* Re: [PATCH v5 4/5] ath11k: add support for device recovery for QCA6390/WCN6855
@ 2022-02-10 10:22 kernel test robot
0 siblings, 0 replies; 3+ messages in thread
From: kernel test robot @ 2022-02-10 10:22 UTC (permalink / raw)
To: kbuild
[-- Attachment #1: Type: text/plain, Size: 18522 bytes --]
CC: llvm(a)lists.linux.dev
CC: kbuild-all(a)lists.01.org
In-Reply-To: <20220208104947.25791-5-quic_wgong@quicinc.com>
References: <20220208104947.25791-5-quic_wgong@quicinc.com>
TO: Wen Gong <quic_wgong@quicinc.com>
Hi Wen,
Thank you for the patch! Perhaps something to improve:
[auto build test WARNING on 76680d49b5e0e661bc4abcdaf13fb7e124b4ca08]
url: https://github.com/0day-ci/linux/commits/Wen-Gong/ath11k-add-feature-for-device-recovery/20220208-194321
base: 76680d49b5e0e661bc4abcdaf13fb7e124b4ca08
:::::: branch date: 2 days ago
:::::: commit date: 2 days ago
config: x86_64-randconfig-c007 (https://download.01.org/0day-ci/archive/20220210/202202101840.AalHfv14-lkp(a)intel.com/config)
compiler: clang version 15.0.0 (https://github.com/llvm/llvm-project e8bff9ae54a55b4dbfeb6ba55f723abbd81bf494)
reproduce (this is a W=1 build):
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# https://github.com/0day-ci/linux/commit/2a8ac8c524013b4d43efd46da5c10746f74586b7
git remote add linux-review https://github.com/0day-ci/linux
git fetch --no-tags linux-review Wen-Gong/ath11k-add-feature-for-device-recovery/20220208-194321
git checkout 2a8ac8c524013b4d43efd46da5c10746f74586b7
# save the config file to linux build tree
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross ARCH=x86_64 clang-analyzer
If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>
clang-analyzer warnings: (new ones prefixed by >>)
^
drivers/hid/hid-core.c:1723:3: note: Calling 'hid_output_report'
hid_output_report(report, buf);
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/hid/hid-core.c:1630:14: note: Field 'id' is <= 0
if (report->id > 0)
^
drivers/hid/hid-core.c:1630:2: note: Taking false branch
if (report->id > 0)
^
drivers/hid/hid-core.c:1634:14: note: Assuming 'n' is < field 'maxfield'
for (n = 0; n < report->maxfield; n++)
^~~~~~~~~~~~~~~~~~~~
drivers/hid/hid-core.c:1634:2: note: Loop condition is true. Entering loop body
for (n = 0; n < report->maxfield; n++)
^
drivers/hid/hid-core.c:1635:3: note: Calling 'hid_output_field'
hid_output_field(report->device, report->field[n], data);
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/hid/hid-core.c:1597:2: note: 'size' initialized here
unsigned size = field->report_size;
^~~~~~~~~~~~~
drivers/hid/hid-core.c:1600:14: note: Assuming 'n' is < 'count'
for (n = 0; n < count; n++) {
^~~~~~~~~
drivers/hid/hid-core.c:1600:2: note: Loop condition is true. Entering loop body
for (n = 0; n < count; n++) {
^
drivers/hid/hid-core.c:1601:7: note: Assuming field 'logical_minimum' is < 0
if (field->logical_minimum < 0) /* signed values */
^~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/hid/hid-core.c:1601:3: note: Taking true branch
if (field->logical_minimum < 0) /* signed values */
^
drivers/hid/hid-core.c:1602:4: note: Calling 'implement'
implement(hid, data, offset + n * size, size,
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/hid/hid-core.c:1421:15: note: Assuming 'n' is <= 32
if (unlikely(n > 32)) {
^
include/linux/compiler.h:78:42: note: expanded from macro 'unlikely'
# define unlikely(x) __builtin_expect(!!(x), 0)
^
drivers/hid/hid-core.c:1421:2: note: Taking false branch
if (unlikely(n > 32)) {
^
drivers/hid/hid-core.c:1425:13: note: Assuming 'n' is >= 32
} else if (n < 32) {
^~~~~~
drivers/hid/hid-core.c:1425:9: note: Taking false branch
} else if (n < 32) {
^
drivers/hid/hid-core.c:1602:4: note: Returning from 'implement'
implement(hid, data, offset + n * size, size,
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/hid/hid-core.c:1600:14: note: Assuming 'n' is < 'count'
for (n = 0; n < count; n++) {
^~~~~~~~~
drivers/hid/hid-core.c:1600:2: note: Loop condition is true. Entering loop body
for (n = 0; n < count; n++) {
^
drivers/hid/hid-core.c:1601:14: note: Field 'logical_minimum' is < 0
if (field->logical_minimum < 0) /* signed values */
^
drivers/hid/hid-core.c:1601:3: note: Taking true branch
if (field->logical_minimum < 0) /* signed values */
^
drivers/hid/hid-core.c:1603:31: note: Passing the value 32 via 2nd parameter 'n'
s32ton(field->value[n], size));
^~~~
drivers/hid/hid-core.c:1603:7: note: Calling 's32ton'
s32ton(field->value[n], size));
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/hid/hid-core.c:1334:6: note: Assuming 'a' is 0
if (a && a != -1)
^
drivers/hid/hid-core.c:1334:8: note: Left side of '&&' is false
if (a && a != -1)
^
drivers/hid/hid-core.c:1336:21: note: The result of the left shift is undefined due to shifting by '32', which is greater or equal to the width of type 'int'
return value & ((1 << n) - 1);
^ ~
drivers/hid/hid-core.c:1984:3: warning: Value stored to 'len' is never read [clang-analyzer-deadcode.DeadStores]
len += sprintf(buf + len, "%shidraw%d", len ? "," : "",
^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/hid/hid-core.c:1984:3: note: Value stored to 'len' is never read
len += sprintf(buf + len, "%shidraw%d", len ? "," : "",
^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Suppressed 5 warnings (5 in non-user code).
Use -header-filter=.* to display errors from all non-system headers. Use -system-headers to display errors from system headers as well.
4 warnings generated.
Suppressed 4 warnings (4 in non-user code).
Use -header-filter=.* to display errors from all non-system headers. Use -system-headers to display errors from system headers as well.
12 warnings generated.
Suppressed 12 warnings (12 in non-user code).
Use -header-filter=.* to display errors from all non-system headers. Use -system-headers to display errors from system headers as well.
12 warnings generated.
Suppressed 12 warnings (12 in non-user code).
Use -header-filter=.* to display errors from all non-system headers. Use -system-headers to display errors from system headers as well.
17 warnings generated.
>> drivers/net/wireless/ath/ath11k/core.c:1389:3: warning: Value stored to 'fail_cont_count' is never read [clang-analyzer-deadcode.DeadStores]
fail_cont_count = atomic_inc_return(&ab->fail_cont_count);
^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/net/wireless/ath/ath11k/core.c:1389:3: note: Value stored to 'fail_cont_count' is never read
fail_cont_count = atomic_inc_return(&ab->fail_cont_count);
^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Suppressed 16 warnings (16 in non-user code).
Use -header-filter=.* to display errors from all non-system headers. Use -system-headers to display errors from system headers as well.
15 warnings generated.
Suppressed 15 warnings (15 in non-user code).
Use -header-filter=.* to display errors from all non-system headers. Use -system-headers to display errors from system headers as well.
15 warnings generated.
Suppressed 15 warnings (15 in non-user code).
Use -header-filter=.* to display errors from all non-system headers. Use -system-headers to display errors from system headers as well.
15 warnings generated.
Suppressed 15 warnings (15 in non-user code).
Use -header-filter=.* to display errors from all non-system headers. Use -system-headers to display errors from system headers as well.
20 warnings generated.
drivers/net/wireless/ath/ath11k/wmi.c:953:2: warning: Value stored to 'ptr' is never read [clang-analyzer-deadcode.DeadStores]
ptr += sizeof(*tlv);
^ ~~~~~~~~~~~~
drivers/net/wireless/ath/ath11k/wmi.c:953:2: note: Value stored to 'ptr' is never read
ptr += sizeof(*tlv);
^ ~~~~~~~~~~~~
drivers/net/wireless/ath/ath11k/wmi.c:6617:7: warning: 2nd function call argument is an uninitialized value [clang-analyzer-core.CallAndMessage]
ar = ath11k_mac_get_ar_by_vdev_id(ab, peer_del_resp.vdev_id);
^
drivers/net/wireless/ath/ath11k/wmi.c:7774:7: note: Taking false branch
id = FIELD_GET(WMI_CMD_HDR_CMD_ID, (cmd_hdr->cmd_id));
^
include/linux/bitfield.h:125:3: note: expanded from macro 'FIELD_GET'
__BF_FIELD_CHECK(_mask, _reg, 0U, "FIELD_GET: "); \
^
include/linux/bitfield.h:62:3: note: expanded from macro '__BF_FIELD_CHECK'
BUILD_BUG_ON_MSG(!__builtin_constant_p(_mask), \
^
include/linux/build_bug.h:39:37: note: expanded from macro 'BUILD_BUG_ON_MSG'
#define BUILD_BUG_ON_MSG(cond, msg) compiletime_assert(!(cond), msg)
^
include/linux/compiler_types.h:346:2: note: expanded from macro 'compiletime_assert'
_compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__)
^
include/linux/compiler_types.h:334:2: note: expanded from macro '_compiletime_assert'
__compiletime_assert(condition, msg, prefix, suffix)
^
include/linux/compiler_types.h:326:3: note: expanded from macro '__compiletime_assert'
if (!(condition)) \
^
drivers/net/wireless/ath/ath11k/wmi.c:7774:7: note: Loop condition is false. Exiting loop
id = FIELD_GET(WMI_CMD_HDR_CMD_ID, (cmd_hdr->cmd_id));
^
include/linux/bitfield.h:125:3: note: expanded from macro 'FIELD_GET'
__BF_FIELD_CHECK(_mask, _reg, 0U, "FIELD_GET: "); \
^
include/linux/bitfield.h:62:3: note: expanded from macro '__BF_FIELD_CHECK'
BUILD_BUG_ON_MSG(!__builtin_constant_p(_mask), \
^
include/linux/build_bug.h:39:37: note: expanded from macro 'BUILD_BUG_ON_MSG'
#define BUILD_BUG_ON_MSG(cond, msg) compiletime_assert(!(cond), msg)
^
include/linux/compiler_types.h:346:2: note: expanded from macro 'compiletime_assert'
_compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__)
^
include/linux/compiler_types.h:334:2: note: expanded from macro '_compiletime_assert'
__compiletime_assert(condition, msg, prefix, suffix)
^
include/linux/compiler_types.h:318:2: note: expanded from macro '__compiletime_assert'
do { \
^
drivers/net/wireless/ath/ath11k/wmi.c:7774:7: note: Taking false branch
id = FIELD_GET(WMI_CMD_HDR_CMD_ID, (cmd_hdr->cmd_id));
^
include/linux/bitfield.h:125:3: note: expanded from macro 'FIELD_GET'
__BF_FIELD_CHECK(_mask, _reg, 0U, "FIELD_GET: "); \
^
include/linux/bitfield.h:64:3: note: expanded from macro '__BF_FIELD_CHECK'
BUILD_BUG_ON_MSG((_mask) == 0, _pfx "mask is zero"); \
^
include/linux/build_bug.h:39:37: note: expanded from macro 'BUILD_BUG_ON_MSG'
#define BUILD_BUG_ON_MSG(cond, msg) compiletime_assert(!(cond), msg)
^
include/linux/compiler_types.h:346:2: note: expanded from macro 'compiletime_assert'
_compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__)
^
include/linux/compiler_types.h:334:2: note: expanded from macro '_compiletime_assert'
__compiletime_assert(condition, msg, prefix, suffix)
^
include/linux/compiler_types.h:326:3: note: expanded from macro '__compiletime_assert'
if (!(condition)) \
^
drivers/net/wireless/ath/ath11k/wmi.c:7774:7: note: Loop condition is false. Exiting loop
id = FIELD_GET(WMI_CMD_HDR_CMD_ID, (cmd_hdr->cmd_id));
^
include/linux/bitfield.h:125:3: note: expanded from macro 'FIELD_GET'
__BF_FIELD_CHECK(_mask, _reg, 0U, "FIELD_GET: "); \
^
include/linux/bitfield.h:64:3: note: expanded from macro '__BF_FIELD_CHECK'
BUILD_BUG_ON_MSG((_mask) == 0, _pfx "mask is zero"); \
^
include/linux/build_bug.h:39:37: note: expanded from macro 'BUILD_BUG_ON_MSG'
#define BUILD_BUG_ON_MSG(cond, msg) compiletime_assert(!(cond), msg)
vim +/fail_cont_count +1389 drivers/net/wireless/ath/ath11k/core.c
d5c65159f28953 Kalle Valo 2019-11-23 1344
2a8ac8c524013b Wen Gong 2022-02-08 1345 static void ath11k_core_reset(struct work_struct *work)
2a8ac8c524013b Wen Gong 2022-02-08 1346 {
2a8ac8c524013b Wen Gong 2022-02-08 1347 struct ath11k_base *ab = container_of(work, struct ath11k_base, reset_work);
2a8ac8c524013b Wen Gong 2022-02-08 1348 int reset_count, fail_cont_count;
2a8ac8c524013b Wen Gong 2022-02-08 1349 long time_left;
2a8ac8c524013b Wen Gong 2022-02-08 1350
2a8ac8c524013b Wen Gong 2022-02-08 1351 if (!(test_bit(ATH11K_FLAG_REGISTERED, &ab->dev_flags))) {
2a8ac8c524013b Wen Gong 2022-02-08 1352 ath11k_warn(ab, "ignore reset dev flags 0x%lx\n", ab->dev_flags);
2a8ac8c524013b Wen Gong 2022-02-08 1353 return;
2a8ac8c524013b Wen Gong 2022-02-08 1354 }
2a8ac8c524013b Wen Gong 2022-02-08 1355
2a8ac8c524013b Wen Gong 2022-02-08 1356 /* Sometimes the recovery will fail and then the next all recovery fail,
2a8ac8c524013b Wen Gong 2022-02-08 1357 * this is to avoid infinite recovery since it can not recovery success.
2a8ac8c524013b Wen Gong 2022-02-08 1358 */
2a8ac8c524013b Wen Gong 2022-02-08 1359 fail_cont_count = atomic_read(&ab->fail_cont_count);
2a8ac8c524013b Wen Gong 2022-02-08 1360
2a8ac8c524013b Wen Gong 2022-02-08 1361 if (fail_cont_count >= ATH11K_RESET_MAX_FAIL_COUNT_FINAL)
2a8ac8c524013b Wen Gong 2022-02-08 1362 return;
2a8ac8c524013b Wen Gong 2022-02-08 1363
2a8ac8c524013b Wen Gong 2022-02-08 1364 if (fail_cont_count >= ATH11K_RESET_MAX_FAIL_COUNT_FIRST &&
2a8ac8c524013b Wen Gong 2022-02-08 1365 time_before(jiffies, ab->reset_fail_timeout))
2a8ac8c524013b Wen Gong 2022-02-08 1366 return;
2a8ac8c524013b Wen Gong 2022-02-08 1367
2a8ac8c524013b Wen Gong 2022-02-08 1368 reset_count = atomic_inc_return(&ab->reset_count);
2a8ac8c524013b Wen Gong 2022-02-08 1369
2a8ac8c524013b Wen Gong 2022-02-08 1370 if (reset_count > 1) {
2a8ac8c524013b Wen Gong 2022-02-08 1371 /* Sometimes it happened another reset worker before the previous one
2a8ac8c524013b Wen Gong 2022-02-08 1372 * completed, then the second reset worker will destroy the previous one,
2a8ac8c524013b Wen Gong 2022-02-08 1373 * thus below is to avoid that.
2a8ac8c524013b Wen Gong 2022-02-08 1374 */
2a8ac8c524013b Wen Gong 2022-02-08 1375 ath11k_warn(ab, "already reseting count %d\n", reset_count);
2a8ac8c524013b Wen Gong 2022-02-08 1376
2a8ac8c524013b Wen Gong 2022-02-08 1377 reinit_completion(&ab->reset_complete);
2a8ac8c524013b Wen Gong 2022-02-08 1378 time_left = wait_for_completion_timeout(&ab->reset_complete,
2a8ac8c524013b Wen Gong 2022-02-08 1379 ATH11K_RESET_TIMEOUT_HZ);
2a8ac8c524013b Wen Gong 2022-02-08 1380
2a8ac8c524013b Wen Gong 2022-02-08 1381 if (time_left) {
2a8ac8c524013b Wen Gong 2022-02-08 1382 ath11k_dbg(ab, ATH11K_DBG_BOOT, "to skip reset\n");
2a8ac8c524013b Wen Gong 2022-02-08 1383 atomic_dec(&ab->reset_count);
2a8ac8c524013b Wen Gong 2022-02-08 1384 return;
2a8ac8c524013b Wen Gong 2022-02-08 1385 }
2a8ac8c524013b Wen Gong 2022-02-08 1386
2a8ac8c524013b Wen Gong 2022-02-08 1387 ab->reset_fail_timeout = jiffies + ATH11K_RESET_FAIL_TIMEOUT_HZ;
2a8ac8c524013b Wen Gong 2022-02-08 1388 /* Record the continuous recovery fail count when recovery failed*/
2a8ac8c524013b Wen Gong 2022-02-08 @1389 fail_cont_count = atomic_inc_return(&ab->fail_cont_count);
2a8ac8c524013b Wen Gong 2022-02-08 1390 }
2a8ac8c524013b Wen Gong 2022-02-08 1391
2a8ac8c524013b Wen Gong 2022-02-08 1392 ath11k_dbg(ab, ATH11K_DBG_BOOT, "reset starting\n");
2a8ac8c524013b Wen Gong 2022-02-08 1393
2a8ac8c524013b Wen Gong 2022-02-08 1394 ab->is_reset = true;
2a8ac8c524013b Wen Gong 2022-02-08 1395 atomic_set(&ab->recovery_count, 0);
2a8ac8c524013b Wen Gong 2022-02-08 1396
2a8ac8c524013b Wen Gong 2022-02-08 1397 ath11k_hif_power_down(ab);
2a8ac8c524013b Wen Gong 2022-02-08 1398 ath11k_qmi_free_resource(ab);
2a8ac8c524013b Wen Gong 2022-02-08 1399 ath11k_hif_power_up(ab);
2a8ac8c524013b Wen Gong 2022-02-08 1400
2a8ac8c524013b Wen Gong 2022-02-08 1401 ath11k_dbg(ab, ATH11K_DBG_BOOT, "reset started\n");
2a8ac8c524013b Wen Gong 2022-02-08 1402 }
2a8ac8c524013b Wen Gong 2022-02-08 1403
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all(a)lists.01.org
^ permalink raw reply [flat|nested] 3+ messages in thread
* [PATCH v5 4/5] ath11k: add support for device recovery for QCA6390/WCN6855
2022-02-08 10:49 [PATCH v5 0/5] ath11k: add feature for device recovery Wen Gong
@ 2022-02-08 10:49 ` Wen Gong
0 siblings, 0 replies; 3+ messages in thread
From: Wen Gong @ 2022-02-08 10:49 UTC (permalink / raw)
To: ath11k; +Cc: linux-wireless, quic_wgong
Currently ath11k has device recovery logic, it is introduced by this
patch "ath11k: Add support for subsystem recovery" which is upstream
by https://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git/commit/?h=ath11k-bringup&id=3a7b4838b6f6f234239f263ef3dc02e612a083ad.
The patch is for AHB devices such as IPQ8074, it has remote proc module
which is used to download the firmware and boots the processor which
firmware is running on. If firmware crashed, remote proc module will
detect it and download and boot firmware again. Below command will
trigger a firmware crash, and then user can test feature of device
recovery.
Test command:
echo assert > /sys/kernel/debug/ath11k/qca6390\ hw2.0/simulate_fw_crash
echo assert > /sys/kernel/debug/ath11k/wcn6855\ hw2.0/simulate_fw_crash
Unfortunately, QCA6390 is PCIe bus, it does not have the remote proc
module, it use mhi module to communicate between firmware and ath11k.
So ath11k does not support device recovery for QCA6390 currently.
This patch is to add the extra logic which is different for QCA6390.
When firmware crashed, MHI_CB_EE_RDDM event will be indicate by
firmware and then ath11k_mhi_op_status_cb which is the callback of
mhi_controller will receive the MHI_CB_EE_RDDM event, then ath11k
will start to do recovery process, ath11k_core_reset() calls
ath11k_hif_power_down()/ath11k_hif_power_up(), then the mhi/ath11k
will start to download and boot firmware. There are some logic to
avoid deadloop recovery and two simultaneous recovery operations.
And because it has muti-radios for the soc, so it add some logic
in ath11k_mac_op_reconfig_complete() to make sure all radios has
reconfig complete and then complete the device recovery.
Also it add workqueue_aux, because ab->workqueue is used when receive
ATH11K_QMI_EVENT_FW_READY in recovery process(queue_work(ab->workqueue,
&ab->restart_work)), and ath11k_core_reset will wait for max
ATH11K_RESET_TIMEOUT_HZ for the previous restart_work finished, if
ath11k_core_reset also queued in ab->workqueue, then it will delay
restart_work of previous recovery and lead previous recovery fail.
ath11k recovery success for QCA6390/WCN6855 after apply this patch.
Tested-on: QCA6390 hw2.0 PCI WLAN.HST.1.0.1-01740-QCAHSTSWPLZ_V2_TO_X86-1
Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03003-QCAHSPSWPL_V1_V2_SILICONZ_LITE-2
Signed-off-by: Wen Gong <quic_wgong@quicinc.com>
---
drivers/net/wireless/ath/ath11k/core.c | 70 ++++++++++++++++++++++++++
drivers/net/wireless/ath/ath11k/core.h | 13 +++++
drivers/net/wireless/ath/ath11k/mac.c | 18 +++++++
drivers/net/wireless/ath/ath11k/mhi.c | 33 ++++++++++++
4 files changed, 134 insertions(+)
diff --git a/drivers/net/wireless/ath/ath11k/core.c b/drivers/net/wireless/ath/ath11k/core.c
index 7c508e9baa6d..00c83fdb0702 100644
--- a/drivers/net/wireless/ath/ath11k/core.c
+++ b/drivers/net/wireless/ath/ath11k/core.c
@@ -1342,6 +1342,65 @@ static void ath11k_core_restart(struct work_struct *work)
complete(&ab->driver_recovery);
}
+static void ath11k_core_reset(struct work_struct *work)
+{
+ struct ath11k_base *ab = container_of(work, struct ath11k_base, reset_work);
+ int reset_count, fail_cont_count;
+ long time_left;
+
+ if (!(test_bit(ATH11K_FLAG_REGISTERED, &ab->dev_flags))) {
+ ath11k_warn(ab, "ignore reset dev flags 0x%lx\n", ab->dev_flags);
+ return;
+ }
+
+ /* Sometimes the recovery will fail and then the next all recovery fail,
+ * this is to avoid infinite recovery since it can not recovery success.
+ */
+ fail_cont_count = atomic_read(&ab->fail_cont_count);
+
+ if (fail_cont_count >= ATH11K_RESET_MAX_FAIL_COUNT_FINAL)
+ return;
+
+ if (fail_cont_count >= ATH11K_RESET_MAX_FAIL_COUNT_FIRST &&
+ time_before(jiffies, ab->reset_fail_timeout))
+ return;
+
+ reset_count = atomic_inc_return(&ab->reset_count);
+
+ if (reset_count > 1) {
+ /* Sometimes it happened another reset worker before the previous one
+ * completed, then the second reset worker will destroy the previous one,
+ * thus below is to avoid that.
+ */
+ ath11k_warn(ab, "already reseting count %d\n", reset_count);
+
+ reinit_completion(&ab->reset_complete);
+ time_left = wait_for_completion_timeout(&ab->reset_complete,
+ ATH11K_RESET_TIMEOUT_HZ);
+
+ if (time_left) {
+ ath11k_dbg(ab, ATH11K_DBG_BOOT, "to skip reset\n");
+ atomic_dec(&ab->reset_count);
+ return;
+ }
+
+ ab->reset_fail_timeout = jiffies + ATH11K_RESET_FAIL_TIMEOUT_HZ;
+ /* Record the continuous recovery fail count when recovery failed*/
+ fail_cont_count = atomic_inc_return(&ab->fail_cont_count);
+ }
+
+ ath11k_dbg(ab, ATH11K_DBG_BOOT, "reset starting\n");
+
+ ab->is_reset = true;
+ atomic_set(&ab->recovery_count, 0);
+
+ ath11k_hif_power_down(ab);
+ ath11k_qmi_free_resource(ab);
+ ath11k_hif_power_up(ab);
+
+ ath11k_dbg(ab, ATH11K_DBG_BOOT, "reset started\n");
+}
+
static int ath11k_init_hw_params(struct ath11k_base *ab)
{
const struct ath11k_hw_params *hw_params = NULL;
@@ -1411,6 +1470,9 @@ EXPORT_SYMBOL(ath11k_core_deinit);
void ath11k_core_free(struct ath11k_base *ab)
{
+ flush_workqueue(ab->workqueue_aux);
+ destroy_workqueue(ab->workqueue_aux);
+
flush_workqueue(ab->workqueue);
destroy_workqueue(ab->workqueue);
@@ -1434,9 +1496,14 @@ struct ath11k_base *ath11k_core_alloc(struct device *dev, size_t priv_size,
if (!ab->workqueue)
goto err_sc_free;
+ ab->workqueue_aux = create_singlethread_workqueue("ath11k_aux_wq");
+ if (!ab->workqueue_aux)
+ goto err_free_wq;
+
mutex_init(&ab->core_lock);
spin_lock_init(&ab->base_lock);
mutex_init(&ab->vdev_id_11d_lock);
+ init_completion(&ab->reset_complete);
INIT_LIST_HEAD(&ab->peers);
init_waitqueue_head(&ab->peer_mapping_wq);
@@ -1445,6 +1512,7 @@ struct ath11k_base *ath11k_core_alloc(struct device *dev, size_t priv_size,
INIT_WORK(&ab->restart_work, ath11k_core_restart);
INIT_WORK(&ab->update_11d_work, ath11k_update_11d);
INIT_WORK(&ab->rfkill_work, ath11k_rfkill_work);
+ INIT_WORK(&ab->reset_work, ath11k_core_reset);
timer_setup(&ab->rx_replenish_retry, ath11k_ce_rx_replenish_retry, 0);
init_completion(&ab->htc_suspend);
init_completion(&ab->wow.wakeup_completed);
@@ -1455,6 +1523,8 @@ struct ath11k_base *ath11k_core_alloc(struct device *dev, size_t priv_size,
return ab;
+err_free_wq:
+ destroy_workqueue(ab->workqueue);
err_sc_free:
kfree(ab);
return NULL;
diff --git a/drivers/net/wireless/ath/ath11k/core.h b/drivers/net/wireless/ath/ath11k/core.h
index 10846e9e871a..3fc49e633c29 100644
--- a/drivers/net/wireless/ath/ath11k/core.h
+++ b/drivers/net/wireless/ath/ath11k/core.h
@@ -39,6 +39,10 @@
extern unsigned int ath11k_frame_mode;
#define ATH11K_MON_TIMER_INTERVAL 10
+#define ATH11K_RESET_TIMEOUT_HZ (20 * HZ)
+#define ATH11K_RESET_MAX_FAIL_COUNT_FIRST 3
+#define ATH11K_RESET_MAX_FAIL_COUNT_FINAL 5
+#define ATH11K_RESET_FAIL_TIMEOUT_HZ (20 * HZ)
enum ath11k_supported_bw {
ATH11K_BW_20 = 0,
@@ -787,6 +791,15 @@ struct ath11k_base {
struct work_struct restart_work;
struct work_struct update_11d_work;
u8 new_alpha2[3];
+ struct workqueue_struct *workqueue_aux;
+ struct work_struct reset_work;
+ atomic_t reset_count;
+ atomic_t recovery_count;
+ bool is_reset;
+ struct completion reset_complete;
+ /* continuous recovery fail count */
+ atomic_t fail_cont_count;
+ unsigned long reset_fail_timeout;
struct {
/* protected by data_lock */
u32 fw_crash_counter;
diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index ed899055944e..c57a8f2c7820 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -7860,6 +7860,8 @@ ath11k_mac_op_reconfig_complete(struct ieee80211_hw *hw,
enum ieee80211_reconfig_type reconfig_type)
{
struct ath11k *ar = hw->priv;
+ struct ath11k_base *ab = ar->ab;
+ int recovery_count;
if (reconfig_type != IEEE80211_RECONFIG_TYPE_RESTART)
return;
@@ -7871,6 +7873,22 @@ ath11k_mac_op_reconfig_complete(struct ieee80211_hw *hw,
ar->pdev->pdev_id);
ar->state = ATH11K_STATE_ON;
ieee80211_wake_queues(ar->hw);
+
+ if (ab->is_reset) {
+ recovery_count = atomic_inc_return(&ab->recovery_count);
+ ath11k_dbg(ab, ATH11K_DBG_BOOT,
+ "recovery count %d\n", recovery_count);
+ /* When there are multiple radios in an SOC,
+ * the recovery has to be done for each radio
+ */
+ if (recovery_count == ab->num_radios) {
+ atomic_dec(&ab->reset_count);
+ complete(&ab->reset_complete);
+ ab->is_reset = false;
+ atomic_set(&ab->fail_cont_count, 0);
+ ath11k_dbg(ab, ATH11K_DBG_BOOT, "reset success\n");
+ }
+ }
}
mutex_unlock(&ar->conf_mutex);
diff --git a/drivers/net/wireless/ath/ath11k/mhi.c b/drivers/net/wireless/ath/ath11k/mhi.c
index fc3524e83e52..61d83be4841f 100644
--- a/drivers/net/wireless/ath/ath11k/mhi.c
+++ b/drivers/net/wireless/ath/ath11k/mhi.c
@@ -292,15 +292,48 @@ static void ath11k_mhi_op_runtime_put(struct mhi_controller *mhi_cntrl)
{
}
+static char *ath11k_mhi_op_callback_to_str(enum mhi_callback reason)
+{
+ switch (reason) {
+ case MHI_CB_IDLE:
+ return "MHI_CB_IDLE";
+ case MHI_CB_PENDING_DATA:
+ return "MHI_CB_PENDING_DATA";
+ case MHI_CB_LPM_ENTER:
+ return "MHI_CB_LPM_ENTER";
+ case MHI_CB_LPM_EXIT:
+ return "MHI_CB_LPM_EXIT";
+ case MHI_CB_EE_RDDM:
+ return "MHI_CB_EE_RDDM";
+ case MHI_CB_EE_MISSION_MODE:
+ return "MHI_CB_EE_MISSION_MODE";
+ case MHI_CB_SYS_ERROR:
+ return "MHI_CB_SYS_ERROR";
+ case MHI_CB_FATAL_ERROR:
+ return "MHI_CB_FATAL_ERROR";
+ case MHI_CB_BW_REQ:
+ return "MHI_CB_BW_REQ";
+ default:
+ return "UNKNOWN";
+ }
+};
+
static void ath11k_mhi_op_status_cb(struct mhi_controller *mhi_cntrl,
enum mhi_callback cb)
{
struct ath11k_base *ab = dev_get_drvdata(mhi_cntrl->cntrl_dev);
+ ath11k_dbg(ab, ATH11K_DBG_BOOT, "mhi notify status reason %s\n",
+ ath11k_mhi_op_callback_to_str(cb));
+
switch (cb) {
case MHI_CB_SYS_ERROR:
ath11k_warn(ab, "firmware crashed: MHI_CB_SYS_ERROR\n");
break;
+ case MHI_CB_EE_RDDM:
+ if (!(test_bit(ATH11K_FLAG_UNREGISTERING, &ab->dev_flags)))
+ queue_work(ab->workqueue_aux, &ab->reset_work);
+ break;
default:
break;
}
--
2.31.1
--
ath11k mailing list
ath11k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath11k
^ permalink raw reply related [flat|nested] 3+ messages in thread
* [PATCH v5 4/5] ath11k: add support for device recovery for QCA6390/WCN6855
@ 2022-02-08 10:49 ` Wen Gong
0 siblings, 0 replies; 3+ messages in thread
From: Wen Gong @ 2022-02-08 10:49 UTC (permalink / raw)
To: ath11k; +Cc: linux-wireless, quic_wgong
Currently ath11k has device recovery logic, it is introduced by this
patch "ath11k: Add support for subsystem recovery" which is upstream
by https://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git/commit/?h=ath11k-bringup&id=3a7b4838b6f6f234239f263ef3dc02e612a083ad.
The patch is for AHB devices such as IPQ8074, it has remote proc module
which is used to download the firmware and boots the processor which
firmware is running on. If firmware crashed, remote proc module will
detect it and download and boot firmware again. Below command will
trigger a firmware crash, and then user can test feature of device
recovery.
Test command:
echo assert > /sys/kernel/debug/ath11k/qca6390\ hw2.0/simulate_fw_crash
echo assert > /sys/kernel/debug/ath11k/wcn6855\ hw2.0/simulate_fw_crash
Unfortunately, QCA6390 is PCIe bus, it does not have the remote proc
module, it use mhi module to communicate between firmware and ath11k.
So ath11k does not support device recovery for QCA6390 currently.
This patch is to add the extra logic which is different for QCA6390.
When firmware crashed, MHI_CB_EE_RDDM event will be indicate by
firmware and then ath11k_mhi_op_status_cb which is the callback of
mhi_controller will receive the MHI_CB_EE_RDDM event, then ath11k
will start to do recovery process, ath11k_core_reset() calls
ath11k_hif_power_down()/ath11k_hif_power_up(), then the mhi/ath11k
will start to download and boot firmware. There are some logic to
avoid deadloop recovery and two simultaneous recovery operations.
And because it has muti-radios for the soc, so it add some logic
in ath11k_mac_op_reconfig_complete() to make sure all radios has
reconfig complete and then complete the device recovery.
Also it add workqueue_aux, because ab->workqueue is used when receive
ATH11K_QMI_EVENT_FW_READY in recovery process(queue_work(ab->workqueue,
&ab->restart_work)), and ath11k_core_reset will wait for max
ATH11K_RESET_TIMEOUT_HZ for the previous restart_work finished, if
ath11k_core_reset also queued in ab->workqueue, then it will delay
restart_work of previous recovery and lead previous recovery fail.
ath11k recovery success for QCA6390/WCN6855 after apply this patch.
Tested-on: QCA6390 hw2.0 PCI WLAN.HST.1.0.1-01740-QCAHSTSWPLZ_V2_TO_X86-1
Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03003-QCAHSPSWPL_V1_V2_SILICONZ_LITE-2
Signed-off-by: Wen Gong <quic_wgong@quicinc.com>
---
drivers/net/wireless/ath/ath11k/core.c | 70 ++++++++++++++++++++++++++
drivers/net/wireless/ath/ath11k/core.h | 13 +++++
drivers/net/wireless/ath/ath11k/mac.c | 18 +++++++
drivers/net/wireless/ath/ath11k/mhi.c | 33 ++++++++++++
4 files changed, 134 insertions(+)
diff --git a/drivers/net/wireless/ath/ath11k/core.c b/drivers/net/wireless/ath/ath11k/core.c
index 7c508e9baa6d..00c83fdb0702 100644
--- a/drivers/net/wireless/ath/ath11k/core.c
+++ b/drivers/net/wireless/ath/ath11k/core.c
@@ -1342,6 +1342,65 @@ static void ath11k_core_restart(struct work_struct *work)
complete(&ab->driver_recovery);
}
+static void ath11k_core_reset(struct work_struct *work)
+{
+ struct ath11k_base *ab = container_of(work, struct ath11k_base, reset_work);
+ int reset_count, fail_cont_count;
+ long time_left;
+
+ if (!(test_bit(ATH11K_FLAG_REGISTERED, &ab->dev_flags))) {
+ ath11k_warn(ab, "ignore reset dev flags 0x%lx\n", ab->dev_flags);
+ return;
+ }
+
+ /* Sometimes the recovery will fail and then the next all recovery fail,
+ * this is to avoid infinite recovery since it can not recovery success.
+ */
+ fail_cont_count = atomic_read(&ab->fail_cont_count);
+
+ if (fail_cont_count >= ATH11K_RESET_MAX_FAIL_COUNT_FINAL)
+ return;
+
+ if (fail_cont_count >= ATH11K_RESET_MAX_FAIL_COUNT_FIRST &&
+ time_before(jiffies, ab->reset_fail_timeout))
+ return;
+
+ reset_count = atomic_inc_return(&ab->reset_count);
+
+ if (reset_count > 1) {
+ /* Sometimes it happened another reset worker before the previous one
+ * completed, then the second reset worker will destroy the previous one,
+ * thus below is to avoid that.
+ */
+ ath11k_warn(ab, "already reseting count %d\n", reset_count);
+
+ reinit_completion(&ab->reset_complete);
+ time_left = wait_for_completion_timeout(&ab->reset_complete,
+ ATH11K_RESET_TIMEOUT_HZ);
+
+ if (time_left) {
+ ath11k_dbg(ab, ATH11K_DBG_BOOT, "to skip reset\n");
+ atomic_dec(&ab->reset_count);
+ return;
+ }
+
+ ab->reset_fail_timeout = jiffies + ATH11K_RESET_FAIL_TIMEOUT_HZ;
+ /* Record the continuous recovery fail count when recovery failed*/
+ fail_cont_count = atomic_inc_return(&ab->fail_cont_count);
+ }
+
+ ath11k_dbg(ab, ATH11K_DBG_BOOT, "reset starting\n");
+
+ ab->is_reset = true;
+ atomic_set(&ab->recovery_count, 0);
+
+ ath11k_hif_power_down(ab);
+ ath11k_qmi_free_resource(ab);
+ ath11k_hif_power_up(ab);
+
+ ath11k_dbg(ab, ATH11K_DBG_BOOT, "reset started\n");
+}
+
static int ath11k_init_hw_params(struct ath11k_base *ab)
{
const struct ath11k_hw_params *hw_params = NULL;
@@ -1411,6 +1470,9 @@ EXPORT_SYMBOL(ath11k_core_deinit);
void ath11k_core_free(struct ath11k_base *ab)
{
+ flush_workqueue(ab->workqueue_aux);
+ destroy_workqueue(ab->workqueue_aux);
+
flush_workqueue(ab->workqueue);
destroy_workqueue(ab->workqueue);
@@ -1434,9 +1496,14 @@ struct ath11k_base *ath11k_core_alloc(struct device *dev, size_t priv_size,
if (!ab->workqueue)
goto err_sc_free;
+ ab->workqueue_aux = create_singlethread_workqueue("ath11k_aux_wq");
+ if (!ab->workqueue_aux)
+ goto err_free_wq;
+
mutex_init(&ab->core_lock);
spin_lock_init(&ab->base_lock);
mutex_init(&ab->vdev_id_11d_lock);
+ init_completion(&ab->reset_complete);
INIT_LIST_HEAD(&ab->peers);
init_waitqueue_head(&ab->peer_mapping_wq);
@@ -1445,6 +1512,7 @@ struct ath11k_base *ath11k_core_alloc(struct device *dev, size_t priv_size,
INIT_WORK(&ab->restart_work, ath11k_core_restart);
INIT_WORK(&ab->update_11d_work, ath11k_update_11d);
INIT_WORK(&ab->rfkill_work, ath11k_rfkill_work);
+ INIT_WORK(&ab->reset_work, ath11k_core_reset);
timer_setup(&ab->rx_replenish_retry, ath11k_ce_rx_replenish_retry, 0);
init_completion(&ab->htc_suspend);
init_completion(&ab->wow.wakeup_completed);
@@ -1455,6 +1523,8 @@ struct ath11k_base *ath11k_core_alloc(struct device *dev, size_t priv_size,
return ab;
+err_free_wq:
+ destroy_workqueue(ab->workqueue);
err_sc_free:
kfree(ab);
return NULL;
diff --git a/drivers/net/wireless/ath/ath11k/core.h b/drivers/net/wireless/ath/ath11k/core.h
index 10846e9e871a..3fc49e633c29 100644
--- a/drivers/net/wireless/ath/ath11k/core.h
+++ b/drivers/net/wireless/ath/ath11k/core.h
@@ -39,6 +39,10 @@
extern unsigned int ath11k_frame_mode;
#define ATH11K_MON_TIMER_INTERVAL 10
+#define ATH11K_RESET_TIMEOUT_HZ (20 * HZ)
+#define ATH11K_RESET_MAX_FAIL_COUNT_FIRST 3
+#define ATH11K_RESET_MAX_FAIL_COUNT_FINAL 5
+#define ATH11K_RESET_FAIL_TIMEOUT_HZ (20 * HZ)
enum ath11k_supported_bw {
ATH11K_BW_20 = 0,
@@ -787,6 +791,15 @@ struct ath11k_base {
struct work_struct restart_work;
struct work_struct update_11d_work;
u8 new_alpha2[3];
+ struct workqueue_struct *workqueue_aux;
+ struct work_struct reset_work;
+ atomic_t reset_count;
+ atomic_t recovery_count;
+ bool is_reset;
+ struct completion reset_complete;
+ /* continuous recovery fail count */
+ atomic_t fail_cont_count;
+ unsigned long reset_fail_timeout;
struct {
/* protected by data_lock */
u32 fw_crash_counter;
diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index ed899055944e..c57a8f2c7820 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -7860,6 +7860,8 @@ ath11k_mac_op_reconfig_complete(struct ieee80211_hw *hw,
enum ieee80211_reconfig_type reconfig_type)
{
struct ath11k *ar = hw->priv;
+ struct ath11k_base *ab = ar->ab;
+ int recovery_count;
if (reconfig_type != IEEE80211_RECONFIG_TYPE_RESTART)
return;
@@ -7871,6 +7873,22 @@ ath11k_mac_op_reconfig_complete(struct ieee80211_hw *hw,
ar->pdev->pdev_id);
ar->state = ATH11K_STATE_ON;
ieee80211_wake_queues(ar->hw);
+
+ if (ab->is_reset) {
+ recovery_count = atomic_inc_return(&ab->recovery_count);
+ ath11k_dbg(ab, ATH11K_DBG_BOOT,
+ "recovery count %d\n", recovery_count);
+ /* When there are multiple radios in an SOC,
+ * the recovery has to be done for each radio
+ */
+ if (recovery_count == ab->num_radios) {
+ atomic_dec(&ab->reset_count);
+ complete(&ab->reset_complete);
+ ab->is_reset = false;
+ atomic_set(&ab->fail_cont_count, 0);
+ ath11k_dbg(ab, ATH11K_DBG_BOOT, "reset success\n");
+ }
+ }
}
mutex_unlock(&ar->conf_mutex);
diff --git a/drivers/net/wireless/ath/ath11k/mhi.c b/drivers/net/wireless/ath/ath11k/mhi.c
index fc3524e83e52..61d83be4841f 100644
--- a/drivers/net/wireless/ath/ath11k/mhi.c
+++ b/drivers/net/wireless/ath/ath11k/mhi.c
@@ -292,15 +292,48 @@ static void ath11k_mhi_op_runtime_put(struct mhi_controller *mhi_cntrl)
{
}
+static char *ath11k_mhi_op_callback_to_str(enum mhi_callback reason)
+{
+ switch (reason) {
+ case MHI_CB_IDLE:
+ return "MHI_CB_IDLE";
+ case MHI_CB_PENDING_DATA:
+ return "MHI_CB_PENDING_DATA";
+ case MHI_CB_LPM_ENTER:
+ return "MHI_CB_LPM_ENTER";
+ case MHI_CB_LPM_EXIT:
+ return "MHI_CB_LPM_EXIT";
+ case MHI_CB_EE_RDDM:
+ return "MHI_CB_EE_RDDM";
+ case MHI_CB_EE_MISSION_MODE:
+ return "MHI_CB_EE_MISSION_MODE";
+ case MHI_CB_SYS_ERROR:
+ return "MHI_CB_SYS_ERROR";
+ case MHI_CB_FATAL_ERROR:
+ return "MHI_CB_FATAL_ERROR";
+ case MHI_CB_BW_REQ:
+ return "MHI_CB_BW_REQ";
+ default:
+ return "UNKNOWN";
+ }
+};
+
static void ath11k_mhi_op_status_cb(struct mhi_controller *mhi_cntrl,
enum mhi_callback cb)
{
struct ath11k_base *ab = dev_get_drvdata(mhi_cntrl->cntrl_dev);
+ ath11k_dbg(ab, ATH11K_DBG_BOOT, "mhi notify status reason %s\n",
+ ath11k_mhi_op_callback_to_str(cb));
+
switch (cb) {
case MHI_CB_SYS_ERROR:
ath11k_warn(ab, "firmware crashed: MHI_CB_SYS_ERROR\n");
break;
+ case MHI_CB_EE_RDDM:
+ if (!(test_bit(ATH11K_FLAG_UNREGISTERING, &ab->dev_flags)))
+ queue_work(ab->workqueue_aux, &ab->reset_work);
+ break;
default:
break;
}
--
2.31.1
^ permalink raw reply related [flat|nested] 3+ messages in thread
end of thread, other threads:[~2022-02-10 10:22 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2022-02-10 10:22 [PATCH v5 4/5] ath11k: add support for device recovery for QCA6390/WCN6855 kernel test robot
-- strict thread matches above, loose matches on Subject: below --
2022-02-08 10:49 [PATCH v5 0/5] ath11k: add feature for device recovery Wen Gong
2022-02-08 10:49 ` [PATCH v5 4/5] ath11k: add support for device recovery for QCA6390/WCN6855 Wen Gong
2022-02-08 10:49 ` Wen Gong
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.