From: Thomas Gleixner <tglx@linutronix.de>
To: LKML <linux-kernel@vger.kernel.org>
Cc: x86@kernel.org, Linus Torvalds <torvalds@linux-foundation.org>,
Andy Lutomirsky <luto@kernel.org>,
Peter Zijlstra <peterz@infradead.org>,
Dave Hansen <dave.hansen@intel.com>,
Borislav Petkov <bpetkov@suse.de>,
Greg KH <gregkh@linuxfoundation.org>,
keescook@google.com, hughd@google.com,
Brian Gerst <brgerst@gmail.com>,
Josh Poimboeuf <jpoimboe@redhat.com>,
Denys Vlasenko <dvlasenk@redhat.com>,
Rik van Riel <riel@redhat.com>,
Boris Ostrovsky <boris.ostrovsky@oracle.com>,
Juergen Gross <jgross@suse.com>,
David Laight <David.Laight@aculab.com>,
Eduardo Valentin <eduval@amazon.com>,
aliguori@amazon.com, Will Deacon <will.deacon@arm.com>,
daniel.gruss@iaik.tugraz.at, Ingo Molnar <mingo@kernel.org>,
Borislav Petkov <bp@alien8.de>,
Dave Hansen <dave.hansen@linux.intel.com>,
"H. Peter Anvin" <hpa@zytor.com>
Subject: [patch V149 35/50] x86/fixmap: Add debugstore entries to cpu_entry_area
Date: Sat, 16 Dec 2017 22:24:29 +0100 [thread overview]
Message-ID: <20171216213139.309098390@linutronix.de> (raw)
In-Reply-To: <20171216212354.120930222@linutronix.de>
[-- Attachment #1: 0043-x86-fixmap-Add-debugstore-entries-to-cpu_entry_area.patch --]
[-- Type: text/plain, Size: 6420 bytes --]
From: Thomas Gleixner <tglx@linutronix.de>
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@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
---
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)
next prev parent reply other threads:[~2017-12-16 21:42 UTC|newest]
Thread overview: 53+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-12-16 21:23 [patch V149 00/50] x86/pti: Updated and reshuffled patch queue Thomas Gleixner
2017-12-16 21:23 ` [patch V149 01/50] x86/mm/dump_pagetables: Check PAGE_PRESENT for real Thomas Gleixner
2017-12-16 21:23 ` [patch V149 02/50] x86/vsyscall/64: Explicitly set _PAGE_USER in the pagetable hierarchy Thomas Gleixner
2017-12-16 21:23 ` [patch V149 03/50] x86/vsyscall/64: Warn and fail vsyscall emulation in NATIVE mode Thomas Gleixner
2017-12-16 21:23 ` [patch V149 04/50] arch: Allow arch_dup_mmap() to fail Thomas Gleixner
2017-12-16 21:23 ` [patch V149 05/50] x86/ldt: Rework locking Thomas Gleixner
2017-12-16 21:24 ` [patch V149 06/50] x86/ldt: Prevent ldt inheritance on exec Thomas Gleixner
2017-12-16 21:24 ` [patch V149 07/50] x86/mm/64: Improve the memory map documentation Thomas Gleixner
2017-12-16 21:24 ` [patch V149 08/50] x86/doc: Remove obvious weirdness Thomas Gleixner
2017-12-16 21:24 ` [patch V149 09/50] x86/entry: Remove SYSENTER_stack naming Thomas Gleixner
2017-12-16 21:24 ` [patch V149 10/50] x86/uv: Use the right tlbflush API Thomas Gleixner
2017-12-16 21:24 ` [patch V149 11/50] x86/microcode: Dont abuse the tlbflush interface Thomas Gleixner
2017-12-16 21:24 ` [patch V149 12/50] x86/mm: Use __flush_tlb_one() for kernel memory Thomas Gleixner
2017-12-16 21:24 ` [patch V149 13/50] x86/mm: Remove superfluous barriers Thomas Gleixner
2017-12-16 21:24 ` [patch V149 14/50] x86/mm: Clarify which functions are supposed to flush what Thomas Gleixner
2017-12-16 21:24 ` [patch V149 15/50] x86/mm: Move the CR3 construction functions to tlbflush.h Thomas Gleixner
2017-12-16 21:24 ` [patch V149 16/50] x86/mm: Remove hard-coded ASID limit checks Thomas Gleixner
2017-12-16 21:24 ` [patch V149 17/50] x86/mm: Put MMU to hardware ASID translation in one place Thomas Gleixner
2017-12-16 21:24 ` [patch V149 18/50] x86/mm: Create asm/invpcid.h Thomas Gleixner
2017-12-16 21:24 ` [patch V149 19/50] x86/cpufeatures: Add X86_BUG_CPU_INSECURE Thomas Gleixner
2017-12-16 21:24 ` [patch V149 20/50] x86/mm/pti: Disable global pages if PAGE_TABLE_ISOLATION=y Thomas Gleixner
2017-12-16 21:24 ` [patch V149 21/50] x86/mm/pti: Prepare the x86/entry assembly code for entry/exit CR3 switching Thomas Gleixner
2017-12-16 21:24 ` [patch V149 22/50] x86/mm/pti: Add infrastructure for page table isolation Thomas Gleixner
2017-12-16 21:24 ` [patch V149 23/50] x86/mm/pti: Add mapping helper functions Thomas Gleixner
2017-12-16 21:24 ` [patch V149 24/50] x86/mm/pti: Allow NX poison to be set in p4d/pgd Thomas Gleixner
2017-12-16 21:24 ` [patch V149 25/50] x86/mm/pti: Allocate a separate user PGD Thomas Gleixner
2017-12-16 21:24 ` [patch V149 26/50] x86/mm/pti: Populate " Thomas Gleixner
2017-12-16 21:24 ` [patch V149 27/50] x86/mm/pti: Add functions to clone kernel PMDs Thomas Gleixner
2017-12-16 21:24 ` [patch V149 28/50] x86/mm/pti: Force entry through trampoline when PTI active Thomas Gleixner
2017-12-16 21:24 ` [patch V149 29/50] x86/fixmap: Move the CPU entry area into a separate PMD Thomas Gleixner
2017-12-16 21:24 ` [patch V149 30/50] x86/mm/pti: Share cpu_entry_area PMDs Thomas Gleixner
2017-12-16 21:24 ` [patch V149 31/50] x86/entry: Align entry text section to PMD boundary Thomas Gleixner
2017-12-16 21:24 ` [patch V149 32/50] x86/mm/pti: Share entry text PMD Thomas Gleixner
2017-12-16 21:24 ` [patch V149 33/50] x86/mm/pti: Map ESPFIX into user space Thomas Gleixner
2017-12-16 21:24 ` [patch V149 34/50] x86/fixmap: Move IDT fixmap into the cpu_entry_area range Thomas Gleixner
2017-12-16 21:24 ` Thomas Gleixner [this message]
2017-12-16 21:24 ` [patch V149 36/50] x86/events/intel/ds: Map debug buffers in fixmap Thomas Gleixner
2017-12-16 21:24 ` [patch V149 37/50] x86/mm/64: Make a full PGD-entry size hole in the memory map Thomas Gleixner
2017-12-17 11:07 ` Kirill A. Shutemov
2017-12-16 21:24 ` [patch V149 38/50] x86/pti: Put the LDT in its own PGD if PTI is on Thomas Gleixner
2017-12-17 11:09 ` Kirill A. Shutemov
2017-12-16 21:24 ` [patch V149 39/50] x86/pti: Map the vsyscall page if needed Thomas Gleixner
2017-12-16 21:24 ` [patch V149 40/50] x86/mm: Allow flushing for future ASID switches Thomas Gleixner
2017-12-16 21:24 ` [patch V149 41/50] x86/mm: Abstract switching CR3 Thomas Gleixner
2017-12-16 21:24 ` [patch V149 42/50] x86/mm: Use/Fix PCID to optimize user/kernel switches Thomas Gleixner
2017-12-16 21:24 ` [patch V149 43/50] x86/mm: Optimize RESTORE_CR3 Thomas Gleixner
2017-12-16 21:24 ` [patch V149 44/50] x86/mm: Use INVPCID for __native_flush_tlb_single() Thomas Gleixner
2017-12-16 21:24 ` [patch V149 45/50] x86/mm: Clarify the whole ASID/kernel PCID/user PCID naming Thomas Gleixner
2017-12-16 21:24 ` [patch V149 46/50] x86/mm/pti: Add Kconfig Thomas Gleixner
2017-12-16 21:24 ` [patch V149 47/50] x86/mm/dump_pagetables: Add page table directory Thomas Gleixner
2017-12-16 21:24 ` [patch V149 48/50] x86/mm/dump_pagetables: Check user space page table for WX pages Thomas Gleixner
2017-12-16 21:24 ` [patch V149 49/50] x86/mm/dump_pagetables: Allow dumping current pagetables Thomas Gleixner
2017-12-16 21:24 ` [patch V149 50/50] x86/ldt: Make the LDT mapping RO Thomas Gleixner
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20171216213139.309098390@linutronix.de \
--to=tglx@linutronix.de \
--cc=David.Laight@aculab.com \
--cc=aliguori@amazon.com \
--cc=boris.ostrovsky@oracle.com \
--cc=bp@alien8.de \
--cc=bpetkov@suse.de \
--cc=brgerst@gmail.com \
--cc=daniel.gruss@iaik.tugraz.at \
--cc=dave.hansen@intel.com \
--cc=dave.hansen@linux.intel.com \
--cc=dvlasenk@redhat.com \
--cc=eduval@amazon.com \
--cc=gregkh@linuxfoundation.org \
--cc=hpa@zytor.com \
--cc=hughd@google.com \
--cc=jgross@suse.com \
--cc=jpoimboe@redhat.com \
--cc=keescook@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=luto@kernel.org \
--cc=mingo@kernel.org \
--cc=peterz@infradead.org \
--cc=riel@redhat.com \
--cc=torvalds@linux-foundation.org \
--cc=will.deacon@arm.com \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
Powered by JetHome