perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
#ifdef CONFIG_CPU_SUP_INTEL
|
|
|
|
|
|
|
|
/* The maximal number of PEBS events: */
|
|
|
|
#define MAX_PEBS_EVENTS 4
|
|
|
|
|
|
|
|
/* The size of a BTS record in bytes: */
|
|
|
|
#define BTS_RECORD_SIZE 24
|
|
|
|
|
|
|
|
#define BTS_BUFFER_SIZE (PAGE_SIZE << 4)
|
|
|
|
#define PEBS_BUFFER_SIZE PAGE_SIZE
|
|
|
|
|
|
|
|
/*
|
|
|
|
* pebs_record_32 for p4 and core not supported
|
|
|
|
|
|
|
|
struct pebs_record_32 {
|
|
|
|
u32 flags, ip;
|
|
|
|
u32 ax, bc, cx, dx;
|
|
|
|
u32 si, di, bp, sp;
|
|
|
|
};
|
|
|
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
struct pebs_record_core {
|
|
|
|
u64 flags, ip;
|
|
|
|
u64 ax, bx, cx, dx;
|
|
|
|
u64 si, di, bp, sp;
|
|
|
|
u64 r8, r9, r10, r11;
|
|
|
|
u64 r12, r13, r14, r15;
|
|
|
|
};
|
|
|
|
|
|
|
|
struct pebs_record_nhm {
|
|
|
|
u64 flags, ip;
|
|
|
|
u64 ax, bx, cx, dx;
|
|
|
|
u64 si, di, bp, sp;
|
|
|
|
u64 r8, r9, r10, r11;
|
|
|
|
u64 r12, r13, r14, r15;
|
|
|
|
u64 status, dla, dse, lat;
|
|
|
|
};
|
|
|
|
|
|
|
|
/*
|
|
|
|
* A debug store configuration.
|
|
|
|
*
|
|
|
|
* We only support architectures that use 64bit fields.
|
|
|
|
*/
|
|
|
|
struct debug_store {
|
|
|
|
u64 bts_buffer_base;
|
|
|
|
u64 bts_index;
|
|
|
|
u64 bts_absolute_maximum;
|
|
|
|
u64 bts_interrupt_threshold;
|
|
|
|
u64 pebs_buffer_base;
|
|
|
|
u64 pebs_index;
|
|
|
|
u64 pebs_absolute_maximum;
|
|
|
|
u64 pebs_interrupt_threshold;
|
|
|
|
u64 pebs_event_reset[MAX_PEBS_EVENTS];
|
|
|
|
};
|
|
|
|
|
|
|
|
static void init_debug_store_on_cpu(int cpu)
|
|
|
|
{
|
|
|
|
struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
|
|
|
|
|
|
|
|
if (!ds)
|
|
|
|
return;
|
|
|
|
|
|
|
|
wrmsr_on_cpu(cpu, MSR_IA32_DS_AREA,
|
|
|
|
(u32)((u64)(unsigned long)ds),
|
|
|
|
(u32)((u64)(unsigned long)ds >> 32));
|
|
|
|
}
|
|
|
|
|
|
|
|
static void fini_debug_store_on_cpu(int cpu)
|
|
|
|
{
|
|
|
|
if (!per_cpu(cpu_hw_events, cpu).ds)
|
|
|
|
return;
|
|
|
|
|
|
|
|
wrmsr_on_cpu(cpu, MSR_IA32_DS_AREA, 0, 0);
|
|
|
|
}
|
|
|
|
|
2010-10-19 12:15:04 +00:00
|
|
|
static int alloc_pebs_buffer(int cpu)
|
|
|
|
{
|
|
|
|
struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
|
2010-10-19 12:55:33 +00:00
|
|
|
int node = cpu_to_node(cpu);
|
2010-10-19 12:15:04 +00:00
|
|
|
int max, thresh = 1; /* always use a single PEBS record */
|
|
|
|
void *buffer;
|
|
|
|
|
|
|
|
if (!x86_pmu.pebs)
|
|
|
|
return 0;
|
|
|
|
|
2010-10-19 12:55:33 +00:00
|
|
|
buffer = kmalloc_node(PEBS_BUFFER_SIZE, GFP_KERNEL | __GFP_ZERO, node);
|
2010-10-19 12:15:04 +00:00
|
|
|
if (unlikely(!buffer))
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
max = PEBS_BUFFER_SIZE / x86_pmu.pebs_record_size;
|
|
|
|
|
|
|
|
ds->pebs_buffer_base = (u64)(unsigned long)buffer;
|
|
|
|
ds->pebs_index = ds->pebs_buffer_base;
|
|
|
|
ds->pebs_absolute_maximum = ds->pebs_buffer_base +
|
|
|
|
max * x86_pmu.pebs_record_size;
|
|
|
|
|
|
|
|
ds->pebs_interrupt_threshold = ds->pebs_buffer_base +
|
|
|
|
thresh * x86_pmu.pebs_record_size;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2010-10-19 12:08:29 +00:00
|
|
|
static void release_pebs_buffer(int cpu)
|
|
|
|
{
|
|
|
|
struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
|
|
|
|
|
|
|
|
if (!ds || !x86_pmu.pebs)
|
|
|
|
return;
|
|
|
|
|
|
|
|
kfree((void *)(unsigned long)ds->pebs_buffer_base);
|
|
|
|
ds->pebs_buffer_base = 0;
|
|
|
|
}
|
|
|
|
|
2010-10-19 12:15:04 +00:00
|
|
|
static int alloc_bts_buffer(int cpu)
|
|
|
|
{
|
|
|
|
struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
|
2010-10-19 12:55:33 +00:00
|
|
|
int node = cpu_to_node(cpu);
|
2010-10-19 12:15:04 +00:00
|
|
|
int max, thresh;
|
|
|
|
void *buffer;
|
|
|
|
|
|
|
|
if (!x86_pmu.bts)
|
|
|
|
return 0;
|
|
|
|
|
2010-10-19 12:55:33 +00:00
|
|
|
buffer = kmalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_ZERO, node);
|
2010-10-19 12:15:04 +00:00
|
|
|
if (unlikely(!buffer))
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
max = BTS_BUFFER_SIZE / BTS_RECORD_SIZE;
|
|
|
|
thresh = max / 16;
|
|
|
|
|
|
|
|
ds->bts_buffer_base = (u64)(unsigned long)buffer;
|
|
|
|
ds->bts_index = ds->bts_buffer_base;
|
|
|
|
ds->bts_absolute_maximum = ds->bts_buffer_base +
|
|
|
|
max * BTS_RECORD_SIZE;
|
|
|
|
ds->bts_interrupt_threshold = ds->bts_absolute_maximum -
|
|
|
|
thresh * BTS_RECORD_SIZE;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2010-10-19 12:08:29 +00:00
|
|
|
static void release_bts_buffer(int cpu)
|
|
|
|
{
|
|
|
|
struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
|
|
|
|
|
|
|
|
if (!ds || !x86_pmu.bts)
|
|
|
|
return;
|
|
|
|
|
|
|
|
kfree((void *)(unsigned long)ds->bts_buffer_base);
|
|
|
|
ds->bts_buffer_base = 0;
|
|
|
|
}
|
|
|
|
|
2010-10-19 12:37:23 +00:00
|
|
|
static int alloc_ds_buffer(int cpu)
|
|
|
|
{
|
2010-10-19 12:55:33 +00:00
|
|
|
int node = cpu_to_node(cpu);
|
2010-10-19 12:37:23 +00:00
|
|
|
struct debug_store *ds;
|
|
|
|
|
2010-10-19 12:55:33 +00:00
|
|
|
ds = kmalloc_node(sizeof(*ds), GFP_KERNEL | __GFP_ZERO, node);
|
2010-10-19 12:37:23 +00:00
|
|
|
if (unlikely(!ds))
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
per_cpu(cpu_hw_events, cpu).ds = ds;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void release_ds_buffer(int cpu)
|
|
|
|
{
|
|
|
|
struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
|
|
|
|
|
|
|
|
if (!ds)
|
|
|
|
return;
|
|
|
|
|
|
|
|
per_cpu(cpu_hw_events, cpu).ds = NULL;
|
|
|
|
kfree(ds);
|
|
|
|
}
|
|
|
|
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
static void release_ds_buffers(void)
|
|
|
|
{
|
|
|
|
int cpu;
|
|
|
|
|
|
|
|
if (!x86_pmu.bts && !x86_pmu.pebs)
|
|
|
|
return;
|
|
|
|
|
|
|
|
get_online_cpus();
|
|
|
|
for_each_online_cpu(cpu)
|
|
|
|
fini_debug_store_on_cpu(cpu);
|
|
|
|
|
|
|
|
for_each_possible_cpu(cpu) {
|
2010-10-19 12:08:29 +00:00
|
|
|
release_pebs_buffer(cpu);
|
|
|
|
release_bts_buffer(cpu);
|
2010-10-19 12:37:23 +00:00
|
|
|
release_ds_buffer(cpu);
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
}
|
|
|
|
put_online_cpus();
|
|
|
|
}
|
|
|
|
|
2010-10-19 12:50:02 +00:00
|
|
|
static void reserve_ds_buffers(void)
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
{
|
2010-10-19 12:22:50 +00:00
|
|
|
int bts_err = 0, pebs_err = 0;
|
|
|
|
int cpu;
|
|
|
|
|
|
|
|
x86_pmu.bts_active = 0;
|
|
|
|
x86_pmu.pebs_active = 0;
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
|
|
|
|
if (!x86_pmu.bts && !x86_pmu.pebs)
|
2010-10-19 12:50:02 +00:00
|
|
|
return;
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
|
2010-10-19 12:22:50 +00:00
|
|
|
if (!x86_pmu.bts)
|
|
|
|
bts_err = 1;
|
|
|
|
|
|
|
|
if (!x86_pmu.pebs)
|
|
|
|
pebs_err = 1;
|
|
|
|
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
get_online_cpus();
|
|
|
|
|
|
|
|
for_each_possible_cpu(cpu) {
|
2010-10-19 12:22:50 +00:00
|
|
|
if (alloc_ds_buffer(cpu)) {
|
|
|
|
bts_err = 1;
|
|
|
|
pebs_err = 1;
|
|
|
|
}
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
|
2010-10-19 12:22:50 +00:00
|
|
|
if (!bts_err && alloc_bts_buffer(cpu))
|
|
|
|
bts_err = 1;
|
|
|
|
|
|
|
|
if (!pebs_err && alloc_pebs_buffer(cpu))
|
|
|
|
pebs_err = 1;
|
2010-10-19 12:15:04 +00:00
|
|
|
|
2010-10-19 12:22:50 +00:00
|
|
|
if (bts_err && pebs_err)
|
2010-10-19 12:15:04 +00:00
|
|
|
break;
|
2010-10-19 12:22:50 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
if (bts_err) {
|
|
|
|
for_each_possible_cpu(cpu)
|
|
|
|
release_bts_buffer(cpu);
|
|
|
|
}
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
|
2010-10-19 12:22:50 +00:00
|
|
|
if (pebs_err) {
|
|
|
|
for_each_possible_cpu(cpu)
|
|
|
|
release_pebs_buffer(cpu);
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
}
|
|
|
|
|
2010-10-19 12:22:50 +00:00
|
|
|
if (bts_err && pebs_err) {
|
|
|
|
for_each_possible_cpu(cpu)
|
|
|
|
release_ds_buffer(cpu);
|
|
|
|
} else {
|
|
|
|
if (x86_pmu.bts && !bts_err)
|
|
|
|
x86_pmu.bts_active = 1;
|
|
|
|
|
|
|
|
if (x86_pmu.pebs && !pebs_err)
|
|
|
|
x86_pmu.pebs_active = 1;
|
|
|
|
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
for_each_online_cpu(cpu)
|
|
|
|
init_debug_store_on_cpu(cpu);
|
|
|
|
}
|
|
|
|
|
|
|
|
put_online_cpus();
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* BTS
|
|
|
|
*/
|
|
|
|
|
|
|
|
static struct event_constraint bts_constraint =
|
|
|
|
EVENT_CONSTRAINT(0, 1ULL << X86_PMC_IDX_FIXED_BTS, 0);
|
|
|
|
|
|
|
|
static void intel_pmu_enable_bts(u64 config)
|
|
|
|
{
|
|
|
|
unsigned long debugctlmsr;
|
|
|
|
|
|
|
|
debugctlmsr = get_debugctlmsr();
|
|
|
|
|
2010-03-25 13:51:49 +00:00
|
|
|
debugctlmsr |= DEBUGCTLMSR_TR;
|
|
|
|
debugctlmsr |= DEBUGCTLMSR_BTS;
|
|
|
|
debugctlmsr |= DEBUGCTLMSR_BTINT;
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
|
|
|
|
if (!(config & ARCH_PERFMON_EVENTSEL_OS))
|
2010-03-25 13:51:49 +00:00
|
|
|
debugctlmsr |= DEBUGCTLMSR_BTS_OFF_OS;
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
|
|
|
|
if (!(config & ARCH_PERFMON_EVENTSEL_USR))
|
2010-03-25 13:51:49 +00:00
|
|
|
debugctlmsr |= DEBUGCTLMSR_BTS_OFF_USR;
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
|
|
|
|
update_debugctlmsr(debugctlmsr);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void intel_pmu_disable_bts(void)
|
|
|
|
{
|
|
|
|
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
|
|
|
|
unsigned long debugctlmsr;
|
|
|
|
|
|
|
|
if (!cpuc->ds)
|
|
|
|
return;
|
|
|
|
|
|
|
|
debugctlmsr = get_debugctlmsr();
|
|
|
|
|
|
|
|
debugctlmsr &=
|
2010-03-25 13:51:49 +00:00
|
|
|
~(DEBUGCTLMSR_TR | DEBUGCTLMSR_BTS | DEBUGCTLMSR_BTINT |
|
|
|
|
DEBUGCTLMSR_BTS_OFF_OS | DEBUGCTLMSR_BTS_OFF_USR);
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
|
|
|
|
update_debugctlmsr(debugctlmsr);
|
|
|
|
}
|
|
|
|
|
2010-09-10 11:28:01 +00:00
|
|
|
static int intel_pmu_drain_bts_buffer(void)
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
{
|
|
|
|
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
|
|
|
|
struct debug_store *ds = cpuc->ds;
|
|
|
|
struct bts_record {
|
|
|
|
u64 from;
|
|
|
|
u64 to;
|
|
|
|
u64 flags;
|
|
|
|
};
|
|
|
|
struct perf_event *event = cpuc->events[X86_PMC_IDX_FIXED_BTS];
|
|
|
|
struct bts_record *at, *top;
|
|
|
|
struct perf_output_handle handle;
|
|
|
|
struct perf_event_header header;
|
|
|
|
struct perf_sample_data data;
|
|
|
|
struct pt_regs regs;
|
|
|
|
|
|
|
|
if (!event)
|
2010-09-10 11:28:01 +00:00
|
|
|
return 0;
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
|
2010-10-19 12:22:50 +00:00
|
|
|
if (!x86_pmu.bts_active)
|
2010-09-10 11:28:01 +00:00
|
|
|
return 0;
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
|
|
|
|
at = (struct bts_record *)(unsigned long)ds->bts_buffer_base;
|
|
|
|
top = (struct bts_record *)(unsigned long)ds->bts_index;
|
|
|
|
|
|
|
|
if (top <= at)
|
2010-09-10 11:28:01 +00:00
|
|
|
return 0;
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
|
|
|
|
ds->bts_index = ds->bts_buffer_base;
|
|
|
|
|
|
|
|
perf_sample_data_init(&data, 0);
|
|
|
|
data.period = event->hw.last_period;
|
|
|
|
regs.ip = 0;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Prepare a generic sample, i.e. fill in the invariant fields.
|
|
|
|
* We will overwrite the from and to address before we output
|
|
|
|
* the sample.
|
|
|
|
*/
|
|
|
|
perf_prepare_sample(&header, &data, event, ®s);
|
|
|
|
|
|
|
|
if (perf_output_begin(&handle, event, header.size * (top - at), 1, 1))
|
2010-09-10 11:28:01 +00:00
|
|
|
return 1;
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
|
|
|
|
for (; at < top; at++) {
|
|
|
|
data.ip = at->from;
|
|
|
|
data.addr = at->to;
|
|
|
|
|
|
|
|
perf_output_sample(&handle, &header, &data, event);
|
|
|
|
}
|
|
|
|
|
|
|
|
perf_output_end(&handle);
|
|
|
|
|
|
|
|
/* There's new data available. */
|
|
|
|
event->hw.interrupts++;
|
|
|
|
event->pending_kill = POLL_IN;
|
2010-09-10 11:28:01 +00:00
|
|
|
return 1;
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* PEBS
|
|
|
|
*/
|
|
|
|
|
|
|
|
static struct event_constraint intel_core_pebs_events[] = {
|
|
|
|
PEBS_EVENT_CONSTRAINT(0x00c0, 0x1), /* INSTR_RETIRED.ANY */
|
|
|
|
PEBS_EVENT_CONSTRAINT(0xfec1, 0x1), /* X87_OPS_RETIRED.ANY */
|
|
|
|
PEBS_EVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */
|
|
|
|
PEBS_EVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */
|
|
|
|
PEBS_EVENT_CONSTRAINT(0x01cb, 0x1), /* MEM_LOAD_RETIRED.L1D_MISS */
|
|
|
|
PEBS_EVENT_CONSTRAINT(0x02cb, 0x1), /* MEM_LOAD_RETIRED.L1D_LINE_MISS */
|
|
|
|
PEBS_EVENT_CONSTRAINT(0x04cb, 0x1), /* MEM_LOAD_RETIRED.L2_MISS */
|
|
|
|
PEBS_EVENT_CONSTRAINT(0x08cb, 0x1), /* MEM_LOAD_RETIRED.L2_LINE_MISS */
|
|
|
|
PEBS_EVENT_CONSTRAINT(0x10cb, 0x1), /* MEM_LOAD_RETIRED.DTLB_MISS */
|
|
|
|
EVENT_CONSTRAINT_END
|
|
|
|
};
|
|
|
|
|
|
|
|
static struct event_constraint intel_nehalem_pebs_events[] = {
|
|
|
|
PEBS_EVENT_CONSTRAINT(0x00c0, 0xf), /* INSTR_RETIRED.ANY */
|
|
|
|
PEBS_EVENT_CONSTRAINT(0xfec1, 0xf), /* X87_OPS_RETIRED.ANY */
|
|
|
|
PEBS_EVENT_CONSTRAINT(0x00c5, 0xf), /* BR_INST_RETIRED.MISPRED */
|
|
|
|
PEBS_EVENT_CONSTRAINT(0x1fc7, 0xf), /* SIMD_INST_RETURED.ANY */
|
|
|
|
PEBS_EVENT_CONSTRAINT(0x01cb, 0xf), /* MEM_LOAD_RETIRED.L1D_MISS */
|
|
|
|
PEBS_EVENT_CONSTRAINT(0x02cb, 0xf), /* MEM_LOAD_RETIRED.L1D_LINE_MISS */
|
|
|
|
PEBS_EVENT_CONSTRAINT(0x04cb, 0xf), /* MEM_LOAD_RETIRED.L2_MISS */
|
|
|
|
PEBS_EVENT_CONSTRAINT(0x08cb, 0xf), /* MEM_LOAD_RETIRED.L2_LINE_MISS */
|
|
|
|
PEBS_EVENT_CONSTRAINT(0x10cb, 0xf), /* MEM_LOAD_RETIRED.DTLB_MISS */
|
|
|
|
EVENT_CONSTRAINT_END
|
|
|
|
};
|
|
|
|
|
|
|
|
static struct event_constraint *
|
|
|
|
intel_pebs_constraints(struct perf_event *event)
|
|
|
|
{
|
|
|
|
struct event_constraint *c;
|
|
|
|
|
2010-04-08 21:03:20 +00:00
|
|
|
if (!event->attr.precise_ip)
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
return NULL;
|
|
|
|
|
|
|
|
if (x86_pmu.pebs_constraints) {
|
|
|
|
for_each_event_constraint(c, x86_pmu.pebs_constraints) {
|
|
|
|
if ((event->hw.config & c->cmask) == c->code)
|
|
|
|
return c;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
return &emptyconstraint;
|
|
|
|
}
|
|
|
|
|
2010-03-03 12:12:23 +00:00
|
|
|
static void intel_pmu_pebs_enable(struct perf_event *event)
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
{
|
|
|
|
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
|
2010-03-03 12:12:23 +00:00
|
|
|
struct hw_perf_event *hwc = &event->hw;
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
|
|
|
|
hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
|
|
|
|
|
2010-03-06 18:49:06 +00:00
|
|
|
cpuc->pebs_enabled |= 1ULL << hwc->idx;
|
2010-03-06 12:47:07 +00:00
|
|
|
WARN_ON_ONCE(cpuc->enabled);
|
2010-03-03 12:12:23 +00:00
|
|
|
|
2010-04-08 21:03:20 +00:00
|
|
|
if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1)
|
2010-03-03 16:07:40 +00:00
|
|
|
intel_pmu_lbr_enable(event);
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
}
|
|
|
|
|
2010-03-03 12:12:23 +00:00
|
|
|
static void intel_pmu_pebs_disable(struct perf_event *event)
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
{
|
|
|
|
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
|
2010-03-03 12:12:23 +00:00
|
|
|
struct hw_perf_event *hwc = &event->hw;
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
|
2010-03-06 18:49:06 +00:00
|
|
|
cpuc->pebs_enabled &= ~(1ULL << hwc->idx);
|
2010-03-06 12:47:07 +00:00
|
|
|
if (cpuc->enabled)
|
2010-03-06 18:49:06 +00:00
|
|
|
wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
|
|
|
|
hwc->config |= ARCH_PERFMON_EVENTSEL_INT;
|
2010-03-03 12:12:23 +00:00
|
|
|
|
2010-04-08 21:03:20 +00:00
|
|
|
if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1)
|
2010-03-03 16:07:40 +00:00
|
|
|
intel_pmu_lbr_disable(event);
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
static void intel_pmu_pebs_enable_all(void)
|
|
|
|
{
|
|
|
|
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
|
|
|
|
|
|
|
|
if (cpuc->pebs_enabled)
|
|
|
|
wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void intel_pmu_pebs_disable_all(void)
|
|
|
|
{
|
|
|
|
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
|
|
|
|
|
|
|
|
if (cpuc->pebs_enabled)
|
|
|
|
wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
|
|
|
|
}
|
|
|
|
|
2010-03-03 12:12:23 +00:00
|
|
|
#include <asm/insn.h>
|
|
|
|
|
|
|
|
static inline bool kernel_ip(unsigned long ip)
|
|
|
|
{
|
|
|
|
#ifdef CONFIG_X86_32
|
|
|
|
return ip > PAGE_OFFSET;
|
|
|
|
#else
|
|
|
|
return (long)ip < 0;
|
|
|
|
#endif
|
|
|
|
}
|
|
|
|
|
|
|
|
static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
|
|
|
|
{
|
|
|
|
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
|
|
|
|
unsigned long from = cpuc->lbr_entries[0].from;
|
|
|
|
unsigned long old_to, to = cpuc->lbr_entries[0].to;
|
|
|
|
unsigned long ip = regs->ip;
|
|
|
|
|
2010-03-03 16:07:40 +00:00
|
|
|
/*
|
|
|
|
* We don't need to fixup if the PEBS assist is fault like
|
|
|
|
*/
|
|
|
|
if (!x86_pmu.intel_cap.pebs_trap)
|
|
|
|
return 1;
|
|
|
|
|
2010-03-05 15:29:14 +00:00
|
|
|
/*
|
|
|
|
* No LBR entry, no basic block, no rewinding
|
|
|
|
*/
|
2010-03-03 12:12:23 +00:00
|
|
|
if (!cpuc->lbr_stack.nr || !from || !to)
|
|
|
|
return 0;
|
|
|
|
|
2010-03-05 15:29:14 +00:00
|
|
|
/*
|
|
|
|
* Basic blocks should never cross user/kernel boundaries
|
|
|
|
*/
|
|
|
|
if (kernel_ip(ip) != kernel_ip(to))
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* unsigned math, either ip is before the start (impossible) or
|
|
|
|
* the basic block is larger than 1 page (sanity)
|
|
|
|
*/
|
|
|
|
if ((ip - to) > PAGE_SIZE)
|
2010-03-03 12:12:23 +00:00
|
|
|
return 0;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We sampled a branch insn, rewind using the LBR stack
|
|
|
|
*/
|
|
|
|
if (ip == to) {
|
|
|
|
regs->ip = from;
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
do {
|
|
|
|
struct insn insn;
|
|
|
|
u8 buf[MAX_INSN_SIZE];
|
|
|
|
void *kaddr;
|
|
|
|
|
|
|
|
old_to = to;
|
|
|
|
if (!kernel_ip(ip)) {
|
2010-03-05 15:29:14 +00:00
|
|
|
int bytes, size = MAX_INSN_SIZE;
|
2010-03-03 12:12:23 +00:00
|
|
|
|
|
|
|
bytes = copy_from_user_nmi(buf, (void __user *)to, size);
|
|
|
|
if (bytes != size)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
kaddr = buf;
|
|
|
|
} else
|
|
|
|
kaddr = (void *)to;
|
|
|
|
|
|
|
|
kernel_insn_init(&insn, kaddr);
|
|
|
|
insn_get_length(&insn);
|
|
|
|
to += insn.length;
|
|
|
|
} while (to < ip);
|
|
|
|
|
|
|
|
if (to == ip) {
|
|
|
|
regs->ip = old_to;
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
2010-03-05 15:29:14 +00:00
|
|
|
/*
|
|
|
|
* Even though we decoded the basic block, the instruction stream
|
|
|
|
* never matched the given IP, either the TO or the IP got corrupted.
|
|
|
|
*/
|
2010-03-03 12:12:23 +00:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
static int intel_pmu_save_and_restart(struct perf_event *event);
|
|
|
|
|
2010-04-08 21:03:20 +00:00
|
|
|
static void __intel_pmu_pebs_event(struct perf_event *event,
|
|
|
|
struct pt_regs *iregs, void *__pebs)
|
|
|
|
{
|
|
|
|
/*
|
|
|
|
* We cast to pebs_record_core since that is a subset of
|
|
|
|
* both formats and we don't use the other fields in this
|
|
|
|
* routine.
|
|
|
|
*/
|
|
|
|
struct pebs_record_core *pebs = __pebs;
|
|
|
|
struct perf_sample_data data;
|
|
|
|
struct pt_regs regs;
|
|
|
|
|
|
|
|
if (!intel_pmu_save_and_restart(event))
|
|
|
|
return;
|
|
|
|
|
|
|
|
perf_sample_data_init(&data, 0);
|
|
|
|
data.period = event->hw.last_period;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We use the interrupt regs as a base because the PEBS record
|
|
|
|
* does not contain a full regs set, specifically it seems to
|
|
|
|
* lack segment descriptors, which get used by things like
|
|
|
|
* user_mode().
|
|
|
|
*
|
|
|
|
* In the simple case fix up only the IP and BP,SP regs, for
|
|
|
|
* PERF_SAMPLE_IP and PERF_SAMPLE_CALLCHAIN to function properly.
|
|
|
|
* A possible PERF_SAMPLE_REGS will have to transfer all regs.
|
|
|
|
*/
|
|
|
|
regs = *iregs;
|
|
|
|
regs.ip = pebs->ip;
|
|
|
|
regs.bp = pebs->bp;
|
|
|
|
regs.sp = pebs->sp;
|
|
|
|
|
2010-04-08 21:03:20 +00:00
|
|
|
if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(®s))
|
2010-04-08 21:03:20 +00:00
|
|
|
regs.flags |= PERF_EFLAGS_EXACT;
|
|
|
|
else
|
|
|
|
regs.flags &= ~PERF_EFLAGS_EXACT;
|
|
|
|
|
|
|
|
if (perf_event_overflow(event, 1, &data, ®s))
|
perf: Rework the PMU methods
Replace pmu::{enable,disable,start,stop,unthrottle} with
pmu::{add,del,start,stop}, all of which take a flags argument.
The new interface extends the capability to stop a counter while
keeping it scheduled on the PMU. We replace the throttled state with
the generic stopped state.
This also allows us to efficiently stop/start counters over certain
code paths (like IRQ handlers).
It also allows scheduling a counter without it starting, allowing for
a generic frozen state (useful for rotating stopped counters).
The stopped state is implemented in two different ways, depending on
how the architecture implemented the throttled state:
1) We disable the counter:
a) the pmu has per-counter enable bits, we flip that
b) we program a NOP event, preserving the counter state
2) We store the counter state and ignore all read/overflow events
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: paulus <paulus@samba.org>
Cc: stephane eranian <eranian@googlemail.com>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Lin Ming <ming.m.lin@intel.com>
Cc: Yanmin <yanmin_zhang@linux.intel.com>
Cc: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
Cc: David Miller <davem@davemloft.net>
Cc: Michael Cree <mcree@orcon.net.nz>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-06-16 12:37:10 +00:00
|
|
|
x86_pmu_stop(event, 0);
|
2010-04-08 21:03:20 +00:00
|
|
|
}
|
|
|
|
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
|
|
|
|
{
|
|
|
|
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
|
|
|
|
struct debug_store *ds = cpuc->ds;
|
|
|
|
struct perf_event *event = cpuc->events[0]; /* PMC0 only */
|
|
|
|
struct pebs_record_core *at, *top;
|
|
|
|
int n;
|
|
|
|
|
2010-10-19 12:22:50 +00:00
|
|
|
if (!x86_pmu.pebs_active)
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
return;
|
|
|
|
|
|
|
|
at = (struct pebs_record_core *)(unsigned long)ds->pebs_buffer_base;
|
|
|
|
top = (struct pebs_record_core *)(unsigned long)ds->pebs_index;
|
|
|
|
|
2010-03-09 10:41:02 +00:00
|
|
|
/*
|
|
|
|
* Whatever else happens, drain the thing
|
|
|
|
*/
|
|
|
|
ds->pebs_index = ds->pebs_buffer_base;
|
|
|
|
|
|
|
|
if (!test_bit(0, cpuc->active_mask))
|
2010-03-06 12:26:11 +00:00
|
|
|
return;
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
|
2010-03-09 10:41:02 +00:00
|
|
|
WARN_ON_ONCE(!event);
|
|
|
|
|
2010-04-08 21:03:20 +00:00
|
|
|
if (!event->attr.precise_ip)
|
2010-03-09 10:41:02 +00:00
|
|
|
return;
|
|
|
|
|
|
|
|
n = top - at;
|
|
|
|
if (n <= 0)
|
|
|
|
return;
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
|
2010-03-09 10:41:02 +00:00
|
|
|
/*
|
|
|
|
* Should not happen, we program the threshold at 1 and do not
|
|
|
|
* set a reset value.
|
|
|
|
*/
|
|
|
|
WARN_ON_ONCE(n > 1);
|
|
|
|
at += n - 1;
|
|
|
|
|
2010-04-08 21:03:20 +00:00
|
|
|
__intel_pmu_pebs_event(event, iregs, at);
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
|
|
|
|
{
|
|
|
|
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
|
|
|
|
struct debug_store *ds = cpuc->ds;
|
|
|
|
struct pebs_record_nhm *at, *top;
|
|
|
|
struct perf_event *event = NULL;
|
2010-03-06 17:57:38 +00:00
|
|
|
u64 status = 0;
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
int bit, n;
|
|
|
|
|
2010-10-19 12:22:50 +00:00
|
|
|
if (!x86_pmu.pebs_active)
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
return;
|
|
|
|
|
|
|
|
at = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base;
|
|
|
|
top = (struct pebs_record_nhm *)(unsigned long)ds->pebs_index;
|
|
|
|
|
|
|
|
ds->pebs_index = ds->pebs_buffer_base;
|
|
|
|
|
|
|
|
n = top - at;
|
2010-03-09 10:41:02 +00:00
|
|
|
if (n <= 0)
|
|
|
|
return;
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Should not happen, we program the threshold at 1 and do not
|
|
|
|
* set a reset value.
|
|
|
|
*/
|
|
|
|
WARN_ON_ONCE(n > MAX_PEBS_EVENTS);
|
|
|
|
|
|
|
|
for ( ; at < top; at++) {
|
2010-04-08 11:36:36 +00:00
|
|
|
for_each_set_bit(bit, (unsigned long *)&at->status, MAX_PEBS_EVENTS) {
|
2010-03-06 17:57:38 +00:00
|
|
|
event = cpuc->events[bit];
|
|
|
|
if (!test_bit(bit, cpuc->active_mask))
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
continue;
|
|
|
|
|
2010-03-06 17:57:38 +00:00
|
|
|
WARN_ON_ONCE(!event);
|
|
|
|
|
2010-04-08 21:03:20 +00:00
|
|
|
if (!event->attr.precise_ip)
|
2010-03-06 17:57:38 +00:00
|
|
|
continue;
|
|
|
|
|
|
|
|
if (__test_and_set_bit(bit, (unsigned long *)&status))
|
|
|
|
continue;
|
|
|
|
|
|
|
|
break;
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
}
|
|
|
|
|
2010-03-06 17:57:38 +00:00
|
|
|
if (!event || bit >= MAX_PEBS_EVENTS)
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
continue;
|
|
|
|
|
2010-04-08 21:03:20 +00:00
|
|
|
__intel_pmu_pebs_event(event, iregs, at);
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* BTS, PEBS probe and setup
|
|
|
|
*/
|
|
|
|
|
|
|
|
static void intel_ds_init(void)
|
|
|
|
{
|
|
|
|
/*
|
|
|
|
* No support for 32bit formats
|
|
|
|
*/
|
|
|
|
if (!boot_cpu_has(X86_FEATURE_DTES64))
|
|
|
|
return;
|
|
|
|
|
|
|
|
x86_pmu.bts = boot_cpu_has(X86_FEATURE_BTS);
|
|
|
|
x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS);
|
|
|
|
if (x86_pmu.pebs) {
|
2010-03-03 16:07:40 +00:00
|
|
|
char pebs_type = x86_pmu.intel_cap.pebs_trap ? '+' : '-';
|
|
|
|
int format = x86_pmu.intel_cap.pebs_format;
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
|
|
|
|
switch (format) {
|
|
|
|
case 0:
|
2010-03-03 16:07:40 +00:00
|
|
|
printk(KERN_CONT "PEBS fmt0%c, ", pebs_type);
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
x86_pmu.pebs_record_size = sizeof(struct pebs_record_core);
|
|
|
|
x86_pmu.drain_pebs = intel_pmu_drain_pebs_core;
|
|
|
|
x86_pmu.pebs_constraints = intel_core_pebs_events;
|
|
|
|
break;
|
|
|
|
|
|
|
|
case 1:
|
2010-03-03 16:07:40 +00:00
|
|
|
printk(KERN_CONT "PEBS fmt1%c, ", pebs_type);
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
x86_pmu.pebs_record_size = sizeof(struct pebs_record_nhm);
|
|
|
|
x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm;
|
|
|
|
x86_pmu.pebs_constraints = intel_nehalem_pebs_events;
|
|
|
|
break;
|
|
|
|
|
|
|
|
default:
|
2010-03-03 16:07:40 +00:00
|
|
|
printk(KERN_CONT "no PEBS fmt%d%c, ", format, pebs_type);
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
x86_pmu.pebs = 0;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
#else /* CONFIG_CPU_SUP_INTEL */
|
|
|
|
|
2010-10-19 12:50:02 +00:00
|
|
|
static void reserve_ds_buffers(void)
|
perf, x86: Add PEBS infrastructure
This patch implements support for Intel Precise Event Based Sampling,
which is an alternative counter mode in which the counter triggers a
hardware assist to collect information on events. The hardware assist
takes a trap like snapshot of a subset of the machine registers.
This data is written to the Intel Debug-Store, which can be programmed
with a data threshold at which to raise a PMI.
With the PEBS hardware assist being trap like, the reported IP is always
one instruction after the actual instruction that triggered the event.
This implements a simple PEBS model that always takes a single PEBS event
at a time. This is done so that the interaction with the rest of the
system is as expected (freq adjust, period randomization, lbr,
callchains, etc.).
It adds an ABI element: perf_event_attr::precise, which indicates that we
wish to use this (constrained, but precise) mode.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: paulus@samba.org
Cc: eranian@google.com
Cc: robert.richter@amd.com
Cc: fweisbec@gmail.com
LKML-Reference: <20100304140100.392111285@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-02 18:52:12 +00:00
|
|
|
{
|
|
|
|
}
|
|
|
|
|
|
|
|
static void release_ds_buffers(void)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
|
|
|
#endif /* CONFIG_CPU_SUP_INTEL */
|