2018-10-16 14:33:44

by Gustavo A. R. Silva

[permalink] [raw]
Subject: [PATCH] IB/ucm: Fix Spectre v1 vulnerability

hdr.cmd can be indirectly controlled by user-space, hence leading to
a potential exploitation of the Spectre variant 1 vulnerability.

This issue was detected with the help of Smatch:

drivers/infiniband/core/ucm.c:1127 ib_ucm_write() warn: potential
spectre issue 'ucm_cmd_table' [r] (local cap)

Fix this by sanitizing hdr.cmd before using it to index
ucm_cmd_table.

Notice that given that speculation windows are large, the policy is
to kill the speculation on the first load and not worry if it can be
completed with a dependent load/store [1].

[1] https://marc.info/?l=linux-kernel&m=152449131114778&w=2

Cc: [email protected]
Signed-off-by: Gustavo A. R. Silva <[email protected]>
---
drivers/infiniband/core/ucm.c | 3 +++
1 file changed, 3 insertions(+)

diff --git a/drivers/infiniband/core/ucm.c b/drivers/infiniband/core/ucm.c
index faa9e61..73332b9 100644
--- a/drivers/infiniband/core/ucm.c
+++ b/drivers/infiniband/core/ucm.c
@@ -46,6 +46,8 @@
#include <linux/mutex.h>
#include <linux/slab.h>

+#include <linux/nospec.h>
+
#include <linux/uaccess.h>

#include <rdma/ib.h>
@@ -1120,6 +1122,7 @@ static ssize_t ib_ucm_write(struct file *filp, const char __user *buf,

if (hdr.cmd >= ARRAY_SIZE(ucm_cmd_table))
return -EINVAL;
+ hdr.cmd = array_index_nospec(hdr.cmd, ARRAY_SIZE(ucm_cmd_table));

if (hdr.in + sizeof(hdr) > len)
return -EINVAL;
--
2.7.4



2018-10-16 16:51:43

by Doug Ledford

[permalink] [raw]
Subject: Re: [PATCH] IB/ucm: Fix Spectre v1 vulnerability

On Tue, 2018-10-16 at 16:32 +0200, Gustavo A. R. Silva wrote:
> hdr.cmd can be indirectly controlled by user-space, hence leading to
> a potential exploitation of the Spectre variant 1 vulnerability.
>
> This issue was detected with the help of Smatch:
>
> drivers/infiniband/core/ucm.c:1127 ib_ucm_write() warn: potential
> spectre issue 'ucm_cmd_table' [r] (local cap)
>
> Fix this by sanitizing hdr.cmd before using it to index
> ucm_cmd_table.
>
> Notice that given that speculation windows are large, the policy is
> to kill the speculation on the first load and not worry if it can be
> completed with a dependent load/store [1].
>
> [1] https://marc.info/?l=linux-kernel&m=152449131114778&w=2
>
> Cc: [email protected]
> Signed-off-by: Gustavo A. R. Silva <[email protected]>

Thanks, applied to for-rc.

--
Doug Ledford <[email protected]>
GPG KeyID: B826A3330E572FDD
Key fingerprint = AE6B 1BDA 122B 23B4 265B 1274 B826 A333 0E57 2FDD


Attachments:
signature.asc (849.00 B)
This is a digitally signed message part