* [PATCH] Input: synaptics-rmi4 - bound the SMBus block read to the caller buffer
@ 2026-06-13 5:39 Bryam Vargas via B4 Relay
2026-06-13 5:51 ` sashiko-bot
0 siblings, 1 reply; 2+ messages in thread
From: Bryam Vargas via B4 Relay @ 2026-06-13 5:39 UTC (permalink / raw)
To: Dmitry Torokhov
Cc: Benjamin Tissoires, linux-input, Andrew Duggan, linux-kernel
From: Bryam Vargas <hexlabsecurity@proton.me>
smb_block_read() takes a destination length but passes it nowhere:
static int smb_block_read(struct rmi_transport_dev *xport,
u8 commandcode, void *buf, size_t len)
{
...
retval = i2c_smbus_read_block_data(client, commandcode, buf);
i2c_smbus_read_block_data() has no destination-size argument; it copies
the block count reported by the device (the first SMBus byte, up to
I2C_SMBUS_BLOCK_MAX = 32) into buf. The RMI callers pass buffers far
smaller than 32 bytes - rmi_read_pdt_entry() reads a PDT entry into an
on-stack u8 buf[RMI_PDT_ENTRY_SIZE] (6 bytes) during the PDT scan - so a
malfunctioning, malicious or counterfeit RMI4 SMBus controller (or an
attacker tampering with the I2C bus) that reports a larger block count
overflows the caller's stack buffer by up to 32 - 6 = 26 bytes,
clobbering the stack canary, saved registers and the return address.
Read into a local I2C_SMBUS_BLOCK_MAX-sized buffer and copy back at most
len bytes, so the device can never write past the caller's buffer.
Fixes: 82264d0cf7ae ("Input: synaptics-rmi4 - add SMBus support")
Cc: stable@vger.kernel.org
Signed-off-by: Bryam Vargas <hexlabsecurity@proton.me>
---
drivers/input/rmi4/rmi_smbus.c | 10 +++++++++-
1 file changed, 9 insertions(+), 1 deletion(-)
diff --git a/drivers/input/rmi4/rmi_smbus.c b/drivers/input/rmi4/rmi_smbus.c
index f3d0b40721df..ea957aba28f1 100644
--- a/drivers/input/rmi4/rmi_smbus.c
+++ b/drivers/input/rmi4/rmi_smbus.c
@@ -177,12 +177,20 @@ static int smb_block_read(struct rmi_transport_dev *xport,
struct rmi_smb_xport *rmi_smb =
container_of(xport, struct rmi_smb_xport, xport);
struct i2c_client *client = rmi_smb->client;
+ u8 data[I2C_SMBUS_BLOCK_MAX];
int retval;
- retval = i2c_smbus_read_block_data(client, commandcode, buf);
+ /*
+ * i2c_smbus_read_block_data() copies the device-reported block count
+ * (up to I2C_SMBUS_BLOCK_MAX) into the destination and has no way to
+ * know its size, so read into a local buffer and copy back at most
+ * len bytes - never past the caller's buffer.
+ */
+ retval = i2c_smbus_read_block_data(client, commandcode, data);
if (retval < 0)
return retval;
+ memcpy(buf, data, min_t(size_t, retval, len));
return retval;
}
---
base-commit: 8e65320d91cdc3b241d4b94855c88459b91abf66
change-id: 20260613-b4-disp-2e033955-ffe3889ce3e9
Best regards,
--
Bryam Vargas <hexlabsecurity@proton.me>
^ permalink raw reply related [flat|nested] 2+ messages in thread
* Re: [PATCH] Input: synaptics-rmi4 - bound the SMBus block read to the caller buffer
2026-06-13 5:39 [PATCH] Input: synaptics-rmi4 - bound the SMBus block read to the caller buffer Bryam Vargas via B4 Relay
@ 2026-06-13 5:51 ` sashiko-bot
0 siblings, 0 replies; 2+ messages in thread
From: sashiko-bot @ 2026-06-13 5:51 UTC (permalink / raw)
To: Bryam Vargas via B4 Relay; +Cc: linux-input, dmitry.torokhov
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
Pre-existing issues:
- [High] Out-of-bounds read and information leak in `rmi_smb_write_block`.
--
commit d7c26cbb5c7a78f15621da67eb9707ffe6750b59
Author: Bryam Vargas <hexlabsecurity@proton.me>
Input: synaptics-rmi4 - bound the SMBus block read to the caller buffer
This commit fixes a stack overflow in smb_block_read by reading into a local
buffer first. It then copies back at most len bytes to ensure the device
never writes past the caller's buffer.
> diff --git a/drivers/input/rmi4/rmi_smbus.c b/drivers/input/rmi4/rmi_smbus.c
> index f3d0b40721df0..ea957aba28f17 100644
> --- a/drivers/input/rmi4/rmi_smbus.c
> +++ b/drivers/input/rmi4/rmi_smbus.c
> @@ -177,12 +177,20 @@ static int smb_block_read(struct rmi_transport_dev *xport,
> struct rmi_smb_xport *rmi_smb =
> container_of(xport, struct rmi_smb_xport, xport);
> struct i2c_client *client = rmi_smb->client;
> + u8 data[I2C_SMBUS_BLOCK_MAX];
> int retval;
>
> - retval = i2c_smbus_read_block_data(client, commandcode, buf);
> + /*
> + * i2c_smbus_read_block_data() copies the device-reported block count
> + * (up to I2C_SMBUS_BLOCK_MAX) into the destination and has no way to
> + * know its size, so read into a local buffer and copy back at most
> + * len bytes - never past the caller's buffer.
> + */
> + retval = i2c_smbus_read_block_data(client, commandcode, data);
> if (retval < 0)
> return retval;
>
> + memcpy(buf, data, min_t(size_t, retval, len));
> return retval;
> }
[Severity: High]
This isn't a bug introduced by this patch, but while looking at this file,
I noticed a similar size calculation issue in rmi_smb_write_block().
Does this code overflow databuff on the final chunk if len is not a
multiple of 32?
drivers/input/rmi4/rmi_smbus.c:rmi_smb_write_block() {
...
while (cur_len > 0) {
/*
* break into 32 bytes chunks to write get command code
*/
int block_len = min_t(int, len, SMB_MAX_COUNT);
...
retval = smb_block_write(xport, commandcode,
databuff, block_len);
...
cur_len -= SMB_MAX_COUNT;
databuff += SMB_MAX_COUNT;
}
...
}
It appears block_len is calculated using the invariant len parameter instead
of cur_len. If len is greater than 32 but not a multiple of 32 (e.g., 40),
the second iteration will evaluate min(40, 32) = 32 instead of the
remaining 8 bytes.
This would cause smb_block_write() to read 32 bytes from databuff when
only 8 valid bytes remain, leading to an out-of-bounds read.
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260613-b4-disp-2e033955-v1-1-43ab7281667a@proton.me?part=1
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2026-06-13 5:51 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-06-13 5:39 [PATCH] Input: synaptics-rmi4 - bound the SMBus block read to the caller buffer Bryam Vargas via B4 Relay
2026-06-13 5:51 ` sashiko-bot
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox