This is a note to let you know that I've just added the patch titled
kaiser: fix perf crashes
to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
kaiser-fix-perf-crashes.patch
and it can be found in the queue-4.9 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From foo@baz Wed Jan 3 20:37:21 CET 2018
From: Hugh Dickins <hughd@xxxxxxxxxx>
Date: Wed, 23 Aug 2017 14:21:14 -0700
Subject: kaiser: fix perf crashes
From: Hugh Dickins <hughd@xxxxxxxxxx>
Avoid perf crashes: place debug_store in the user-mapped per-cpu area
instead of allocating, and use 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.
Signed-off-by: Hugh Dickins <hughd@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
arch/x86/events/intel/ds.c | 57 +++++++++++++++++++++++++++++++++++----------
1 file changed, 45 insertions(+), 12 deletions(-)
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -2,11 +2,15 @@
#include <linux/types.h>
#include <linux/slab.h>
+#include <asm/kaiser.h>
#include <asm/perf_event.h>
#include <asm/insn.h>
#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
@@ -268,6 +272,39 @@ 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)
+{
+#ifdef CONFIG_KAISER
+ 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) < 0) {
+ __free_pages(page, order);
+ addr = 0;
+ }
+ return (void *)addr;
+#else
+ return kmalloc_node(size, flags | __GFP_ZERO, node);
+#endif
+}
+
+static void dsfree(const void *buffer, size_t size)
+{
+#ifdef CONFIG_KAISER
+ if (!buffer)
+ return;
+ kaiser_remove_mapping((unsigned long)buffer, size);
+ free_pages((unsigned long)buffer, get_order(size));
+#else
+ kfree(buffer);
+#endif
+}
+
static int alloc_pebs_buffer(int cpu)
{
struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
@@ -278,7 +315,7 @@ 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;
@@ -289,7 +326,7 @@ 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;
@@ -315,7 +352,8 @@ 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;
}
@@ -329,7 +367,7 @@ 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;
@@ -355,19 +393,15 @@ 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;
@@ -381,7 +415,6 @@ static void release_ds_buffer(int cpu)
return;
per_cpu(cpu_hw_events, cpu).ds = NULL;
- kfree(ds);
}
void release_ds_buffers(void)
Patches currently in stable-queue which might be from hughd@xxxxxxxxxx are
queue-4.9/kaiser-vmstat-show-nr_kaisertable-as-nr_overhead.patch
queue-4.9/kaiser-add-nokaiser-boot-option-using-alternative.patch
queue-4.9/kaiser-fix-unlikely-error-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kaiser_flush_tlb_on_return_to_user-check-pcid.patch
queue-4.9/x86-paravirt-dont-patch-flush_tlb_single.patch
queue-4.9/kaiser-merged-update.patch
queue-4.9/kaiser-delete-kaiser_real_switch-option.patch
queue-4.9/kaiser-kaiser_remove_mapping-move-along-the-pgd.patch
queue-4.9/kaiser-fix-perf-crashes.patch
queue-4.9/kaiser-drop-is_atomic-arg-to-kaiser_pagetable_walk.patch
queue-4.9/kaiser-load_new_mm_cr3-let-switch_user_cr3-flush-user.patch
queue-4.9/kaiser-enhanced-by-kernel-and-user-pcids.patch
queue-4.9/kaiser-x86_cr3_pcid_noflush-and-x86_cr3_pcid_user.patch
queue-4.9/kaiser-align-addition-to-x86-mm-makefile.patch
queue-4.9/kaiser-use-alternative-instead-of-x86_cr3_pcid_noflush.patch
queue-4.9/kaiser-stack-map-page_size-at-thread_size-page_size.patch
queue-4.9/kaiser-name-that-0x1000-kaiser_shadow_pgd_offset.patch
queue-4.9/kaiser-fix-regs-to-do_nmi-ifndef-config_kaiser.patch
queue-4.9/kaiser-do-not-set-_page_nx-on-pgd_none.patch
queue-4.9/kaiser-tidied-up-asm-kaiser.h-somewhat.patch
queue-4.9/kaiser-cleanups-while-trying-for-gold-link.patch
queue-4.9/kaiser-tidied-up-kaiser_add-remove_mapping-slightly.patch
queue-4.9/kaiser-fix-build-and-fixme-in-alloc_ldt_struct.patch
queue-4.9/kaiser-kernel-address-isolation.patch
queue-4.9/kaiser-enomem-if-kaiser_pagetable_walk-null.patch
queue-4.9/kaiser-asm-tlbflush.h-handle-nopge-at-lower-level.patch
queue-4.9/kaiser-paranoid_entry-pass-cr3-need-to-paranoid_exit.patch
queue-4.9/kaiser-kaiser-depends-on-smp.patch
queue-4.9/kaiser-pcid-0-for-kernel-and-128-for-user.patch