[PATCH v5 0/5] ath11k: add feature for device recovery

[PATCH v5 0/5] ath11k: add feature for device recovery

[Wen Gong]

Currently recovery is work success for QCA6390/WCN6855 without the RDDM dump feature,
because patch "ath11k: configure RDDM size to mhi for recovery by firmware"
added in v5.

v5:
    1. rebased to ath.git ath-202202030905
    2. change a few commit message
    3. fix count set sequence of ath11k_core_reset in "ath11k: add synchronization operation between reconfigure of mac80211 and ath11k_base"
    4. add patch "ath11k: configure RDDM size to mhi for recovery by firmware" to support RDDM
    5. move destroy_workqueue(ab->workqueue_aux) from ath11k_pci_remove() to ath11k_core_free()

v4: add patch "ath11k: fix invalid m3 buffer address"
    recovery will fail when download firmware without this patch

v3: remove time_left set but not used in
    "ath11k: add synchronization operation between reconfigure of mac80211 and ath11k_base"

v2: s/initilized/initialized in commit log of patch
    "ath11k: add synchronization operation between reconfigure of mac80211 and ath11k_base"

Add support for device recovery.

Carl Huang (1):
  ath11k: fix invalid m3 buffer address

Wen Gong (4):
  ath11k: add ath11k_qmi_free_resource() for recovery
  ath11k: configure RDDM size to mhi for recovery by firmware
  ath11k: add support for device recovery for QCA6390/WCN6855
  ath11k: add synchronization operation between reconfigure of mac80211
    and ath11k_base

 drivers/net/wireless/ath/ath11k/core.c | 121 +++++++++++++++++++++++--
 drivers/net/wireless/ath/ath11k/core.h |  18 ++++
 drivers/net/wireless/ath/ath11k/mac.c  |  40 ++++++++
 drivers/net/wireless/ath/ath11k/mhi.c  |  35 +++++++
 drivers/net/wireless/ath/ath11k/qmi.c  |   6 ++
 drivers/net/wireless/ath/ath11k/qmi.h  |   1 +
 6 files changed, 213 insertions(+), 8 deletions(-)


base-commit: 76680d49b5e0e661bc4abcdaf13fb7e124b4ca08
-- 
2.31.1


-- 
ath11k mailing list
ath11k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath11k

[PATCH v5 0/5] ath11k: add feature for device recovery

[Wen Gong]

Currently recovery is work success for QCA6390/WCN6855 without the RDDM dump feature,
because patch "ath11k: configure RDDM size to mhi for recovery by firmware"
added in v5.

v5:
    1. rebased to ath.git ath-202202030905
    2. change a few commit message
    3. fix count set sequence of ath11k_core_reset in "ath11k: add synchronization operation between reconfigure of mac80211 and ath11k_base"
    4. add patch "ath11k: configure RDDM size to mhi for recovery by firmware" to support RDDM
    5. move destroy_workqueue(ab->workqueue_aux) from ath11k_pci_remove() to ath11k_core_free()

v4: add patch "ath11k: fix invalid m3 buffer address"
    recovery will fail when download firmware without this patch

v3: remove time_left set but not used in
    "ath11k: add synchronization operation between reconfigure of mac80211 and ath11k_base"

v2: s/initilized/initialized in commit log of patch
    "ath11k: add synchronization operation between reconfigure of mac80211 and ath11k_base"

Add support for device recovery.

Carl Huang (1):
  ath11k: fix invalid m3 buffer address

Wen Gong (4):
  ath11k: add ath11k_qmi_free_resource() for recovery
  ath11k: configure RDDM size to mhi for recovery by firmware
  ath11k: add support for device recovery for QCA6390/WCN6855
  ath11k: add synchronization operation between reconfigure of mac80211
    and ath11k_base

 drivers/net/wireless/ath/ath11k/core.c | 121 +++++++++++++++++++++++--
 drivers/net/wireless/ath/ath11k/core.h |  18 ++++
 drivers/net/wireless/ath/ath11k/mac.c  |  40 ++++++++
 drivers/net/wireless/ath/ath11k/mhi.c  |  35 +++++++
 drivers/net/wireless/ath/ath11k/qmi.c  |   6 ++
 drivers/net/wireless/ath/ath11k/qmi.h  |   1 +
 6 files changed, 213 insertions(+), 8 deletions(-)


base-commit: 76680d49b5e0e661bc4abcdaf13fb7e124b4ca08
-- 
2.31.1

[PATCH v5 1/5] ath11k: add ath11k_qmi_free_resource() for recovery

[Wen Gong]

ath11k_qmi_free_target_mem_chunk() and ath11k_qmi_m3_free() is static
in qmi.c, they are needed for recovery, export them in a new function.

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/qmi.c | 5 +++++
 drivers/net/wireless/ath/ath11k/qmi.h | 1 +
 2 files changed, 6 insertions(+)

diff --git a/drivers/net/wireless/ath/ath11k/qmi.c b/drivers/net/wireless/ath/ath11k/qmi.c
index d0701e8eca9c..1144e828cf5c 100644
--- a/drivers/net/wireless/ath/ath11k/qmi.c
+++ b/drivers/net/wireless/ath/ath11k/qmi.c
@@ -3025,3 +3025,8 @@ void ath11k_qmi_deinit_service(struct ath11k_base *ab)
 }
 EXPORT_SYMBOL(ath11k_qmi_deinit_service);
 
+void ath11k_qmi_free_resource(struct ath11k_base *ab)
+{
+	ath11k_qmi_free_target_mem_chunk(ab);
+	ath11k_qmi_m3_free(ab);
+}
diff --git a/drivers/net/wireless/ath/ath11k/qmi.h b/drivers/net/wireless/ath/ath11k/qmi.h
index ba2eff4d59cb..61678de56ac7 100644
--- a/drivers/net/wireless/ath/ath11k/qmi.h
+++ b/drivers/net/wireless/ath/ath11k/qmi.h
@@ -492,5 +492,6 @@ void ath11k_qmi_event_work(struct work_struct *work);
 void ath11k_qmi_msg_recv_work(struct work_struct *work);
 void ath11k_qmi_deinit_service(struct ath11k_base *ab);
 int ath11k_qmi_init_service(struct ath11k_base *ab);
+void ath11k_qmi_free_resource(struct ath11k_base *ab);
 
 #endif
-- 
2.31.1


-- 
ath11k mailing list
ath11k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath11k

[PATCH v5 1/5] ath11k: add ath11k_qmi_free_resource() for recovery

[Wen Gong]

ath11k_qmi_free_target_mem_chunk() and ath11k_qmi_m3_free() is static
in qmi.c, they are needed for recovery, export them in a new function.

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/qmi.c | 5 +++++
 drivers/net/wireless/ath/ath11k/qmi.h | 1 +
 2 files changed, 6 insertions(+)

diff --git a/drivers/net/wireless/ath/ath11k/qmi.c b/drivers/net/wireless/ath/ath11k/qmi.c
index d0701e8eca9c..1144e828cf5c 100644
--- a/drivers/net/wireless/ath/ath11k/qmi.c
+++ b/drivers/net/wireless/ath/ath11k/qmi.c
@@ -3025,3 +3025,8 @@ void ath11k_qmi_deinit_service(struct ath11k_base *ab)
 }
 EXPORT_SYMBOL(ath11k_qmi_deinit_service);
 
+void ath11k_qmi_free_resource(struct ath11k_base *ab)
+{
+	ath11k_qmi_free_target_mem_chunk(ab);
+	ath11k_qmi_m3_free(ab);
+}
diff --git a/drivers/net/wireless/ath/ath11k/qmi.h b/drivers/net/wireless/ath/ath11k/qmi.h
index ba2eff4d59cb..61678de56ac7 100644
--- a/drivers/net/wireless/ath/ath11k/qmi.h
+++ b/drivers/net/wireless/ath/ath11k/qmi.h
@@ -492,5 +492,6 @@ void ath11k_qmi_event_work(struct work_struct *work);
 void ath11k_qmi_msg_recv_work(struct work_struct *work);
 void ath11k_qmi_deinit_service(struct ath11k_base *ab);
 int ath11k_qmi_init_service(struct ath11k_base *ab);
+void ath11k_qmi_free_resource(struct ath11k_base *ab);
 
 #endif
-- 
2.31.1

[PATCH v5 2/5] ath11k: fix invalid m3 buffer address

[Wen Gong]

From: Carl Huang <quic_cjhuang@quicinc.com>

This is to fix m3 buffer reuse issue as m3_mem->size isn't set to
ZERO in free function, which leads invalid m3 downloading to
firmware and firmware crashed.

Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03003-QCAHSPSWPL_V1_V2_SILICONZ_LITE-2

Signed-off-by: Carl Huang <quic_cjhuang@quicinc.com>
Signed-off-by: Wen Gong <quic_wgong@quicinc.com>
---
 drivers/net/wireless/ath/ath11k/qmi.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/ath/ath11k/qmi.c b/drivers/net/wireless/ath/ath11k/qmi.c
index 1144e828cf5c..d4d831566a89 100644
--- a/drivers/net/wireless/ath/ath11k/qmi.c
+++ b/drivers/net/wireless/ath/ath11k/qmi.c
@@ -2342,6 +2342,7 @@ static void ath11k_qmi_m3_free(struct ath11k_base *ab)
 	dma_free_coherent(ab->dev, m3_mem->size,
 			  m3_mem->vaddr, m3_mem->paddr);
 	m3_mem->vaddr = NULL;
+	m3_mem->size = 0;
 }
 
 static int ath11k_qmi_wlanfw_m3_info_send(struct ath11k_base *ab)
-- 
2.31.1


-- 
ath11k mailing list
ath11k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath11k

[PATCH v5 2/5] ath11k: fix invalid m3 buffer address

[Wen Gong]

From: Carl Huang <quic_cjhuang@quicinc.com>

This is to fix m3 buffer reuse issue as m3_mem->size isn't set to
ZERO in free function, which leads invalid m3 downloading to
firmware and firmware crashed.

Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03003-QCAHSPSWPL_V1_V2_SILICONZ_LITE-2

Signed-off-by: Carl Huang <quic_cjhuang@quicinc.com>
Signed-off-by: Wen Gong <quic_wgong@quicinc.com>
---
 drivers/net/wireless/ath/ath11k/qmi.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/ath/ath11k/qmi.c b/drivers/net/wireless/ath/ath11k/qmi.c
index 1144e828cf5c..d4d831566a89 100644
--- a/drivers/net/wireless/ath/ath11k/qmi.c
+++ b/drivers/net/wireless/ath/ath11k/qmi.c
@@ -2342,6 +2342,7 @@ static void ath11k_qmi_m3_free(struct ath11k_base *ab)
 	dma_free_coherent(ab->dev, m3_mem->size,
 			  m3_mem->vaddr, m3_mem->paddr);
 	m3_mem->vaddr = NULL;
+	m3_mem->size = 0;
 }
 
 static int ath11k_qmi_wlanfw_m3_info_send(struct ath11k_base *ab)
-- 
2.31.1

[PATCH v5 3/5] ath11k: configure RDDM size to mhi for recovery by firmware

[Wen Gong]

The rddm_size is needed by firmware while mhi enter RDDM state, add it
to support recovery when ath11k receive MHI_CB_EE_RDDM message.

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/mhi.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/ath/ath11k/mhi.c b/drivers/net/wireless/ath/ath11k/mhi.c
index 8b2143802816..fc3524e83e52 100644
--- a/drivers/net/wireless/ath/ath11k/mhi.c
+++ b/drivers/net/wireless/ath/ath11k/mhi.c
@@ -13,6 +13,7 @@
 #include "pci.h"
 
 #define MHI_TIMEOUT_DEFAULT_MS	90000
+#define RDDM_DUMP_SIZE	0x420000
 
 static struct mhi_channel_config ath11k_mhi_channels_qca6390[] = {
 	{
@@ -382,6 +383,7 @@ int ath11k_mhi_register(struct ath11k_pci *ab_pci)
 		mhi_ctrl->iova_stop = 0xFFFFFFFF;
 	}
 
+	mhi_ctrl->rddm_size = RDDM_DUMP_SIZE;
 	mhi_ctrl->sbl_size = SZ_512K;
 	mhi_ctrl->seg_len = SZ_512K;
 	mhi_ctrl->fbc_download = true;
-- 
2.31.1


-- 
ath11k mailing list
ath11k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath11k

[PATCH v5 3/5] ath11k: configure RDDM size to mhi for recovery by firmware

[Wen Gong]

The rddm_size is needed by firmware while mhi enter RDDM state, add it
to support recovery when ath11k receive MHI_CB_EE_RDDM message.

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/mhi.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/ath/ath11k/mhi.c b/drivers/net/wireless/ath/ath11k/mhi.c
index 8b2143802816..fc3524e83e52 100644
--- a/drivers/net/wireless/ath/ath11k/mhi.c
+++ b/drivers/net/wireless/ath/ath11k/mhi.c
@@ -13,6 +13,7 @@
 #include "pci.h"
 
 #define MHI_TIMEOUT_DEFAULT_MS	90000
+#define RDDM_DUMP_SIZE	0x420000
 
 static struct mhi_channel_config ath11k_mhi_channels_qca6390[] = {
 	{
@@ -382,6 +383,7 @@ int ath11k_mhi_register(struct ath11k_pci *ab_pci)
 		mhi_ctrl->iova_stop = 0xFFFFFFFF;
 	}
 
+	mhi_ctrl->rddm_size = RDDM_DUMP_SIZE;
 	mhi_ctrl->sbl_size = SZ_512K;
 	mhi_ctrl->seg_len = SZ_512K;
 	mhi_ctrl->fbc_download = true;
-- 
2.31.1

[PATCH v5 4/5] ath11k: add support for device recovery for QCA6390/WCN6855

[Wen Gong]

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

[PATCH v5 4/5] ath11k: add support for device recovery for QCA6390/WCN6855

[Wen Gong]

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

[PATCH v5 5/5] ath11k: add synchronization operation between reconfigure of mac80211 and ath11k_base

[Wen Gong]

ieee80211_reconfig() of mac80211 is the main function for recovery of
each ieee80211_hw and ath11k, and ath11k_core_reconfigure_on_crash()
is the main function for recovery of ath11k_base, it has more than
one ieee80211_hw and ath11k for each ath11k_base, so it need to add
synchronization between them, otherwise it has many issue.

For example, when ath11k_core_reconfigure_on_crash() is not complete,
mac80211 send a hw scan request to ath11k, it leads firmware crash,
because firmware has not been initialized at that moment, firmware
is only finished downloaded and loaded, it can not receive scan
command.

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 | 51 ++++++++++++++++++++++----
 drivers/net/wireless/ath/ath11k/core.h |  5 +++
 drivers/net/wireless/ath/ath11k/mac.c  | 22 +++++++++++
 3 files changed, 70 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/core.c b/drivers/net/wireless/ath/ath11k/core.c
index 00c83fdb0702..8ce93fd9e1e6 100644
--- a/drivers/net/wireless/ath/ath11k/core.c
+++ b/drivers/net/wireless/ath/ath11k/core.c
@@ -1263,12 +1263,11 @@ static void ath11k_update_11d(struct work_struct *work)
 	}
 }
 
-static void ath11k_core_restart(struct work_struct *work)
+static void ath11k_core_pre_reconfigure_recovery(struct ath11k_base *ab)
 {
-	struct ath11k_base *ab = container_of(work, struct ath11k_base, restart_work);
 	struct ath11k *ar;
 	struct ath11k_pdev *pdev;
-	int i, ret = 0;
+	int i;
 
 	spin_lock_bh(&ab->base_lock);
 	ab->stats.fw_crash_counter++;
@@ -1301,12 +1300,13 @@ static void ath11k_core_restart(struct work_struct *work)
 
 	wake_up(&ab->wmi_ab.tx_credits_wq);
 	wake_up(&ab->peer_mapping_wq);
+}
 
-	ret = ath11k_core_reconfigure_on_crash(ab);
-	if (ret) {
-		ath11k_err(ab, "failed to reconfigure driver on crash recovery\n");
-		return;
-	}
+static void ath11k_core_post_reconfigure_recovery(struct ath11k_base *ab)
+{
+	struct ath11k *ar;
+	struct ath11k_pdev *pdev;
+	int i;
 
 	for (i = 0; i < ab->num_radios; i++) {
 		pdev = &ab->pdevs[i];
@@ -1342,6 +1342,27 @@ static void ath11k_core_restart(struct work_struct *work)
 	complete(&ab->driver_recovery);
 }
 
+static void ath11k_core_restart(struct work_struct *work)
+{
+	struct ath11k_base *ab = container_of(work, struct ath11k_base, restart_work);
+	int ret;
+
+	if (!ab->is_reset)
+		ath11k_core_pre_reconfigure_recovery(ab);
+
+	ret = ath11k_core_reconfigure_on_crash(ab);
+	if (ret) {
+		ath11k_err(ab, "failed to reconfigure driver on crash recovery\n");
+		return;
+	}
+
+	if (ab->is_reset)
+		complete_all(&ab->reconfigure_complete);
+
+	if (!ab->is_reset)
+		ath11k_core_post_reconfigure_recovery(ab);
+}
+
 static void ath11k_core_reset(struct work_struct *work)
 {
 	struct ath11k_base *ab = container_of(work, struct ath11k_base, reset_work);
@@ -1393,6 +1414,18 @@ static void ath11k_core_reset(struct work_struct *work)
 
 	ab->is_reset = true;
 	atomic_set(&ab->recovery_count, 0);
+	reinit_completion(&ab->recovery_start);
+	atomic_set(&ab->recovery_start_count, 0);
+
+	ath11k_core_pre_reconfigure_recovery(ab);
+
+	reinit_completion(&ab->reconfigure_complete);
+	ath11k_core_post_reconfigure_recovery(ab);
+
+	ath11k_dbg(ab, ATH11K_DBG_BOOT, "waiting recovery start...\n");
+
+	time_left = wait_for_completion_timeout(&ab->recovery_start,
+						ATH11K_RECOVER_START_TIMEOUT_HZ);
 
 	ath11k_hif_power_down(ab);
 	ath11k_qmi_free_resource(ab);
@@ -1504,6 +1537,8 @@ struct ath11k_base *ath11k_core_alloc(struct device *dev, size_t priv_size,
 	spin_lock_init(&ab->base_lock);
 	mutex_init(&ab->vdev_id_11d_lock);
 	init_completion(&ab->reset_complete);
+	init_completion(&ab->reconfigure_complete);
+	init_completion(&ab->recovery_start);
 
 	INIT_LIST_HEAD(&ab->peers);
 	init_waitqueue_head(&ab->peer_mapping_wq);
diff --git a/drivers/net/wireless/ath/ath11k/core.h b/drivers/net/wireless/ath/ath11k/core.h
index 3fc49e633c29..0fd5a7ee6304 100644
--- a/drivers/net/wireless/ath/ath11k/core.h
+++ b/drivers/net/wireless/ath/ath11k/core.h
@@ -43,6 +43,8 @@ extern unsigned int ath11k_frame_mode;
 #define ATH11K_RESET_MAX_FAIL_COUNT_FIRST 3
 #define ATH11K_RESET_MAX_FAIL_COUNT_FINAL 5
 #define ATH11K_RESET_FAIL_TIMEOUT_HZ (20 * HZ)
+#define ATH11K_RECONFIGURE_TIMEOUT_HZ (10 * HZ)
+#define ATH11K_RECOVER_START_TIMEOUT_HZ (20 * HZ)
 
 enum ath11k_supported_bw {
 	ATH11K_BW_20	= 0,
@@ -795,8 +797,11 @@ struct ath11k_base {
 	struct work_struct reset_work;
 	atomic_t reset_count;
 	atomic_t recovery_count;
+	atomic_t recovery_start_count;
 	bool is_reset;
 	struct completion reset_complete;
+	struct completion reconfigure_complete;
+	struct completion recovery_start;
 	/* continuous recovery fail count */
 	atomic_t fail_cont_count;
 	unsigned long reset_fail_timeout;
diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index c57a8f2c7820..1a735bb804e1 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -5726,6 +5726,27 @@ static int ath11k_mac_config_mon_status_default(struct ath11k *ar, bool enable)
 	return ret;
 }
 
+static void ath11k_mac_wait_reconfigure(struct ath11k_base *ab)
+{
+	int recovery_start_count;
+
+	if (!ab->is_reset)
+		return;
+
+	recovery_start_count = atomic_inc_return(&ab->recovery_start_count);
+	ath11k_dbg(ab, ATH11K_DBG_MAC, "recovery start count %d\n", recovery_start_count);
+
+	if (recovery_start_count == ab->num_radios) {
+		complete(&ab->recovery_start);
+		ath11k_dbg(ab, ATH11K_DBG_MAC, "recovery started success\n");
+	}
+
+	ath11k_dbg(ab, ATH11K_DBG_MAC, "waiting reconfigure...\n");
+
+	wait_for_completion_timeout(&ab->reconfigure_complete,
+				    ATH11K_RECONFIGURE_TIMEOUT_HZ);
+}
+
 static int ath11k_mac_op_start(struct ieee80211_hw *hw)
 {
 	struct ath11k *ar = hw->priv;
@@ -5742,6 +5763,7 @@ static int ath11k_mac_op_start(struct ieee80211_hw *hw)
 		break;
 	case ATH11K_STATE_RESTARTING:
 		ar->state = ATH11K_STATE_RESTARTED;
+		ath11k_mac_wait_reconfigure(ab);
 		break;
 	case ATH11K_STATE_RESTARTED:
 	case ATH11K_STATE_WEDGED:
-- 
2.31.1


-- 
ath11k mailing list
ath11k@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/ath11k

[PATCH v5 5/5] ath11k: add synchronization operation between reconfigure of mac80211 and ath11k_base

[Wen Gong]

ieee80211_reconfig() of mac80211 is the main function for recovery of
each ieee80211_hw and ath11k, and ath11k_core_reconfigure_on_crash()
is the main function for recovery of ath11k_base, it has more than
one ieee80211_hw and ath11k for each ath11k_base, so it need to add
synchronization between them, otherwise it has many issue.

For example, when ath11k_core_reconfigure_on_crash() is not complete,
mac80211 send a hw scan request to ath11k, it leads firmware crash,
because firmware has not been initialized at that moment, firmware
is only finished downloaded and loaded, it can not receive scan
command.

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 | 51 ++++++++++++++++++++++----
 drivers/net/wireless/ath/ath11k/core.h |  5 +++
 drivers/net/wireless/ath/ath11k/mac.c  | 22 +++++++++++
 3 files changed, 70 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/core.c b/drivers/net/wireless/ath/ath11k/core.c
index 00c83fdb0702..8ce93fd9e1e6 100644
--- a/drivers/net/wireless/ath/ath11k/core.c
+++ b/drivers/net/wireless/ath/ath11k/core.c
@@ -1263,12 +1263,11 @@ static void ath11k_update_11d(struct work_struct *work)
 	}
 }
 
-static void ath11k_core_restart(struct work_struct *work)
+static void ath11k_core_pre_reconfigure_recovery(struct ath11k_base *ab)
 {
-	struct ath11k_base *ab = container_of(work, struct ath11k_base, restart_work);
 	struct ath11k *ar;
 	struct ath11k_pdev *pdev;
-	int i, ret = 0;
+	int i;
 
 	spin_lock_bh(&ab->base_lock);
 	ab->stats.fw_crash_counter++;
@@ -1301,12 +1300,13 @@ static void ath11k_core_restart(struct work_struct *work)
 
 	wake_up(&ab->wmi_ab.tx_credits_wq);
 	wake_up(&ab->peer_mapping_wq);
+}
 
-	ret = ath11k_core_reconfigure_on_crash(ab);
-	if (ret) {
-		ath11k_err(ab, "failed to reconfigure driver on crash recovery\n");
-		return;
-	}
+static void ath11k_core_post_reconfigure_recovery(struct ath11k_base *ab)
+{
+	struct ath11k *ar;
+	struct ath11k_pdev *pdev;
+	int i;
 
 	for (i = 0; i < ab->num_radios; i++) {
 		pdev = &ab->pdevs[i];
@@ -1342,6 +1342,27 @@ static void ath11k_core_restart(struct work_struct *work)
 	complete(&ab->driver_recovery);
 }
 
+static void ath11k_core_restart(struct work_struct *work)
+{
+	struct ath11k_base *ab = container_of(work, struct ath11k_base, restart_work);
+	int ret;
+
+	if (!ab->is_reset)
+		ath11k_core_pre_reconfigure_recovery(ab);
+
+	ret = ath11k_core_reconfigure_on_crash(ab);
+	if (ret) {
+		ath11k_err(ab, "failed to reconfigure driver on crash recovery\n");
+		return;
+	}
+
+	if (ab->is_reset)
+		complete_all(&ab->reconfigure_complete);
+
+	if (!ab->is_reset)
+		ath11k_core_post_reconfigure_recovery(ab);
+}
+
 static void ath11k_core_reset(struct work_struct *work)
 {
 	struct ath11k_base *ab = container_of(work, struct ath11k_base, reset_work);
@@ -1393,6 +1414,18 @@ static void ath11k_core_reset(struct work_struct *work)
 
 	ab->is_reset = true;
 	atomic_set(&ab->recovery_count, 0);
+	reinit_completion(&ab->recovery_start);
+	atomic_set(&ab->recovery_start_count, 0);
+
+	ath11k_core_pre_reconfigure_recovery(ab);
+
+	reinit_completion(&ab->reconfigure_complete);
+	ath11k_core_post_reconfigure_recovery(ab);
+
+	ath11k_dbg(ab, ATH11K_DBG_BOOT, "waiting recovery start...\n");
+
+	time_left = wait_for_completion_timeout(&ab->recovery_start,
+						ATH11K_RECOVER_START_TIMEOUT_HZ);
 
 	ath11k_hif_power_down(ab);
 	ath11k_qmi_free_resource(ab);
@@ -1504,6 +1537,8 @@ struct ath11k_base *ath11k_core_alloc(struct device *dev, size_t priv_size,
 	spin_lock_init(&ab->base_lock);
 	mutex_init(&ab->vdev_id_11d_lock);
 	init_completion(&ab->reset_complete);
+	init_completion(&ab->reconfigure_complete);
+	init_completion(&ab->recovery_start);
 
 	INIT_LIST_HEAD(&ab->peers);
 	init_waitqueue_head(&ab->peer_mapping_wq);
diff --git a/drivers/net/wireless/ath/ath11k/core.h b/drivers/net/wireless/ath/ath11k/core.h
index 3fc49e633c29..0fd5a7ee6304 100644
--- a/drivers/net/wireless/ath/ath11k/core.h
+++ b/drivers/net/wireless/ath/ath11k/core.h
@@ -43,6 +43,8 @@ extern unsigned int ath11k_frame_mode;
 #define ATH11K_RESET_MAX_FAIL_COUNT_FIRST 3
 #define ATH11K_RESET_MAX_FAIL_COUNT_FINAL 5
 #define ATH11K_RESET_FAIL_TIMEOUT_HZ (20 * HZ)
+#define ATH11K_RECONFIGURE_TIMEOUT_HZ (10 * HZ)
+#define ATH11K_RECOVER_START_TIMEOUT_HZ (20 * HZ)
 
 enum ath11k_supported_bw {
 	ATH11K_BW_20	= 0,
@@ -795,8 +797,11 @@ struct ath11k_base {
 	struct work_struct reset_work;
 	atomic_t reset_count;
 	atomic_t recovery_count;
+	atomic_t recovery_start_count;
 	bool is_reset;
 	struct completion reset_complete;
+	struct completion reconfigure_complete;
+	struct completion recovery_start;
 	/* continuous recovery fail count */
 	atomic_t fail_cont_count;
 	unsigned long reset_fail_timeout;
diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index c57a8f2c7820..1a735bb804e1 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -5726,6 +5726,27 @@ static int ath11k_mac_config_mon_status_default(struct ath11k *ar, bool enable)
 	return ret;
 }
 
+static void ath11k_mac_wait_reconfigure(struct ath11k_base *ab)
+{
+	int recovery_start_count;
+
+	if (!ab->is_reset)
+		return;
+
+	recovery_start_count = atomic_inc_return(&ab->recovery_start_count);
+	ath11k_dbg(ab, ATH11K_DBG_MAC, "recovery start count %d\n", recovery_start_count);
+
+	if (recovery_start_count == ab->num_radios) {
+		complete(&ab->recovery_start);
+		ath11k_dbg(ab, ATH11K_DBG_MAC, "recovery started success\n");
+	}
+
+	ath11k_dbg(ab, ATH11K_DBG_MAC, "waiting reconfigure...\n");
+
+	wait_for_completion_timeout(&ab->reconfigure_complete,
+				    ATH11K_RECONFIGURE_TIMEOUT_HZ);
+}
+
 static int ath11k_mac_op_start(struct ieee80211_hw *hw)
 {
 	struct ath11k *ar = hw->priv;
@@ -5742,6 +5763,7 @@ static int ath11k_mac_op_start(struct ieee80211_hw *hw)
 		break;
 	case ATH11K_STATE_RESTARTING:
 		ar->state = ATH11K_STATE_RESTARTED;
+		ath11k_mac_wait_reconfigure(ab);
 		break;
 	case ATH11K_STATE_RESTARTED:
 	case ATH11K_STATE_WEDGED:
-- 
2.31.1