summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorLyude Paul <lyude@redhat.com>2019-07-25 15:40:01 -0400
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2019-08-29 08:26:42 +0200
commit8ba408f45ee01c3871248d0c8fcb80bdb21ea4fe (patch)
tree5e5518513b225df0fdb4f369492152b514b70495
parent17017ebb8676295a1b896c4c405fd587b794c299 (diff)
drm/nouveau: Don't retry infinitely when receiving no data on i2c over AUX
commit c358ebf59634f06d8ed176da651ec150df3c8686 upstream. While I had thought I had fixed this issue in: commit 342406e4fbba ("drm/nouveau/i2c: Disable i2c bus access after ->fini()") It turns out that while I did fix the error messages I was seeing on my P50 when trying to access i2c busses with the GPU in runtime suspend, I accidentally had missed one important detail that was mentioned on the bug report this commit was supposed to fix: that the CPU would only lock up when trying to access i2c busses _on connected devices_ _while the GPU is not in runtime suspend_. Whoops. That definitely explains why I was not able to get my machine to hang with i2c bus interactions until now, as plugging my P50 into it's dock with an HDMI monitor connected allowed me to finally reproduce this locally. Now that I have managed to reproduce this issue properly, it looks like the problem is much simpler then it looks. It turns out that some connected devices, such as MST laptop docks, will actually ACK i2c reads even if no data was actually read: [ 275.063043] nouveau 0000:01:00.0: i2c: aux 000a: 1: 0000004c 1 [ 275.063447] nouveau 0000:01:00.0: i2c: aux 000a: 00 01101000 10040000 [ 275.063759] nouveau 0000:01:00.0: i2c: aux 000a: rd 00000001 [ 275.064024] nouveau 0000:01:00.0: i2c: aux 000a: rd 00000000 [ 275.064285] nouveau 0000:01:00.0: i2c: aux 000a: rd 00000000 [ 275.064594] nouveau 0000:01:00.0: i2c: aux 000a: rd 00000000 Because we don't handle the situation of i2c ack without any data, we end up entering an infinite loop in nvkm_i2c_aux_i2c_xfer() since the value of cnt always remains at 0. This finally properly explains how this could result in a CPU hang like the ones observed in the aforementioned commit. So, fix this by retrying transactions if no data is written or received, and give up and fail the transaction if we continue to not write or receive any data after 32 retries. Signed-off-by: Lyude Paul <lyude@redhat.com> Cc: stable@vger.kernel.org Signed-off-by: Ben Skeggs <bskeggs@redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/i2c/aux.c24
1 files changed, 17 insertions, 7 deletions
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/aux.c b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/aux.c
index b4e7404fe660..a11637b0f6cc 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/aux.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/aux.c
@@ -40,8 +40,7 @@ nvkm_i2c_aux_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num)
u8 *ptr = msg->buf;
while (remaining) {
- u8 cnt = (remaining > 16) ? 16 : remaining;
- u8 cmd;
+ u8 cnt, retries, cmd;
if (msg->flags & I2C_M_RD)
cmd = 1;
@@ -51,10 +50,19 @@ nvkm_i2c_aux_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num)
if (mcnt || remaining > 16)
cmd |= 4; /* MOT */
- ret = aux->func->xfer(aux, true, cmd, msg->addr, ptr, &cnt);
- if (ret < 0) {
- nvkm_i2c_aux_release(aux);
- return ret;
+ for (retries = 0, cnt = 0;
+ retries < 32 && !cnt;
+ retries++) {
+ cnt = min_t(u8, remaining, 16);
+ ret = aux->func->xfer(aux, true, cmd,
+ msg->addr, ptr, &cnt);
+ if (ret < 0)
+ goto out;
+ }
+ if (!cnt) {
+ AUX_TRACE(aux, "no data after 32 retries");
+ ret = -EIO;
+ goto out;
}
ptr += cnt;
@@ -64,8 +72,10 @@ nvkm_i2c_aux_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num)
msg++;
}
+ ret = num;
+out:
nvkm_i2c_aux_release(aux);
- return num;
+ return ret;
}
static u32