| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <1360951381-26313-1-git-send-email-roger.pau@citrix.com>
Date: Fri, 15 Feb 2013 19:03:01 +0100
From: Roger Pau Monne <roger.pau@...rix.com>
To: <linux-kernel@...r.kernel.org>
CC: Roger Pau Monne <roger.pau@...rix.com>,
Konrad Rzeszutek Wilk <konrad.wilk@...cle.com>,
<xen-devel@...ts.xen.org>
Subject: [PATCH] xen-blkfront: switch from llist to list
Replace the use of llist with list.
llist_for_each_entry_safe can trigger a bug in GCC 4.1, so it's best
to remove it and use a doubly linked list, which is used extensively
in the kernel already.
Specifically this bug can be triggered by hot-unplugging a disk,
either by doing xm block-detach or by save/restore cycle.
BUG: unable to handle kernel paging request at fffffffffffffff0
IP: [<ffffffffa0047223>] blkif_free+0x63/0x130 [xen_blkfront]
The crash call trace is:
...
bad_area_nosemaphore+0x13/0x20
do_page_fault+0x25e/0x4b0
page_fault+0x25/0x30
? blkif_free+0x63/0x130 [xen_blkfront]
blkfront_resume+0x46/0xa0 [xen_blkfront]
xenbus_dev_resume+0x6c/0x140
pm_op+0x192/0x1b0
device_resume+0x82/0x1e0
dpm_resume+0xc9/0x1a0
dpm_resume_end+0x15/0x30
do_suspend+0x117/0x1e0
When drilling down to the assembler code, on newer GCC it does
.L29:
cmpq $-16, %r12 #, persistent_gnt check
je .L30 #, out of the loop
.L25:
... code in the loop
testq %r13, %r13 # n
je .L29 #, back to the top of the loop
cmpq $-16, %r12 #, persistent_gnt check
movq 16(%r12), %r13 # <variable>.node.next, n
jne .L25 #, back to the top of the loop
.L30:
While on GCC 4.1, it is:
L78:
... code in the loop
testq %r13, %r13 # n
je .L78 #, back to the top of the loop
movq 16(%rbx), %r13 # <variable>.node.next, n
jmp .L78 #, back to the top of the loop
Which basically means that the exit loop condition instead of
being:
&(pos)->member != NULL;
is:
;
which makes the loop unbound.
Since we always manipulate the list while holding the io_lock, there's
no need for additional locking (llist used previously is safe to use
concurrently without additional locking).
Should be backported to 3.8 stable.
Signed-off-by: Roger Pau Monné <roger.pau@...rix.com>
[Part of the description]
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@...cle.com>
Cc: xen-devel@...ts.xen.org
---
drivers/block/xen-blkfront.c | 27 ++++++++++++++-------------
include/linux/llist.h | 25 -------------------------
2 files changed, 14 insertions(+), 38 deletions(-)
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 11043c1..01b91a5 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -44,7 +44,7 @@
#include <linux/mutex.h>
#include <linux/scatterlist.h>
#include <linux/bitmap.h>
-#include <linux/llist.h>
+#include <linux/list.h>
#include <xen/xen.h>
#include <xen/xenbus.h>
@@ -68,7 +68,7 @@ enum blkif_state {
struct grant {
grant_ref_t gref;
unsigned long pfn;
- struct llist_node node;
+ struct list_head node;
};
struct blk_shadow {
@@ -105,7 +105,7 @@ struct blkfront_info
struct work_struct work;
struct gnttab_free_callback callback;
struct blk_shadow shadow[BLK_RING_SIZE];
- struct llist_head persistent_gnts;
+ struct list_head persistent_gnts;
unsigned int persistent_gnts_c;
unsigned long shadow_free;
unsigned int feature_flush;
@@ -371,10 +371,11 @@ static int blkif_queue_request(struct request *req)
lsect = fsect + (sg->length >> 9) - 1;
if (info->persistent_gnts_c) {
- BUG_ON(llist_empty(&info->persistent_gnts));
- gnt_list_entry = llist_entry(
- llist_del_first(&info->persistent_gnts),
- struct grant, node);
+ BUG_ON(list_empty(&info->persistent_gnts));
+ gnt_list_entry = list_first_entry(
+ &info->persistent_gnts,
+ struct grant, node);
+ list_del(&gnt_list_entry->node);
ref = gnt_list_entry->gref;
buffer_mfn = pfn_to_mfn(gnt_list_entry->pfn);
@@ -790,9 +791,8 @@ static void blkif_restart_queue(struct work_struct *work)
static void blkif_free(struct blkfront_info *info, int suspend)
{
- struct llist_node *all_gnts;
struct grant *persistent_gnt;
- struct llist_node *n;
+ struct grant *n;
/* Prevent new requests being issued until we fix things up. */
spin_lock_irq(&info->io_lock);
@@ -804,8 +804,9 @@ static void blkif_free(struct blkfront_info *info, int suspend)
/* Remove all persistent grants */
if (info->persistent_gnts_c) {
- all_gnts = llist_del_all(&info->persistent_gnts);
- llist_for_each_entry_safe(persistent_gnt, n, all_gnts, node) {
+ list_for_each_entry_safe(persistent_gnt, n,
+ &info->persistent_gnts, node) {
+ list_del(&persistent_gnt->node);
gnttab_end_foreign_access(persistent_gnt->gref, 0, 0UL);
__free_page(pfn_to_page(persistent_gnt->pfn));
kfree(persistent_gnt);
@@ -868,7 +869,7 @@ static void blkif_completion(struct blk_shadow *s, struct blkfront_info *info,
}
/* Add the persistent grant into the list of free grants */
for (i = 0; i < s->req.u.rw.nr_segments; i++) {
- llist_add(&s->grants_used[i]->node, &info->persistent_gnts);
+ list_add(&s->grants_used[i]->node, &info->persistent_gnts);
info->persistent_gnts_c++;
}
}
@@ -1164,7 +1165,7 @@ static int blkfront_probe(struct xenbus_device *dev,
spin_lock_init(&info->io_lock);
info->xbdev = dev;
info->vdevice = vdevice;
- init_llist_head(&info->persistent_gnts);
+ INIT_LIST_HEAD(&info->persistent_gnts);
info->persistent_gnts_c = 0;
info->connected = BLKIF_STATE_DISCONNECTED;
INIT_WORK(&info->work, blkif_restart_queue);
diff --git a/include/linux/llist.h b/include/linux/llist.h
index d0ab98f..a5199f6 100644
--- a/include/linux/llist.h
+++ b/include/linux/llist.h
@@ -125,31 +125,6 @@ static inline void init_llist_head(struct llist_head *list)
(pos) = llist_entry((pos)->member.next, typeof(*(pos)), member))
/**
- * llist_for_each_entry_safe - iterate safely against remove over some entries
- * of lock-less list of given type.
- * @pos: the type * to use as a loop cursor.
- * @n: another type * to use as a temporary storage.
- * @node: the fist entry of deleted list entries.
- * @member: the name of the llist_node with the struct.
- *
- * In general, some entries of the lock-less list can be traversed
- * safely only after being removed from list, so start with an entry
- * instead of list head. This variant allows removal of entries
- * as we iterate.
- *
- * If being used on entries deleted from lock-less list directly, the
- * traverse order is from the newest to the oldest added entry. If
- * you want to traverse from the oldest to the newest, you must
- * reverse the order by yourself before traversing.
- */
-#define llist_for_each_entry_safe(pos, n, node, member) \
- for ((pos) = llist_entry((node), typeof(*(pos)), member), \
- (n) = (pos)->member.next; \
- &(pos)->member != NULL; \
- (pos) = llist_entry(n, typeof(*(pos)), member), \
- (n) = (&(pos)->member != NULL) ? (pos)->member.next : NULL)
-
-/**
* llist_empty - tests whether a lock-less list is empty
* @head: the list to test
*
--
1.7.7.5 (Apple Git-26)
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists