[PATCH v5 12/20] x86: perf: intel_pt: Intel PT PMU driver

From: Alexander Shishkin
Date: Mon Oct 13 2014 - 09:52:40 EST


Add support for Intel Processor Trace (PT) to kernel's perf events.
PT is an extension of Intel Architecture that collects information about
software execuction such as control flow, execution modes and timings and
formats it into highly compressed binary packets. Even being compressed,
these packets are generated at hundreds of megabytes per second per core,
which makes it impractical to decode them on the fly in the kernel.

This driver exports trace data by through AUX space in the perf ring
buffer, which is zero-copy mapped into userspace for faster data retrieval.

Signed-off-by: Alexander Shishkin <alexander.shishkin@xxxxxxxxxxxxxxx>
---
arch/x86/include/uapi/asm/msr-index.h | 18 +
arch/x86/kernel/cpu/Makefile | 1 +
arch/x86/kernel/cpu/intel_pt.h | 129 ++++
arch/x86/kernel/cpu/perf_event.h | 2 +
arch/x86/kernel/cpu/perf_event_intel.c | 8 +
arch/x86/kernel/cpu/perf_event_intel_pt.c | 995 ++++++++++++++++++++++++++++++
6 files changed, 1153 insertions(+)
create mode 100644 arch/x86/kernel/cpu/intel_pt.h
create mode 100644 arch/x86/kernel/cpu/perf_event_intel_pt.c

diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h
index e21331ce36..caae296ab7 100644
--- a/arch/x86/include/uapi/asm/msr-index.h
+++ b/arch/x86/include/uapi/asm/msr-index.h
@@ -74,6 +74,24 @@
#define MSR_IA32_PERF_CAPABILITIES 0x00000345
#define MSR_PEBS_LD_LAT_THRESHOLD 0x000003f6

+#define MSR_IA32_RTIT_CTL 0x00000570
+#define RTIT_CTL_TRACEEN BIT(0)
+#define RTIT_CTL_OS BIT(2)
+#define RTIT_CTL_USR BIT(3)
+#define RTIT_CTL_CR3EN BIT(7)
+#define RTIT_CTL_TOPA BIT(8)
+#define RTIT_CTL_TSC_EN BIT(10)
+#define RTIT_CTL_DISRETC BIT(11)
+#define RTIT_CTL_BRANCH_EN BIT(13)
+#define MSR_IA32_RTIT_STATUS 0x00000571
+#define RTIT_STATUS_CONTEXTEN BIT(1)
+#define RTIT_STATUS_TRIGGEREN BIT(2)
+#define RTIT_STATUS_ERROR BIT(4)
+#define RTIT_STATUS_STOPPED BIT(5)
+#define MSR_IA32_RTIT_CR3_MATCH 0x00000572
+#define MSR_IA32_RTIT_OUTPUT_BASE 0x00000560
+#define MSR_IA32_RTIT_OUTPUT_MASK 0x00000561
+
#define MSR_MTRRfix64K_00000 0x00000250
#define MSR_MTRRfix16K_80000 0x00000258
#define MSR_MTRRfix16K_A0000 0x00000259
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 7e1fd4e085..00d40f889d 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -39,6 +39,7 @@ obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_lbr.o perf_event_intel_ds.o per
obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_uncore.o perf_event_intel_uncore_snb.o
obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_uncore_snbep.o perf_event_intel_uncore_nhmex.o
obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_rapl.o
+obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_pt.o
endif


diff --git a/arch/x86/kernel/cpu/intel_pt.h b/arch/x86/kernel/cpu/intel_pt.h
new file mode 100644
index 0000000000..9fa9c165cc
--- /dev/null
+++ b/arch/x86/kernel/cpu/intel_pt.h
@@ -0,0 +1,129 @@
+/*
+ * Intel(R) Processor Trace PMU driver for perf
+ * Copyright (c) 2013-2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * Intel PT is specified in the Intel Architecture Instruction Set Extensions
+ * Programming Reference:
+ * http://software.intel.com/en-us/intel-isa-extensions
+ */
+
+#ifndef __INTEL_PT_H__
+#define __INTEL_PT_H__
+
+/*
+ * Single-entry ToPA: when this close to region boundary, switch
+ * buffers to avoid losing data.
+ */
+#define TOPA_PMI_MARGIN 512
+
+/*
+ * Table of Physical Addresses bits
+ */
+enum topa_sz {
+ TOPA_4K = 0,
+ TOPA_8K,
+ TOPA_16K,
+ TOPA_32K,
+ TOPA_64K,
+ TOPA_128K,
+ TOPA_256K,
+ TOPA_512K,
+ TOPA_1MB,
+ TOPA_2MB,
+ TOPA_4MB,
+ TOPA_8MB,
+ TOPA_16MB,
+ TOPA_32MB,
+ TOPA_64MB,
+ TOPA_128MB,
+ TOPA_SZ_END,
+};
+
+static inline unsigned int sizes(enum topa_sz tsz)
+{
+ return 1 << (tsz + 12);
+};
+
+struct topa_entry {
+ u64 end : 1;
+ u64 rsvd0 : 1;
+ u64 intr : 1;
+ u64 rsvd1 : 1;
+ u64 stop : 1;
+ u64 rsvd2 : 1;
+ u64 size : 4;
+ u64 rsvd3 : 2;
+ u64 base : 36;
+ u64 rsvd4 : 16;
+};
+
+#define TOPA_SHIFT 12
+#define PT_CPUID_LEAVES 2
+
+enum pt_capabilities {
+ PT_CAP_max_subleaf = 0,
+ PT_CAP_cr3_filtering,
+ PT_CAP_topa_output,
+ PT_CAP_topa_multiple_entries,
+ PT_CAP_payloads_lip,
+};
+
+struct pt_pmu {
+ struct pmu pmu;
+ u32 caps[4 * PT_CPUID_LEAVES];
+};
+
+/**
+ * struct pt_buffer - buffer configuration; one buffer per task_struct or
+ * cpu, depending on perf event configuration
+ * @tables: list of ToPA tables in this buffer
+ * @first, @last: shorthands for first and last topa tables
+ * @cur: current topa table
+ * @nr_pages: buffer size in pages
+ * @cur_idx: current output region's index within @cur table
+ * @output_off: offset within the current output region
+ * @data_size: running total of the amount of data in this buffer
+ * @lost: if data was lost/truncated
+ * @head: logical write offset inside the buffer
+ * @snapshot: if this is for a snapshot/overwrite counter
+ * @stop_pos, @intr_pos: STOP and INT topa entries in the buffer
+ * @data_pages: array of pages from perf
+ * @topa_index: table of topa entries indexed by page offset
+ */
+struct pt_buffer {
+ /* hint for allocation */
+ int cpu;
+ /* list of ToPA tables */
+ struct list_head tables;
+ /* top-level table */
+ struct topa *first, *last, *cur;
+ unsigned int cur_idx;
+ size_t output_off;
+ unsigned long nr_pages;
+ local_t data_size;
+ local_t lost;
+ local64_t head;
+ bool snapshot;
+ unsigned long stop_pos, intr_pos;
+ void **data_pages;
+ struct topa_entry *topa_index[0];
+};
+
+/**
+ * struct pt - per-cpu pt
+ */
+struct pt {
+ struct perf_output_handle handle;
+ int handle_nmi;
+};
+
+#endif /* __INTEL_PT_H__ */
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 8eee92be78..9f9b02fea6 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -750,6 +750,8 @@ void intel_pmu_lbr_init_snb(void);

int intel_pmu_setup_lbr_filter(struct perf_event *event);

+void intel_pt_interrupt(void);
+
int p4_pmu_init(void);

int p6_pmu_init(void);
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 3851def505..6e04da1b04 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1528,6 +1528,14 @@ again:
}

/*
+ * Intel PT
+ */
+ if (__test_and_clear_bit(55, (unsigned long *)&status)) {
+ handled++;
+ intel_pt_interrupt();
+ }
+
+ /*
* Checkpointed counters can lead to 'spurious' PMIs because the
* rollback caused by the PMI will have cleared the overflow status
* bit. Therefore always force probe these counters.
diff --git a/arch/x86/kernel/cpu/perf_event_intel_pt.c b/arch/x86/kernel/cpu/perf_event_intel_pt.c
new file mode 100644
index 0000000000..bc8bf1f24d
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_intel_pt.c
@@ -0,0 +1,995 @@
+/*
+ * Intel(R) Processor Trace PMU driver for perf
+ * Copyright (c) 2013-2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * Intel PT is specified in the Intel Architecture Instruction Set Extensions
+ * Programming Reference:
+ * http://software.intel.com/en-us/intel-isa-extensions
+ */
+
+#undef DEBUG
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/device.h>
+
+#include <asm/perf_event.h>
+#include <asm/insn.h>
+
+#include "perf_event.h"
+#include "intel_pt.h"
+
+static DEFINE_PER_CPU(struct pt, pt_ctx);
+
+static struct pt_pmu pt_pmu;
+
+enum cpuid_regs {
+ CR_EAX = 0,
+ CR_ECX,
+ CR_EDX,
+ CR_EBX
+};
+
+/*
+ * Capabilities of Intel PT hardware, such as number of address bits or
+ * supported output schemes, are cached and exported to userspace as "caps"
+ * attribute group of pt pmu device
+ * (/sys/bus/event_source/devices/intel_pt/caps/) so that userspace can store
+ * relevant bits together with intel_pt traces.
+ */
+#define PT_CAP(_n, _l, _r, _m) \
+ [PT_CAP_ ## _n] = { .name = __stringify(_n), .leaf = _l, \
+ .reg = _r, .mask = _m }
+
+static struct pt_cap_desc {
+ const char *name;
+ u32 leaf;
+ u8 reg;
+ u32 mask;
+} pt_caps[] = {
+ PT_CAP(max_subleaf, 0, CR_EAX, 0xffffffff),
+ PT_CAP(cr3_filtering, 0, CR_EBX, BIT(0)),
+ PT_CAP(topa_output, 0, CR_ECX, BIT(0)),
+ PT_CAP(topa_multiple_entries, 0, CR_ECX, BIT(1)),
+ PT_CAP(payloads_lip, 0, CR_ECX, BIT(31)),
+};
+
+static u32 pt_cap_get(enum pt_capabilities cap)
+{
+ struct pt_cap_desc *cd = &pt_caps[cap];
+ u32 c = pt_pmu.caps[cd->leaf * 4 + cd->reg];
+ unsigned int shift = __ffs(cd->mask);
+
+ return (c & cd->mask) >> shift;
+}
+
+static ssize_t pt_cap_show(struct device *cdev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct dev_ext_attribute *ea =
+ container_of(attr, struct dev_ext_attribute, attr);
+ enum pt_capabilities cap = (long)ea->var;
+
+ return snprintf(buf, PAGE_SIZE, "%x\n", pt_cap_get(cap));
+}
+
+static struct attribute_group pt_cap_group = {
+ .name = "caps",
+};
+
+PMU_FORMAT_ATTR(tsc, "config:10" );
+PMU_FORMAT_ATTR(noretcomp, "config:11" );
+
+static struct attribute *pt_formats_attr[] = {
+ &format_attr_tsc.attr,
+ &format_attr_noretcomp.attr,
+ NULL,
+};
+
+static struct attribute_group pt_format_group = {
+ .name = "format",
+ .attrs = pt_formats_attr,
+};
+
+static const struct attribute_group *pt_attr_groups[] = {
+ &pt_cap_group,
+ &pt_format_group,
+ NULL,
+};
+
+static int __init pt_pmu_hw_init(void)
+{
+ struct dev_ext_attribute *de_attrs;
+ struct attribute **attrs;
+ size_t size;
+ long i;
+
+ if (test_cpu_cap(&boot_cpu_data, X86_FEATURE_INTEL_PT)) {
+ for (i = 0; i < PT_CPUID_LEAVES; i++)
+ cpuid_count(20, i,
+ &pt_pmu.caps[CR_EAX + i * 4],
+ &pt_pmu.caps[CR_EBX + i * 4],
+ &pt_pmu.caps[CR_ECX + i * 4],
+ &pt_pmu.caps[CR_EDX + i * 4]);
+ } else
+ return -ENODEV;
+
+ size = sizeof(struct attribute *) * (ARRAY_SIZE(pt_caps) + 1);
+ attrs = kzalloc(size, GFP_KERNEL);
+ if (!attrs)
+ goto err_attrs;
+
+ size = sizeof(struct dev_ext_attribute) * (ARRAY_SIZE(pt_caps) + 1);
+ de_attrs = kzalloc(size, GFP_KERNEL);
+ if (!de_attrs)
+ goto err_de_attrs;
+
+ for (i = 0; i < ARRAY_SIZE(pt_caps); i++) {
+ de_attrs[i].attr.attr.name = pt_caps[i].name;
+
+ sysfs_attr_init(&de_attrs[i].attr.attr);
+ de_attrs[i].attr.attr.mode = S_IRUGO;
+ de_attrs[i].attr.show = pt_cap_show;
+ de_attrs[i].var = (void *)i;
+ attrs[i] = &de_attrs[i].attr.attr;
+ }
+
+ pt_cap_group.attrs = attrs;
+ return 0;
+
+err_de_attrs:
+ kfree(de_attrs);
+err_attrs:
+ kfree(attrs);
+
+ return -ENOMEM;
+}
+
+#define PT_CONFIG_MASK (RTIT_CTL_TSC_EN | RTIT_CTL_DISRETC)
+/* bits 57:14 are reserved for packet enables */
+#define PT_BYPASS_MASK 0x03ffffffffffc000ull
+
+static bool pt_event_valid(struct perf_event *event)
+{
+ u64 config = event->attr.config;
+
+ /* admin can set any packet generation parameters */
+ if (capable(CAP_SYS_ADMIN) && (config & PT_BYPASS_MASK) == config)
+ return true;
+
+ if ((config & PT_CONFIG_MASK) != config)
+ return false;
+
+ return true;
+}
+
+/*
+ * PT configuration helpers
+ * These all are cpu affine and operate on a local PT
+ */
+
+static bool pt_is_running(void)
+{
+ u64 ctl;
+
+ rdmsrl(MSR_IA32_RTIT_CTL, ctl);
+
+ return !!(ctl & RTIT_CTL_TRACEEN);
+}
+
+static int pt_config(struct perf_event *event)
+{
+ u64 reg;
+
+ reg = RTIT_CTL_TOPA | RTIT_CTL_BRANCH_EN;
+
+ if (!event->attr.exclude_kernel)
+ reg |= RTIT_CTL_OS;
+ if (!event->attr.exclude_user)
+ reg |= RTIT_CTL_USR;
+
+ reg |= (event->attr.config & PT_CONFIG_MASK);
+
+ /*
+ * User can try to set bits in RTIT_CTL through PT_BYPASS_MASK,
+ * that aren't supported by the hardware. Weather or not a
+ * particular bitmask is supported by a cpu can't be determined
+ * via cpuid or otherwise, so we have to rely on #GP handling
+ * to catch these cases.
+ */
+ return wrmsrl_safe(MSR_IA32_RTIT_CTL, reg);
+}
+
+static void pt_config_start(bool start)
+{
+ u64 ctl;
+
+ rdmsrl(MSR_IA32_RTIT_CTL, ctl);
+ if (start)
+ ctl |= RTIT_CTL_TRACEEN;
+ else
+ ctl &= ~RTIT_CTL_TRACEEN;
+ wrmsrl(MSR_IA32_RTIT_CTL, ctl);
+
+ /*
+ * A wrmsr that disables trace generation serializes other PT
+ * registers and causes all data packets to be written to memory,
+ * but a fence is required for the data to become globally visible.
+ *
+ * The below WMB, separating data store and aux_head store matches
+ * the consumer's RMB that separates aux_head load and data load.
+ */
+ if (!start)
+ wmb();
+}
+
+static void pt_config_buffer(void *buf, unsigned int topa_idx,
+ unsigned int output_off)
+{
+ u64 reg;
+
+ wrmsrl(MSR_IA32_RTIT_OUTPUT_BASE, virt_to_phys(buf));
+
+ reg = 0x7f | ((u64)topa_idx << 7) | ((u64)output_off << 32);
+
+ wrmsrl(MSR_IA32_RTIT_OUTPUT_MASK, reg);
+}
+
+/*
+ * Keep ToPA table-related metadata on the same page as the actual table,
+ * taking up a few words from the top
+ */
+
+#define TENTS_PER_PAGE (((PAGE_SIZE - 40) / sizeof(struct topa_entry)) - 1)
+
+struct topa {
+ struct topa_entry table[TENTS_PER_PAGE];
+ struct list_head list;
+ u64 phys;
+ u64 offset;
+ size_t size;
+ int last;
+};
+
+/* make negative table index stand for the last table entry */
+#define TOPA_ENTRY(t, i) ((i) == -1 ? &(t)->table[(t)->last] : &(t)->table[(i)])
+
+/*
+ * allocate page-sized ToPA table
+ */
+static struct topa *topa_alloc(int cpu, gfp_t gfp)
+{
+ int node = cpu_to_node(cpu);
+ struct topa *topa;
+ struct page *p;
+
+ p = alloc_pages_node(node, gfp | __GFP_ZERO, 0);
+ if (!p)
+ return NULL;
+
+ topa = page_address(p);
+ topa->last = 0;
+ topa->phys = page_to_phys(p);
+
+ /*
+ * In case of singe-entry ToPA, always put the self-referencing END
+ * link as the 2nd entry in the table
+ */
+ if (!pt_cap_get(PT_CAP_topa_multiple_entries)) {
+ TOPA_ENTRY(topa, 1)->base = topa->phys >> TOPA_SHIFT;
+ TOPA_ENTRY(topa, 1)->end = 1;
+ }
+
+ return topa;
+}
+
+static void topa_free(struct topa *topa)
+{
+ free_page((unsigned long)topa);
+}
+
+/**
+ * topa_insert_table - insert a ToPA table into a buffer
+ * @buf - pt buffer that's being extended
+ * @topa - new topa table to be inserted
+ *
+ * If it's the first table in this buffer, set up buffer's pointers
+ * accordingly; otherwise, add a END=1 link entry to @topa to the current
+ * "last" table and adjust the last table pointer to @topa.
+ */
+static void topa_insert_table(struct pt_buffer *buf, struct topa *topa)
+{
+ struct topa *last = buf->last;
+
+ list_add_tail(&topa->list, &buf->tables);
+
+ if (!buf->first) {
+ buf->first = buf->last = buf->cur = topa;
+ return;
+ }
+
+ topa->offset = last->offset + last->size;
+ buf->last = topa;
+
+ if (!pt_cap_get(PT_CAP_topa_multiple_entries))
+ return;
+
+ BUG_ON(last->last != TENTS_PER_PAGE - 1);
+
+ TOPA_ENTRY(last, -1)->base = topa->phys >> TOPA_SHIFT;
+ TOPA_ENTRY(last, -1)->end = 1;
+}
+
+static bool topa_table_full(struct topa *topa)
+{
+ /* single-entry ToPA is a special case */
+ if (!pt_cap_get(PT_CAP_topa_multiple_entries))
+ return !!topa->last;
+
+ return topa->last == TENTS_PER_PAGE - 1;
+}
+
+static int topa_insert_pages(struct pt_buffer *buf, gfp_t gfp)
+{
+ struct topa *topa = buf->last;
+ int order = 0;
+ struct page *p;
+
+ p = virt_to_page(buf->data_pages[buf->nr_pages]);
+ if (PagePrivate(p))
+ order = page_private(p);
+
+ if (topa_table_full(topa)) {
+ topa = topa_alloc(buf->cpu, gfp);
+ if (!topa)
+ return -ENOMEM;
+
+ topa_insert_table(buf, topa);
+ }
+
+ TOPA_ENTRY(topa, -1)->base = page_to_phys(p) >> TOPA_SHIFT;
+ TOPA_ENTRY(topa, -1)->size = order;
+ if (!buf->snapshot && !pt_cap_get(PT_CAP_topa_multiple_entries)) {
+ TOPA_ENTRY(topa, -1)->intr = 1;
+ TOPA_ENTRY(topa, -1)->stop = 1;
+ }
+
+ topa->last++;
+ topa->size += sizes(order);
+
+ buf->nr_pages += 1ul << order;
+
+ return 0;
+}
+
+static void pt_topa_dump(struct pt_buffer *buf)
+{
+ struct topa *topa;
+
+ list_for_each_entry(topa, &buf->tables, list) {
+ int i;
+
+ pr_debug("# table @%p (%p), off %llx size %zx\n", topa->table,
+ (void *)topa->phys, topa->offset, topa->size);
+ for (i = 0; i < TENTS_PER_PAGE; i++) {
+ pr_debug("# entry @%p (%lx sz %u %c%c%c) raw=%16llx\n",
+ &topa->table[i],
+ (unsigned long)topa->table[i].base << TOPA_SHIFT,
+ sizes(topa->table[i].size),
+ topa->table[i].end ? 'E' : ' ',
+ topa->table[i].intr ? 'I' : ' ',
+ topa->table[i].stop ? 'S' : ' ',
+ *(u64 *)&topa->table[i]);
+ if ((pt_cap_get(PT_CAP_topa_multiple_entries)
+ && topa->table[i].stop)
+ || topa->table[i].end)
+ break;
+ }
+ }
+}
+
+/* advance to the next output region */
+static void pt_buffer_advance(struct pt_buffer *buf)
+{
+ buf->output_off = 0;
+ buf->cur_idx++;
+
+ if (buf->cur_idx == buf->cur->last) {
+ if (buf->cur == buf->last)
+ buf->cur = buf->first;
+ else
+ buf->cur = list_entry(buf->cur->list.next, struct topa,
+ list);
+ buf->cur_idx = 0;
+ }
+}
+
+static void pt_update_head(struct pt *pt)
+{
+ struct pt_buffer *buf = perf_get_aux(&pt->handle);
+ u64 topa_idx, base, old;
+
+ /* offset of the first region in this table from the beginning of buf */
+ base = buf->cur->offset + buf->output_off;
+
+ /* offset of the current output region within this table */
+ for (topa_idx = 0; topa_idx < buf->cur_idx; topa_idx++)
+ base += sizes(buf->cur->table[topa_idx].size);
+
+ if (buf->snapshot) {
+ local_set(&buf->data_size, base);
+ } else {
+ old = (local64_xchg(&buf->head, base) &
+ ((buf->nr_pages << PAGE_SHIFT) - 1));
+ if (base < old)
+ base += buf->nr_pages << PAGE_SHIFT;
+
+ local_add(base - old, &buf->data_size);
+ }
+}
+
+static void *pt_buffer_region(struct pt_buffer *buf)
+{
+ return phys_to_virt(buf->cur->table[buf->cur_idx].base << TOPA_SHIFT);
+}
+
+static size_t pt_buffer_region_size(struct pt_buffer *buf)
+{
+ return sizes(buf->cur->table[buf->cur_idx].size);
+}
+
+/**
+ * pt_handle_status - take care of possible status conditions
+ * @pt: per-cpu pt handle
+ */
+static void pt_handle_status(struct pt *pt)
+{
+ struct pt_buffer *buf = perf_get_aux(&pt->handle);
+ int advance = 0;
+ u64 status;
+
+ rdmsrl(MSR_IA32_RTIT_STATUS, status);
+
+ if (status & RTIT_STATUS_ERROR) {
+ pr_err_ratelimited("ToPA ERROR encountered, trying to recover\n");
+ pt_topa_dump(buf);
+ status &= ~RTIT_STATUS_ERROR;
+ wrmsrl(MSR_IA32_RTIT_STATUS, status);
+ }
+
+ if (status & RTIT_STATUS_STOPPED) {
+ status &= ~RTIT_STATUS_STOPPED;
+ wrmsrl(MSR_IA32_RTIT_STATUS, status);
+
+ /*
+ * On systems that only do single-entry ToPA, hitting STOP
+ * means we are already losing data; need to let the decoder
+ * know.
+ */
+ if (!pt_cap_get(PT_CAP_topa_multiple_entries) ||
+ buf->output_off == sizes(TOPA_ENTRY(buf->cur, buf->cur_idx)->size)) {
+ local_inc(&buf->lost);
+ advance++;
+ }
+ }
+
+ /*
+ * Also on single-entry ToPA implementations, interrupt will come
+ * before the output reaches its output region's boundary.
+ */
+ if (!pt_cap_get(PT_CAP_topa_multiple_entries) && !buf->snapshot &&
+ pt_buffer_region_size(buf) - buf->output_off <= TOPA_PMI_MARGIN) {
+ void *head = pt_buffer_region(buf);
+
+ /* everything within this margin needs to be zeroed out */
+ memset(head + buf->output_off, 0,
+ pt_buffer_region_size(buf) -
+ buf->output_off);
+ advance++;
+ }
+
+ if (advance)
+ pt_buffer_advance(buf);
+}
+
+static void pt_read_offset(struct pt_buffer *buf)
+{
+ u64 offset, base_topa;
+
+ rdmsrl(MSR_IA32_RTIT_OUTPUT_BASE, base_topa);
+ buf->cur = phys_to_virt(base_topa);
+
+ rdmsrl(MSR_IA32_RTIT_OUTPUT_MASK, offset);
+ /* offset within current output region */
+ buf->output_off = offset >> 32;
+ /* index of current output region within this table */
+ buf->cur_idx = (offset & 0xffffff80) >> 7;
+}
+
+/**
+ * pt_buffer_fini_topa() - deallocate ToPA structure of a buffer
+ * @buf: pt buffer
+ */
+static void pt_buffer_fini_topa(struct pt_buffer *buf)
+{
+ struct topa *topa, *iter;
+
+ list_for_each_entry_safe(topa, iter, &buf->tables, list) {
+ /*
+ * right now, this is in free_aux() path only, so
+ * no need to unlink this table from the list
+ */
+ topa_free(topa);
+ }
+}
+
+static unsigned int pt_topa_next_entry(struct pt_buffer *buf, unsigned int pg)
+{
+ struct topa_entry *te = buf->topa_index[pg];
+
+ if (buf->first == buf->last && buf->first->last == 1)
+ return pg;
+
+ do {
+ pg++;
+ pg &= buf->nr_pages - 1;
+ } while (buf->topa_index[pg] == te);
+
+ return pg;
+}
+
+static int pt_buffer_reset_markers(struct pt_buffer *buf,
+ struct perf_output_handle *handle)
+
+{
+ unsigned long idx, npages, end;
+
+ if (buf->snapshot)
+ return 0;
+
+ /* can't stop in the middle of an output region */
+ if (buf->output_off + handle->size + 1 <
+ sizes(TOPA_ENTRY(buf->cur, buf->cur_idx)->size))
+ return -EINVAL;
+
+
+ /* single entry ToPA is handled by marking all regions STOP=1 INT=1 */
+ if (!pt_cap_get(PT_CAP_topa_multiple_entries))
+ return 0;
+
+ /* clear STOP and INT from current entry */
+ buf->topa_index[buf->stop_pos]->stop = 0;
+ buf->topa_index[buf->intr_pos]->intr = 0;
+
+ if (pt_cap_get(PT_CAP_topa_multiple_entries)) {
+ npages = (handle->size + 1) >> PAGE_SHIFT;
+ end = (local64_read(&buf->head) >> PAGE_SHIFT) + npages;
+ if (end > handle->wakeup >> PAGE_SHIFT)
+ end = handle->wakeup >> PAGE_SHIFT;
+ idx = end & (buf->nr_pages - 1);
+ buf->stop_pos = idx;
+ idx = (local64_read(&buf->head) >> PAGE_SHIFT) + npages / 2;
+ idx &= buf->nr_pages - 1;
+ buf->intr_pos = idx;
+ }
+
+ buf->topa_index[buf->stop_pos]->stop = 1;
+ buf->topa_index[buf->intr_pos]->intr = 1;
+
+ return 0;
+}
+
+static void pt_buffer_setup_topa_index(struct pt_buffer *buf)
+{
+ struct topa *cur = buf->first, *prev = buf->last;
+ struct topa_entry *te_cur = TOPA_ENTRY(cur, 0),
+ *te_prev = TOPA_ENTRY(prev, prev->last - 1);
+ int pg = 0, idx = 0, ntopa = 0;
+
+ while (pg < buf->nr_pages) {
+ int tidx;
+
+ /* pages within one topa entry */
+ for (tidx = 0; tidx < 1 << te_cur->size; tidx++, pg++)
+ buf->topa_index[pg] = te_prev;
+
+ te_prev = te_cur;
+
+ if (idx == cur->last - 1) {
+ /* advance to next topa table */
+ idx = 0;
+ cur = list_entry(cur->list.next, struct topa, list);
+ ntopa++;
+ } else
+ idx++;
+ te_cur = TOPA_ENTRY(cur, idx);
+ }
+
+}
+
+static void pt_buffer_reset_offsets(struct pt_buffer *buf, unsigned long head)
+{
+ int pg;
+
+ if (buf->snapshot)
+ head &= (buf->nr_pages << PAGE_SHIFT) - 1;
+
+ pg = (head >> PAGE_SHIFT) & (buf->nr_pages - 1);
+ pg = pt_topa_next_entry(buf, pg);
+
+ buf->cur = (struct topa *)((unsigned long)buf->topa_index[pg] & PAGE_MASK);
+ buf->cur_idx = ((unsigned long)buf->topa_index[pg] -
+ (unsigned long)buf->cur) / sizeof(struct topa_entry);
+ buf->output_off = head & (sizes(buf->cur->table[buf->cur_idx].size) - 1);
+
+ local64_set(&buf->head, head);
+ local_set(&buf->data_size, 0);
+}
+
+/**
+ * pt_buffer_init_topa() - initialize ToPA table for pt buffer
+ * @buf: pt buffer
+ * @size: total size of all regions within this ToPA
+ * @gfp: allocation flags
+ */
+static int pt_buffer_init_topa(struct pt_buffer *buf, unsigned long nr_pages,
+ gfp_t gfp)
+{
+ struct topa *topa;
+ int err;
+
+ topa = topa_alloc(buf->cpu, gfp);
+ if (!topa)
+ return -ENOMEM;
+
+ topa_insert_table(buf, topa);
+
+ while (buf->nr_pages < nr_pages) {
+ err = topa_insert_pages(buf, gfp);
+ if (err) {
+ pt_buffer_fini_topa(buf);
+ return -ENOMEM;
+ }
+ }
+
+ pt_buffer_setup_topa_index(buf);
+
+ /* link last table to the first one, unless we're double buffering */
+ if (pt_cap_get(PT_CAP_topa_multiple_entries)) {
+ TOPA_ENTRY(buf->last, -1)->base = buf->first->phys >> TOPA_SHIFT;
+ TOPA_ENTRY(buf->last, -1)->end = 1;
+ }
+
+ pt_topa_dump(buf);
+ return 0;
+}
+
+/**
+ * pt_buffer_setup_aux() - set up topa tables for a PT buffer
+ * @cpu: cpu on which to allocate, -1 means current
+ * @pages: array of pointers to buffer pages passed from perf core
+ * @nr_pages: number of pages in the buffer
+ * @snapshot: if this is a snapshot/overwrite counter
+ */
+static void *
+pt_buffer_setup_aux(int cpu, void **pages, int nr_pages, bool snapshot)
+{
+ struct pt_buffer *buf;
+ int node, ret;
+
+ if (!nr_pages)
+ return NULL;
+
+ if (cpu == -1)
+ cpu = raw_smp_processor_id();
+ node = cpu_to_node(cpu);
+
+ buf = kzalloc_node(offsetof(struct pt_buffer, topa_index[nr_pages]),
+ GFP_KERNEL, node);
+ if (!buf)
+ return NULL;
+
+ buf->cpu = cpu;
+ buf->snapshot = snapshot;
+ buf->data_pages = pages;
+
+ INIT_LIST_HEAD(&buf->tables);
+
+ ret = pt_buffer_init_topa(buf, nr_pages, GFP_KERNEL);
+ if (ret) {
+ kfree(buf);
+ return NULL;
+ }
+
+ return buf;
+}
+
+/**
+ * pt_buffer_free_aux() - perf mmap_close path callback
+ * @data: pt buffer
+ */
+static void pt_buffer_free_aux(void *data)
+{
+ struct pt_buffer *buf = data;
+
+ pt_buffer_fini_topa(buf);
+ kfree(buf);
+}
+
+/**
+ * pt_buffer_is_full - check if the buffer is full
+ * @buf: pt buffer
+ * @pt: per-cpu pt handle
+ * If the user hasn't read data from the output region that aux_head
+ * points to, the buffer is considered full: the user needs to read at
+ * least this region and update aux_tail to point past it.
+ */
+static bool pt_buffer_is_full(struct pt_buffer *buf, struct pt *pt)
+{
+ if (buf->snapshot)
+ return false;
+
+ if (local_read(&buf->data_size) >= pt->handle.size)
+ return true;
+
+ return false;
+}
+
+void intel_pt_interrupt(void)
+{
+ struct pt *pt = this_cpu_ptr(&pt_ctx);
+ struct pt_buffer *buf;
+ struct perf_event *event = pt->handle.event;
+
+ if (!ACCESS_ONCE(pt->handle_nmi))
+ return;
+
+ pt_config_start(false);
+
+ if (!event)
+ return;
+
+ buf = perf_get_aux(&pt->handle);
+ if (!buf)
+ return;
+
+ pt_read_offset(buf);
+
+ pt_handle_status(pt);
+
+ pt_update_head(pt);
+
+ perf_aux_output_end(&pt->handle, local_xchg(&buf->data_size, 0),
+ local_xchg(&buf->lost, 0));
+
+ if (!event->hw.state) {
+ int ret = pt_config(event);
+
+ if (ret) {
+ event->hw.state = PERF_HES_STOPPED;
+ return;
+ }
+
+ buf = perf_aux_output_begin(&pt->handle, event);
+ if (!buf) {
+ event->hw.state = PERF_HES_STOPPED;
+ return;
+ }
+
+ pt_buffer_reset_offsets(buf, pt->handle.head);
+ ret = pt_buffer_reset_markers(buf, &pt->handle);
+ if (ret) {
+ perf_aux_output_end(&pt->handle, 0, true);
+ return;
+ }
+
+ pt_config_buffer(buf->cur->table, buf->cur_idx,
+ buf->output_off);
+ wrmsrl(MSR_IA32_RTIT_STATUS, 0);
+ pt_config_start(true);
+ }
+}
+
+static void pt_event_start(struct perf_event *event, int mode)
+{
+ struct pt *pt = this_cpu_ptr(&pt_ctx);
+ struct pt_buffer *buf = perf_get_aux(&pt->handle);
+
+ if (pt_is_running() || !buf || pt_buffer_is_full(buf, pt) ||
+ pt_config(event)) {
+ event->hw.state = PERF_HES_STOPPED;
+ return;
+ }
+
+ ACCESS_ONCE(pt->handle_nmi) = 1;
+ event->hw.state = 0;
+
+ pt_config_buffer(buf->cur->table, buf->cur_idx,
+ buf->output_off);
+ wrmsrl(MSR_IA32_RTIT_STATUS, 0);
+ pt_config_start(true);
+}
+
+static void pt_event_stop(struct perf_event *event, int mode)
+{
+ struct pt *pt = this_cpu_ptr(&pt_ctx);
+
+ ACCESS_ONCE(pt->handle_nmi) = 0;
+ pt_config_start(false);
+
+ if (event->hw.state == PERF_HES_STOPPED)
+ return;
+
+ event->hw.state = PERF_HES_STOPPED;
+
+ if (mode & PERF_EF_UPDATE) {
+ struct pt *pt = this_cpu_ptr(&pt_ctx);
+ struct pt_buffer *buf = perf_get_aux(&pt->handle);
+
+ if (!buf)
+ return;
+
+ if (WARN_ON_ONCE(pt->handle.event != event))
+ return;
+
+ pt_read_offset(buf);
+
+ pt_handle_status(pt);
+
+ pt_update_head(pt);
+ }
+}
+
+static void pt_event_del(struct perf_event *event, int mode)
+{
+ struct pt *pt = this_cpu_ptr(&pt_ctx);
+ struct pt_buffer *buf;
+ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+ pt_event_stop(event, PERF_EF_UPDATE);
+
+ buf = perf_get_aux(&pt->handle);
+ cpuc->pt_enabled = 0;
+
+ if (buf) {
+ if (buf->snapshot)
+ pt->handle.head =
+ local_xchg(&buf->data_size,
+ buf->nr_pages << PAGE_SHIFT);
+ perf_aux_output_end(&pt->handle, local_xchg(&buf->data_size, 0),
+ local_xchg(&buf->lost, 0));
+ }
+}
+
+static int pt_event_add(struct perf_event *event, int mode)
+{
+ struct pt_buffer *buf;
+ struct pt *pt = this_cpu_ptr(&pt_ctx);
+ struct hw_perf_event *hwc = &event->hw;
+ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ int ret = -EBUSY;
+
+ if (cpuc->lbr_users || cpuc->bts_enabled)
+ goto out;
+
+ ret = pt_config(event);
+ if (ret) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ if (pt->handle.event) {
+ ret = -EBUSY;
+ goto out;
+ }
+
+ buf = perf_aux_output_begin(&pt->handle, event);
+ if (!buf) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ pt_buffer_reset_offsets(buf, pt->handle.head);
+ if (!buf->snapshot) {
+ ret = pt_buffer_reset_markers(buf, &pt->handle);
+ if (ret) {
+ perf_aux_output_end(&pt->handle, 0, true);
+ goto out;
+ }
+ }
+
+ if (mode & PERF_EF_START) {
+ pt_event_start(event, 0);
+ if (hwc->state == PERF_HES_STOPPED) {
+ pt_event_del(event, 0);
+ ret = -EBUSY;
+ }
+ } else {
+ hwc->state = PERF_HES_STOPPED;
+ }
+
+out:
+
+ if (ret)
+ hwc->state = PERF_HES_STOPPED;
+ else
+ cpuc->pt_enabled = 1;
+
+ return ret;
+}
+
+static void pt_event_read(struct perf_event *event)
+{
+}
+
+static int pt_event_init(struct perf_event *event)
+{
+ if (event->attr.type != pt_pmu.pmu.type)
+ return -ENOENT;
+
+ if (!pt_event_valid(event))
+ return -EINVAL;
+
+ return 0;
+}
+
+static __init int pt_init(void)
+{
+ int ret, cpu, prior_warn = 0;
+
+ BUILD_BUG_ON(sizeof(struct topa) > PAGE_SIZE);
+ get_online_cpus();
+ for_each_online_cpu(cpu) {
+ u64 ctl;
+
+ ret = rdmsrl_safe_on_cpu(cpu, MSR_IA32_RTIT_CTL, &ctl);
+ if (!ret && (ctl & RTIT_CTL_TRACEEN))
+ prior_warn++;
+ }
+ put_online_cpus();
+
+ ret = pt_pmu_hw_init();
+ if (ret)
+ return ret;
+
+ if (!pt_cap_get(PT_CAP_topa_output)) {
+ pr_warn("ToPA output is not supported on this CPU\n");
+ return -ENODEV;
+ }
+
+ if (prior_warn)
+ pr_warn("PT is enabled at boot time, traces may be empty\n");
+
+ if (!pt_cap_get(PT_CAP_topa_multiple_entries))
+ pt_pmu.pmu.capabilities =
+ PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_AUX_SW_DOUBLEBUF;
+
+ pt_pmu.pmu.capabilities |= PERF_PMU_CAP_EXCLUSIVE | PERF_PMU_CAP_ITRACE;
+ pt_pmu.pmu.attr_groups = pt_attr_groups;
+ pt_pmu.pmu.task_ctx_nr = perf_hw_context;
+ pt_pmu.pmu.event_init = pt_event_init;
+ pt_pmu.pmu.add = pt_event_add;
+ pt_pmu.pmu.del = pt_event_del;
+ pt_pmu.pmu.start = pt_event_start;
+ pt_pmu.pmu.stop = pt_event_stop;
+ pt_pmu.pmu.read = pt_event_read;
+ pt_pmu.pmu.setup_aux = pt_buffer_setup_aux;
+ pt_pmu.pmu.free_aux = pt_buffer_free_aux;
+ ret = perf_pmu_register(&pt_pmu.pmu, "intel_pt", -1);
+
+ return ret;
+}
+
+module_init(pt_init);
--
2.1.0

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/