1U<<31))) +#define CTR_OVERFLOWED(n) (!((n) & (1U<<(counter_width-1)))) #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) @@ -40,20 +42,20 @@ #define CTRL_SET_UM(val, m) (val |= (m << 8)) #define CTRL_SET_EVENT(val, e) (val |= e) -static unsigned long reset_value[NUM_COUNTERS]; +static u64 *reset_value; static void ppro_fill_in_addresses(struct op_msrs * const msrs) { int i; - for (i = 0; i < NUM_COUNTERS; i++) { + 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_CONTROLS; i++) { + for (i = 0; i < num_counters; i++) { if (reserve_evntsel_nmi(MSR_P6_EVNTSEL0 + i)) msrs->controls[i].addr = MSR_P6_EVNTSEL0 + i; else @@ -67,8 +69,22 @@ static void ppro_setup_ctrs(struct op_msrs const * const msrs) unsigned int low, high; int i; + if (!reset_value) { + reset_value = kmalloc(sizeof(unsigned) * num_counters, + GFP_ATOMIC); + if (!reset_value) + return; + } + + if (cpu_has_arch_perfmon) { + union cpuid10_eax eax; + eax.full = cpuid_eax(0xa); + if (counter_width < eax.split.bit_width) + counter_width = eax.split.bit_width; + } + /* clear all counters */ - for (i = 0 ; i < NUM_CONTROLS; ++i) { + for (i = 0 ; i < num_counters; ++i) { if (unlikely(!CTRL_IS_RESERVED(msrs, i))) continue; CTRL_READ(low, high, msrs, i); @@ -77,18 +93,18 @@ static void ppro_setup_ctrs(struct op_msrs const * const msrs) } /* avoid a false detection of ctr overflows in NMI handler */ - for (i = 0; i < NUM_COUNTERS; ++i) { + for (i = 0; i < num_counters; ++i) { if (unlikely(!CTR_IS_RESERVED(msrs, i))) continue; - CTR_32BIT_WRITE(1, msrs, i); + wrmsrl(msrs->counters[i].addr, -1LL); } /* enable active counters */ - for (i = 0; i < NUM_COUNTERS; ++i) { + for (i = 0; i < num_counters; ++i) { if ((counter_config[i].enabled) && (CTR_IS_RESERVED(msrs, i))) { reset_value[i] = counter_config[i].count; - CTR_32BIT_WRITE(counter_config[i].count, msrs, i); + wrmsrl(msrs->counters[i].addr, -reset_value[i]); CTRL_READ(low, high, msrs, i); CTRL_CLEAR(low); @@ -111,13 +127,13 @@ static int ppro_check_ctrs(struct pt_regs * const regs, unsigned int low, high; int i; - for (i = 0 ; i < NUM_COUNTERS; ++i) { + for (i = 0 ; i < num_counters; ++i) { if (!reset_value[i]) continue; CTR_READ(low, high, msrs, i); if (CTR_OVERFLOWED(low)) { oprofile_add_sample(regs, i); - CTR_32BIT_WRITE(reset_value[i], msrs, i); + wrmsrl(msrs->counters[i].addr, -reset_value[i]); } } @@ -141,7 +157,7 @@ static void ppro_start(struct op_msrs const * const msrs) unsigned int low, high; int i; - for (i = 0; i < NUM_COUNTERS; ++i) { + for (i = 0; i < num_counters; ++i) { if (reset_value[i]) { CTRL_READ(low, high, msrs, i); CTRL_SET_ACTIVE(low); @@ -156,7 +172,7 @@ static void ppro_stop(struct op_msrs const * const msrs) unsigned int low, high; int i; - for (i = 0; i < NUM_COUNTERS; ++i) { + for (i = 0; i < num_counters; ++i) { if (!reset_value[i]) continue; CTRL_READ(low, high, msrs, i); @@ -169,21 +185,65 @@ static void ppro_shutdown(struct op_msrs const * const msrs) { int i; - for (i = 0 ; i < NUM_COUNTERS ; ++i) { + for (i = 0 ; i < num_counters ; ++i) { if (CTR_IS_RESERVED(msrs, i)) release_perfctr_nmi(MSR_P6_PERFCTR0 + i); } - for (i = 0 ; i < NUM_CONTROLS ; ++i) { + for (i = 0 ; i < num_counters ; ++i) { if (CTRL_IS_RESERVED(msrs, i)) release_evntsel_nmi(MSR_P6_EVNTSEL0 + i); } + if (reset_value) { + kfree(reset_value); + reset_value = NULL; + } } struct op_x86_model_spec const op_ppro_spec = { - .num_counters = NUM_COUNTERS, - .num_controls = NUM_CONTROLS, + .num_counters = 2, + .num_controls = 2, + .fill_in_addresses = &ppro_fill_in_addresses, + .setup_ctrs = &ppro_setup_ctrs, + .check_ctrs = &ppro_check_ctrs, + .start = &ppro_start, + .stop = &ppro_stop, + .shutdown = &ppro_shutdown +}; + +/* + * Architectural performance monitoring. + * + * Newer Intel CPUs (Core1+) have support for architectural + * events described in CPUID 0xA. See the IA32 SDM Vol3b.18 for details. + * The advantage of this is that it can be done without knowing about + * the specific CPU. + */ + +void arch_perfmon_setup_counters(void) +{ + union cpuid10_eax eax; + + eax.full = cpuid_eax(0xa); + + /* Workaround for BIOS bugs in 6/15. Taken from perfmon2 */ + if (eax.split.version_id == 0 && current_cpu_data.x86 == 6 && + current_cpu_data.x86_model == 15) { + eax.split.version_id = 2; + eax.split.num_counters = 2; + eax.split.bit_width = 40; + } + + num_counters = eax.split.num_counters; + + op_arch_perfmon_spec.num_counters = num_counters; + op_arch_perfmon_spec.num_controls = num_counters; +} + +struct op_x86_model_spec op_arch_perfmon_spec = { + /* num_counters/num_controls filled in at runtime */ .fill_in_addresses = &ppro_fill_in_addresses, + /* user space does the cpuid check for available events */ .setup_ctrs = &ppro_setup_ctrs, .check_ctrs = &ppro_check_ctrs, .start = &ppro_start, -- cgit v1.1 From 59512900baab03c5629f2ff5efad1d5d4e682ece Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Mon, 29 Sep 2008 22:23:33 +0200 Subject: oprofile: discover counters for op ppro too Discover number of counters for all family 6 models even when not in arch perfmon mode. Signed-off-by: Andi Kleen Signed-off-by: Robert Richter --- arch/x86/oprofile/op_model_ppro.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'arch/x86/oprofile/op_model_ppro.c') diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c index 12e207a..f5a2268 100644 --- a/arch/x86/oprofile/op_model_ppro.c +++ b/arch/x86/oprofile/op_model_ppro.c @@ -200,9 +200,9 @@ static void ppro_shutdown(struct op_msrs const * const msrs) } -struct op_x86_model_spec const op_ppro_spec = { - .num_counters = 2, - .num_controls = 2, +struct op_x86_model_spec op_ppro_spec = { + .num_counters = 2, /* can be overriden */ + .num_controls = 2, /* dito */ .fill_in_addresses = &ppro_fill_in_addresses, .setup_ctrs = &ppro_setup_ctrs, .check_ctrs = &ppro_check_ctrs, @@ -238,6 +238,8 @@ void arch_perfmon_setup_counters(void) op_arch_perfmon_spec.num_counters = num_counters; op_arch_perfmon_spec.num_controls = num_counters; + op_ppro_spec.num_counters = num_counters; + op_ppro_spec.num_controls = num_counters; } struct op_x86_model_spec op_arch_perfmon_spec = { -- cgit v1.1 From c92960fccb9f32a1d6110f6dcfe483ed96c62beb Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Fri, 5 Sep 2008 17:12:36 +0200 Subject: oprofile: whitespace fixes Signed-off-by: Robert Richter --- arch/x86/oprofile/op_model_ppro.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'arch/x86/oprofile/op_model_ppro.c') diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c index eff431f..c665bac 100644 --- a/arch/x86/oprofile/op_model_ppro.c +++ b/arch/x86/oprofile/op_model_ppro.c @@ -181,12 +181,12 @@ static void ppro_shutdown(struct op_msrs const * const msrs) struct op_x86_model_spec const op_ppro_spec = { - .num_counters = NUM_COUNTERS, - .num_controls = NUM_CONTROLS, - .fill_in_addresses = &ppro_fill_in_addresses, - .setup_ctrs = &ppro_setup_ctrs, - .check_ctrs = &ppro_check_ctrs, - .start = &ppro_start, - .stop = &ppro_stop, - .shutdown = &ppro_shutdown + .num_counters = NUM_COUNTERS, + .num_controls = NUM_CONTROLS, + .fill_in_addresses = &ppro_fill_in_addresses, + .setup_ctrs = &ppro_setup_ctrs, + .check_ctrs = &ppro_check_ctrs, + .start = &ppro_start, + .stop = &ppro_stop, + .shutdown = &ppro_shutdown }; -- cgit v1.1