[patch V149 35/50] x86/fixmap: Add debugstore entries to cpu_entry_area

From: Thomas Gleixner
Date: Sat Dec 16 2017 - 16:42:22 EST


From: Thomas Gleixner <tglx@xxxxxxxxxxxxx>

The Intel PEBS/BTS debug store is a design trainwreck as is expects virtual
addresses which must be visible in any execution context.

So it is required to make these mappings visible to user space when kernel
page table isolation is active.

Provide enough room for the buffer mappings in the cpu_entry_area so the
buffers are available in the user space visible fixmap.

At the point where the kernel side fixmap is populated there is no buffer
available yet, but the kernel PMD must be populated. To achieve this set
the fixmap entries for these buffers to non present.

Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Boris Ostrovsky <boris.ostrovsky@xxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Brian Gerst <brgerst@xxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: David Laight <David.Laight@xxxxxxxxxx>
Cc: Denys Vlasenko <dvlasenk@xxxxxxxxxx>
Cc: Eduardo Valentin <eduval@xxxxxxxxxx>
Cc: Greg KH <gregkh@xxxxxxxxxxxxxxxxxxx>
Cc: H. Peter Anvin <hpa@xxxxxxxxx>
Cc: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>
Cc: Juergen Gross <jgross@xxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Will Deacon <will.deacon@xxxxxxx>
Cc: aliguori@xxxxxxxxxx
Cc: daniel.gruss@xxxxxxxxxxxxxx
Cc: hughd@xxxxxxxxxx
Cc: keescook@xxxxxxxxxx
---
arch/x86/events/intel/ds.c | 5 +++--
arch/x86/events/perf_event.h | 21 ++-------------------
arch/x86/include/asm/fixmap.h | 13 +++++++++++++
arch/x86/include/asm/intel_ds.h | 36 ++++++++++++++++++++++++++++++++++++
arch/x86/kernel/cpu/common.c | 21 +++++++++++++++++++++
5 files changed, 75 insertions(+), 21 deletions(-)

--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -8,11 +8,12 @@

#include "../perf_event.h"

+/* Waste a full page so it can be mapped into the cpu_entry_area */
+DEFINE_PER_CPU_PAGE_ALIGNED(struct debug_store, cpu_debug_store);
+
/* 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 << 4)
#define PEBS_FIXUP_SIZE PAGE_SIZE

/*
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -14,6 +14,8 @@

#include <linux/perf_event.h>

+#include <asm/intel_ds.h>
+
/* To enable MSR tracing please use the generic trace points. */

/*
@@ -77,8 +79,6 @@ struct amd_nb {
struct event_constraint event_constraints[X86_PMC_IDX_MAX];
};

-/* The maximal number of PEBS events: */
-#define MAX_PEBS_EVENTS 8
#define PEBS_COUNTER_MASK ((1ULL << MAX_PEBS_EVENTS) - 1)

/*
@@ -95,23 +95,6 @@ struct amd_nb {
PERF_SAMPLE_TRANSACTION | PERF_SAMPLE_PHYS_ADDR | \
PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER)

-/*
- * 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];
-};
-
#define PEBS_REGS \
(PERF_REG_X86_AX | \
PERF_REG_X86_BX | \
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -19,6 +19,7 @@
#include <asm/acpi.h>
#include <asm/apicdef.h>
#include <asm/page.h>
+#include <asm/intel_ds.h>
#ifdef CONFIG_X86_32
#include <linux/threads.h>
#include <asm/kmap_types.h>
@@ -78,6 +79,18 @@ struct cpu_entry_area {
*/
char exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ];
#endif
+#ifdef CONFIG_CPU_SUP_INTEL
+ /*
+ * Per CPU debug store for Intel performance monitoring. Wastes a
+ * full page at the moment.
+ */
+ struct debug_store cpu_debug_store;
+ /*
+ * The actual PEBS/BTS buffers must be mapped to user space
+ * Reserve enough fixmap PTEs.
+ */
+ struct debug_store_buffers cpu_debug_buffers;
+#endif
};

#define CPU_ENTRY_AREA_PAGES (sizeof(struct cpu_entry_area) / PAGE_SIZE)
--- /dev/null
+++ b/arch/x86/include/asm/intel_ds.h
@@ -0,0 +1,36 @@
+#ifndef _ASM_INTEL_DS_H
+#define _ASM_INTEL_DS_H
+
+#include <linux/percpu-defs.h>
+
+#define BTS_BUFFER_SIZE (PAGE_SIZE << 4)
+#define PEBS_BUFFER_SIZE (PAGE_SIZE << 4)
+
+/* The maximal number of PEBS events: */
+#define MAX_PEBS_EVENTS 8
+
+/*
+ * 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];
+} __aligned(PAGE_SIZE);
+
+DECLARE_PER_CPU_PAGE_ALIGNED(struct debug_store, cpu_debug_store);
+
+struct debug_store_buffers {
+ char bts_buffer[BTS_BUFFER_SIZE];
+ char pebs_buffer[PEBS_BUFFER_SIZE];
+};
+
+#endif
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -31,6 +31,7 @@
#include <linux/cpumask.h>
#include <asm/pgtable.h>
#include <linux/atomic.h>
+#include <asm/intel_ds.h>
#include <asm/proto.h>
#include <asm/setup.h>
#include <asm/apic.h>
@@ -514,6 +515,16 @@ static DEFINE_PER_CPU_PAGE_ALIGNED(char,
static DEFINE_PER_CPU_PAGE_ALIGNED(struct entry_stack_page,
entry_stack_storage);

+/*
+ * Force the population of PMDs for not yet allocated per cpu
+ * memory like debug store buffers.
+ */
+static void __init set_percpu_fixmap_ptes(int idx, int pages)
+{
+ for (; pages; pages--, idx--)
+ __set_fixmap(idx, 0, PAGE_NONE);
+}
+
static void __init
set_percpu_fixmap_pages(int idx, void *ptr, int pages, pgprot_t prot)
{
@@ -592,6 +603,16 @@ static void __init setup_cpu_entry_area(
__set_fixmap(get_cpu_entry_area_index(cpu, entry_trampoline),
__pa_symbol(_entry_trampoline), PAGE_KERNEL_RX);
#endif
+
+#ifdef CONFIG_CPU_SUP_INTEL
+ BUILD_BUG_ON(sizeof(struct debug_store) % PAGE_SIZE != 0);
+ set_percpu_fixmap_pages(get_cpu_entry_area_index(cpu, cpu_debug_store),
+ &per_cpu(cpu_debug_store, cpu),
+ sizeof(struct debug_store) / PAGE_SIZE,
+ PAGE_KERNEL);
+ set_percpu_fixmap_ptes(get_cpu_entry_area_index(cpu, cpu_debug_buffers),
+ sizeof(struct debug_store_buffers) / PAGE_SIZE);
+#endif
}

void __init setup_cpu_entry_areas(void)