Date:   Mon, 27 Nov 2017 11:49:10 +0100
From:   Ingo Molnar <mingo@...nel.org>
To:     linux-kernel@...r.kernel.org
Cc:     Dave Hansen <dave.hansen@...ux.intel.com>,
        Andy Lutomirski <luto@...capital.net>,
        Thomas Gleixner <tglx@...utronix.de>,
        "H . Peter Anvin" <hpa@...or.com>,
        Peter Zijlstra <peterz@...radead.org>,
        Borislav Petkov <bp@...en8.de>,
        Linus Torvalds <torvalds@...ux-foundation.org>
Subject: [PATCH 11/24] x86/mm/kaiser: Map virtually-addressed performance monitoring buffers

From: Hugh Dickins <hughd@...gle.com>

The BTS and PEBS buffers both have their virtual addresses
programmed into the hardware.  This means that any access to them
is performed via the page tables.  The times that the hardware
accesses these are entirely dependent on how the performance
monitoring hardware events are set up.  In other words, there is
no way for the kernel to tell when the hardware might access
these buffers.

To avoid perf crashes, place 'debug_store' in the user-mapped
per-CPU area instead of dynamically allocating.  Also use the
page allocator plus kaiser_add_mapping() to keep the BTS and PEBS
buffers user-mapped (that is, present in the user mapping, though
visible only to kernel and hardware).  The PEBS fixup buffer does
not need this treatment.

The need for a user-mapped struct debug_store showed up before doing
any conscious perf testing: in a couple of kernel paging oopses on
Westmere, implicating the debug_store offset of the per-CPU area.

[Dave] Added explicit _PAGE_GLOBAL
[Dave] Removed KAISER #ifdefs by moving kmalloc() to plain page allocator
[Dave] Reworded the commit message a bit to be consistent with other patches

Signed-off-by: Hugh Dickins <hughd@...gle.com>
Signed-off-by: Dave Hansen <dave.hansen@...ux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@...utronix.de>
Cc: Andy Lutomirski <luto@...nel.org>
Cc: Borislav Petkov <bp@...en8.de>
Cc: Brian Gerst <brgerst@...il.com>
Cc: Denys Vlasenko <dvlasenk@...hat.com>
Cc: H. Peter Anvin <hpa@...or.com>
Cc: Josh Poimboeuf <jpoimboe@...hat.com>
Cc: Linus Torvalds <torvalds@...ux-foundation.org>
Cc: Peter Zijlstra <peterz@...radead.org>
Cc: Rik van Riel <riel@...hat.com>
Cc: daniel.gruss@...k.tugraz.at
Cc: keescook@...gle.com
Cc: linux-mm@...ck.org
Cc: michael.schwarz@...k.tugraz.at
Cc: moritz.lipp@...k.tugraz.at
Cc: richard.fellner@...dent.tugraz.at
Link: https://lkml.kernel.org/r/20171123003500.7EC0DB4E@viggo.jf.intel.com
Signed-off-by: Ingo Molnar <mingo@...nel.org>
---
 arch/x86/events/intel/ds.c | 49 ++++++++++++++++++++++++++++++++++------------
 1 file changed, 37 insertions(+), 12 deletions(-)

diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 3674a4b6f8bd..b5cf473e443a 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/bitops.h>
 #include <linux/types.h>
+#include <linux/kaiser.h>
 #include <linux/slab.h>
 
 #include <asm/perf_event.h>
@@ -8,6 +9,9 @@
 
 #include "../perf_event.h"
 
+static
+DEFINE_PER_CPU_SHARED_ALIGNED_USER_MAPPED(struct debug_store, cpu_debug_store);
+
 /* The size of a BTS record in bytes: */
 #define BTS_RECORD_SIZE		24
 
@@ -279,6 +283,31 @@ void fini_debug_store_on_cpu(int cpu)
 
 static DEFINE_PER_CPU(void *, insn_buffer);
 
+static void *dsalloc(size_t size, gfp_t flags, int node)
+{
+	unsigned int order = get_order(size);
+	struct page *page;
+	unsigned long addr;
+
+	page = __alloc_pages_node(node, flags | __GFP_ZERO, order);
+	if (!page)
+		return NULL;
+	addr = (unsigned long)page_address(page);
+	if (kaiser_add_mapping(addr, size, __PAGE_KERNEL | _PAGE_GLOBAL) < 0) {
+		__free_pages(page, order);
+		addr = 0;
+	}
+	return (void *)addr;
+}
+
+static void dsfree(const void *buffer, size_t size)
+{
+	if (!buffer)
+		return;
+	kaiser_remove_mapping((unsigned long)buffer, size);
+	free_pages((unsigned long)buffer, get_order(size));
+}
+
 static int alloc_pebs_buffer(int cpu)
 {
 	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
@@ -289,7 +318,7 @@ static int alloc_pebs_buffer(int cpu)
 	if (!x86_pmu.pebs)
 		return 0;
 
-	buffer = kzalloc_node(x86_pmu.pebs_buffer_size, GFP_KERNEL, node);
+	buffer = dsalloc(x86_pmu.pebs_buffer_size, GFP_KERNEL, node);
 	if (unlikely(!buffer))
 		return -ENOMEM;
 
@@ -300,7 +329,7 @@ static int alloc_pebs_buffer(int cpu)
 	if (x86_pmu.intel_cap.pebs_format < 2) {
 		ibuffer = kzalloc_node(PEBS_FIXUP_SIZE, GFP_KERNEL, node);
 		if (!ibuffer) {
-			kfree(buffer);
+			dsfree(buffer, x86_pmu.pebs_buffer_size);
 			return -ENOMEM;
 		}
 		per_cpu(insn_buffer, cpu) = ibuffer;
@@ -326,7 +355,8 @@ static void release_pebs_buffer(int cpu)
 	kfree(per_cpu(insn_buffer, cpu));
 	per_cpu(insn_buffer, cpu) = NULL;
 
-	kfree((void *)(unsigned long)ds->pebs_buffer_base);
+	dsfree((void *)(unsigned long)ds->pebs_buffer_base,
+			x86_pmu.pebs_buffer_size);
 	ds->pebs_buffer_base = 0;
 }
 
@@ -340,7 +370,7 @@ static int alloc_bts_buffer(int cpu)
 	if (!x86_pmu.bts)
 		return 0;
 
-	buffer = kzalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, node);
+	buffer = dsalloc(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, node);
 	if (unlikely(!buffer)) {
 		WARN_ONCE(1, "%s: BTS buffer allocation failure\n", __func__);
 		return -ENOMEM;
@@ -366,19 +396,15 @@ static void release_bts_buffer(int cpu)
 	if (!ds || !x86_pmu.bts)
 		return;
 
-	kfree((void *)(unsigned long)ds->bts_buffer_base);
+	dsfree((void *)(unsigned long)ds->bts_buffer_base, BTS_BUFFER_SIZE);
 	ds->bts_buffer_base = 0;
 }
 
 static int alloc_ds_buffer(int cpu)
 {
-	int node = cpu_to_node(cpu);
-	struct debug_store *ds;
-
-	ds = kzalloc_node(sizeof(*ds), GFP_KERNEL, node);
-	if (unlikely(!ds))
-		return -ENOMEM;
+	struct debug_store *ds = per_cpu_ptr(&cpu_debug_store, cpu);
 
+	memset(ds, 0, sizeof(*ds));
 	per_cpu(cpu_hw_events, cpu).ds = ds;
 
 	return 0;
@@ -392,7 +418,6 @@ static void release_ds_buffer(int cpu)
 		return;
 
 	per_cpu(cpu_hw_events, cpu).ds = NULL;
-	kfree(ds);
 }
 
 void release_ds_buffers(void)
-- 
2.14.1

Powered by blists - more mailing lists