Commit 4b708b7b1a2c ("firmware: google: check if size is valid when decoding VPD data") adds length checks, but the new vpd_decode_entry() function botched the logic -- it adds the key length twice, instead of adding the key and value lengths separately.
On my local system, this means vpd.c's vpd_section_create_attribs() hits an error case after the first attribute it parses, since it's no longer looking at the correct offset. With this patch, I'm back to seeing all the correct attributes in /sys/firmware/vpd/...
Fixes: 4b708b7b1a2c ("firmware: google: check if size is valid when decoding VPD data") Cc: stable@vger.kernel.org Cc: Hung-Te Lin hungte@chromium.org Cc: Guenter Roeck groeck@chromium.org Cc: Stephen Boyd swboyd@chromium.org Signed-off-by: Brian Norris briannorris@chromium.org --- drivers/firmware/google/vpd_decode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/firmware/google/vpd_decode.c b/drivers/firmware/google/vpd_decode.c index dda525c0f968..5c6f2a74f104 100644 --- a/drivers/firmware/google/vpd_decode.c +++ b/drivers/firmware/google/vpd_decode.c @@ -52,7 +52,7 @@ static int vpd_decode_entry(const u32 max_len, const u8 *input_buf, if (max_len - consumed < *entry_len) return VPD_FAIL;
- consumed += decoded_len; + consumed += *entry_len; *_consumed = consumed; return VPD_OK; }
On Mon, Sep 30, 2019 at 2:45 PM Brian Norris briannorris@chromium.org wrote:
Fixes: 4b708b7b1a2c ("firmware: google: check if size is valid when decoding VPD data") Cc: stable@vger.kernel.org
Perhaps I should have modified the subject to note the urgency (e.g., [PATCH 5.4]). The above regression was recently shipped to v4.14.146 and v4.19.75.
Brian
Quoting Brian Norris (2019-09-30 14:45:22)
Commit 4b708b7b1a2c ("firmware: google: check if size is valid when decoding VPD data") adds length checks, but the new vpd_decode_entry() function botched the logic -- it adds the key length twice, instead of adding the key and value lengths separately.
On my local system, this means vpd.c's vpd_section_create_attribs() hits an error case after the first attribute it parses, since it's no longer looking at the correct offset. With this patch, I'm back to seeing all the correct attributes in /sys/firmware/vpd/...
Fixes: 4b708b7b1a2c ("firmware: google: check if size is valid when decoding VPD data") Cc: stable@vger.kernel.org Cc: Hung-Te Lin hungte@chromium.org Cc: Guenter Roeck groeck@chromium.org Cc: Stephen Boyd swboyd@chromium.org Signed-off-by: Brian Norris briannorris@chromium.org
Reviewed-by: Stephen Boyd swboyd@chromium.org
linux-stable-mirror@lists.linaro.org