3.4-stable review patch. If anyone has any objections, please let me know.
------------------
From: Matt Wilson <m...@amazon.com>
commit d0b4d64aadb9f4a90669848de9ef3819050a98cd upstream.
Commit 85ff6acb075a484780b3d763fdf41596d8fc0970 (xen/granttable: Grant
tables V2 implementation) changed the GREFS_PER_GRANT_FRAME macro from
a constant to a conditional expression. The expression depends on
grant_table_version being appropriately set. Unfortunately, at init
time grant_table_version will be 0. The GREFS_PER_GRANT_FRAME
conditional expression checks for "grant_table_version == 1", and
therefore returns the number of grant references per frame for v2.
This causes gnttab_init() to allocate fewer pages for gnttab_list, as
a frame can old half the number of v2 entries than v1 entries. After
gnttab_resume() is called, grant_table_version is appropriately
set. nr_init_grefs will then be miscalculated and gnttab_free_count
will hold a value larger than the actual number of free gref entries.
If a guest is heavily utilizing improperly initialized v1 grant
tables, memory corruption can occur. One common manifestation is
corruption of the vmalloc list, resulting in a poisoned pointer
derefrence when accessing /proc/meminfo or /proc/vmallocinfo:
[ 40.770064] BUG: unable to handle kernel paging request at 0000200200001407
[ 40.770083] IP: [<ffffffff811a6fb0>] get_vmalloc_info+0x70/0x110
[ 40.770102] PGD 0
[ 40.770107] Oops: 0000 [#1] SMP
[ 40.770114] CPU 10
This patch introduces a static variable, grefs_per_grant_frame, to
cache the calculated value. gnttab_init() now calls
gnttab_request_version() early so that grant_table_version and
grefs_per_grant_frame can be appropriately set. A few BUG_ON()s have
been added to prevent this type of bug from reoccurring in the future.
Signed-off-by: Matt Wilson <m...@amazon.com>
Reviewed-and-Tested-by: Steven Noonan <snoo...@amazon.com>
Acked-by: Ian Campbell <ian.campb...@citrix.com>
Cc: Konrad Rzeszutek Wilk <konrad.w...@oracle.com>
Cc: Annie Li <annie...@oracle.com>
Cc: xen-de...@lists.xen.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Konrad Rzeszutek Wilk <konrad.w...@oracle.com>
Signed-off-by: Greg Kroah-Hartman <gre...@linuxfoundation.org>
---
drivers/xen/grant-table.c | 48 +++++++++++++++++++++++++++-------------------
1 file changed, 29 insertions(+), 19 deletions(-)
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -53,10 +53,6 @@
/* External tools reserve first few grant table entries. */
#define NR_RESERVED_ENTRIES 8
#define GNTTAB_LIST_END 0xffffffff
-#define GREFS_PER_GRANT_FRAME \
-(grant_table_version == 1 ? \
-(PAGE_SIZE / sizeof(struct grant_entry_v1)) : \
-(PAGE_SIZE / sizeof(union grant_entry_v2)))
static grant_ref_t **gnttab_list;
static unsigned int nr_grant_frames;
@@ -151,6 +147,7 @@ static struct gnttab_ops *gnttab_interfa
static grant_status_t *grstatus;
static int grant_table_version;
+static int grefs_per_grant_frame;
static struct gnttab_free_callback *gnttab_free_callback_list;
@@ -679,12 +676,14 @@ static int grow_gnttab_list(unsigned int
unsigned int new_nr_grant_frames, extra_entries, i;
unsigned int nr_glist_frames, new_nr_glist_frames;
+ BUG_ON(grefs_per_grant_frame == 0);
+
new_nr_grant_frames = nr_grant_frames + more_frames;
- extra_entries = more_frames * GREFS_PER_GRANT_FRAME;
+ extra_entries = more_frames * grefs_per_grant_frame;
- nr_glist_frames = (nr_grant_frames * GREFS_PER_GRANT_FRAME + RPP - 1) /
RPP;
+ nr_glist_frames = (nr_grant_frames * grefs_per_grant_frame + RPP - 1) /
RPP;
new_nr_glist_frames =
- (new_nr_grant_frames * GREFS_PER_GRANT_FRAME + RPP - 1) / RPP;
+ (new_nr_grant_frames * grefs_per_grant_frame + RPP - 1) / RPP;
for (i = nr_glist_frames; i < new_nr_glist_frames; i++) {
gnttab_list[i] = (grant_ref_t *)__get_free_page(GFP_ATOMIC);
if (!gnttab_list[i])
@@ -692,12 +691,12 @@ static int grow_gnttab_list(unsigned int
}
- for (i = GREFS_PER_GRANT_FRAME * nr_grant_frames;
- i < GREFS_PER_GRANT_FRAME * new_nr_grant_frames - 1; i++)
+ for (i = grefs_per_grant_frame * nr_grant_frames;
+ i < grefs_per_grant_frame * new_nr_grant_frames - 1; i++)
gnttab_entry(i) = i + 1;
gnttab_entry(i) = gnttab_free_head;
- gnttab_free_head = GREFS_PER_GRANT_FRAME * nr_grant_frames;
+ gnttab_free_head = grefs_per_grant_frame * nr_grant_frames;
gnttab_free_count += extra_entries;
nr_grant_frames = new_nr_grant_frames;
@@ -799,7 +798,8 @@ EXPORT_SYMBOL_GPL(gnttab_unmap_refs);
static unsigned nr_status_frames(unsigned nr_grant_frames)
{
- return (nr_grant_frames * GREFS_PER_GRANT_FRAME + SPP - 1) / SPP;
+ BUG_ON(grefs_per_grant_frame == 0);
+ return (nr_grant_frames * grefs_per_grant_frame + SPP - 1) / SPP;
}
static int gnttab_map_frames_v1(unsigned long *frames, unsigned int nr_gframes)
@@ -957,6 +957,7 @@ static void gnttab_request_version(void)
rc = HYPERVISOR_grant_table_op(GNTTABOP_set_version, &gsv, 1);
if (rc == 0 && gsv.version == 2) {
grant_table_version = 2;
+ grefs_per_grant_frame = PAGE_SIZE / sizeof(union
grant_entry_v2);
gnttab_interface = &gnttab_v2_ops;
} else if (grant_table_version == 2) {
/*
@@ -969,17 +970,17 @@ static void gnttab_request_version(void)
panic("we need grant tables version 2, but only version 1 is
available");
} else {
grant_table_version = 1;
+ grefs_per_grant_frame = PAGE_SIZE / sizeof(struct
grant_entry_v1);
gnttab_interface = &gnttab_v1_ops;
}
printk(KERN_INFO "Grant tables using version %d layout.\n",
grant_table_version);
}
-int gnttab_resume(void)
+static int gnttab_setup(void)
{
unsigned int max_nr_gframes;
- gnttab_request_version();
max_nr_gframes = gnttab_max_grant_frames();
if (max_nr_gframes < nr_grant_frames)
return -ENOSYS;
@@ -1002,6 +1003,12 @@ int gnttab_resume(void)
return 0;
}
+int gnttab_resume(void)
+{
+ gnttab_request_version();
+ return gnttab_setup();
+}
+
int gnttab_suspend(void)
{
gnttab_interface->unmap_frames();
@@ -1013,9 +1020,10 @@ static int gnttab_expand(unsigned int re
int rc;
unsigned int cur, extra;
+ BUG_ON(grefs_per_grant_frame == 0);
cur = nr_grant_frames;
- extra = ((req_entries + (GREFS_PER_GRANT_FRAME-1)) /
- GREFS_PER_GRANT_FRAME);
+ extra = ((req_entries + (grefs_per_grant_frame-1)) /
+ grefs_per_grant_frame);
if (cur + extra > gnttab_max_grant_frames())
return -ENOSPC;
@@ -1033,21 +1041,23 @@ int gnttab_init(void)
unsigned int nr_init_grefs;
int ret;
+ gnttab_request_version();
nr_grant_frames = 1;
boot_max_nr_grant_frames = __max_nr_grant_frames();
/* Determine the maximum number of frames required for the
* grant reference free list on the current hypervisor.
*/
+ BUG_ON(grefs_per_grant_frame == 0);
max_nr_glist_frames = (boot_max_nr_grant_frames *
- GREFS_PER_GRANT_FRAME / RPP);
+ grefs_per_grant_frame / RPP);
gnttab_list = kmalloc(max_nr_glist_frames * sizeof(grant_ref_t *),
GFP_KERNEL);
if (gnttab_list == NULL)
return -ENOMEM;
- nr_glist_frames = (nr_grant_frames * GREFS_PER_GRANT_FRAME + RPP - 1) /
RPP;
+ nr_glist_frames = (nr_grant_frames * grefs_per_grant_frame + RPP - 1) /
RPP;
for (i = 0; i < nr_glist_frames; i++) {
gnttab_list[i] = (grant_ref_t *)__get_free_page(GFP_KERNEL);
if (gnttab_list[i] == NULL) {
@@ -1056,12 +1066,12 @@ int gnttab_init(void)
}
}
- if (gnttab_resume() < 0) {
+ if (gnttab_setup() < 0) {
ret = -ENODEV;
goto ini_nomem;
}
- nr_init_grefs = nr_grant_frames * GREFS_PER_GRANT_FRAME;
+ nr_init_grefs = nr_grant_frames * grefs_per_grant_frame;
for (i = NR_RESERVED_ENTRIES; i < nr_init_grefs - 1; i++)
gnttab_entry(i) = i + 1;
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
