[PATCH v2 5/5] wifi: brcmfmac: pcie: support inband device wake and deep sleep

[Andre Eikmeyer <dev@deq.rocks>]

The BCM4364 and BCM4377 firmware report inband deep sleep in the PCIe
shared flags. The driver only advertises that it has no out-of-band
device wake, which leaves deep sleep disabled. The firmware then stays
awake and keeps its latency tolerance short enough to hold the package
out of PC10.

Advertise inband device wake when the firmware supports it and follow
the handshake of the firmware. The device asks for deep sleep while
device wake is deasserted, the host acknowledges it once it has nothing
to send, asserts device wake before it uses the rings again and waits
for the exit note, and deasserts device wake after 200 ms without ring
writes. Hooks around the ring lock cover every host to device ring
writer. A system suspend asserts device wake before D3_INFORM and
acknowledges no deep sleep request until the resume.

Tested on a MacBookPro15,1 (BCM4364) and a MacBookAir9,1 (BCM4377). The
firmware enters and leaves deep sleep about 40 times a minute at idle
with Wi-Fi associated, traffic and downloads work, and the package
reaches PC10 without ignoring the latency tolerance of the Wi-Fi port.

Signed-off-by: Andre Eikmeyer <dev@deq.rocks>
---
 .../broadcom/brcm80211/brcmfmac/commonring.c  |  14 ++
 .../broadcom/brcm80211/brcmfmac/commonring.h  |   5 +
 .../broadcom/brcm80211/brcmfmac/pcie.c        | 233 +++++++++++++++++-
 3 files changed, 249 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/commonring.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/commonring.c
index e44236cb210..881505b992c 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/commonring.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/commonring.c
@@ -28,6 +28,16 @@ void brcmf_commonring_register_cb(struct brcmf_commonring *commonring,
 }
 
 
+/* Both run outside the ring lock and may sleep */
+void brcmf_commonring_register_pm_cb(struct brcmf_commonring *commonring,
+				     void (*cr_wake)(void *ctx),
+				     void (*cr_idle)(void *ctx))
+{
+	commonring->cr_wake = cr_wake;
+	commonring->cr_idle = cr_idle;
+}
+
+
 void brcmf_commonring_config(struct brcmf_commonring *commonring, u16 depth,
 			     u16 item_len, void *buf_addr)
 {
@@ -53,6 +63,8 @@ void brcmf_commonring_lock(struct brcmf_commonring *commonring)
 {
 	unsigned long flags;
 
+	if (commonring->cr_wake)
+		commonring->cr_wake(commonring->cr_ctx);
 	spin_lock_irqsave(&commonring->lock, flags);
 	commonring->flags = flags;
 }
@@ -62,6 +74,8 @@ void brcmf_commonring_unlock(struct brcmf_commonring *commonring)
 		__releases(&commonring->lock)
 {
 	spin_unlock_irqrestore(&commonring->lock, commonring->flags);
+	if (commonring->cr_idle)
+		commonring->cr_idle(commonring->cr_ctx);
 }
 
 
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/commonring.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/commonring.h
index 7fb11f4823e..a27be6d7b17 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/commonring.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/commonring.h
@@ -20,6 +20,8 @@ struct brcmf_commonring {
 	int (*cr_update_wptr)(void *ctx);
 	int (*cr_write_rptr)(void *ctx);
 	int (*cr_write_wptr)(void *ctx);
+	void (*cr_wake)(void *ctx);
+	void (*cr_idle)(void *ctx);
 
 	void *cr_ctx;
 
@@ -38,6 +40,9 @@ void brcmf_commonring_register_cb(struct brcmf_commonring *commonring,
 				  int (*cr_update_wptr)(void *ctx),
 				  int (*cr_write_rptr)(void *ctx),
 				  int (*cr_write_wptr)(void *ctx), void *ctx);
+void brcmf_commonring_register_pm_cb(struct brcmf_commonring *commonring,
+				     void (*cr_wake)(void *ctx),
+				     void (*cr_idle)(void *ctx));
 void brcmf_commonring_config(struct brcmf_commonring *commonring, u16 depth,
 			     u16 item_len, void *buf_addr);
 void brcmf_commonring_lock(struct brcmf_commonring *commonring);
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
index faa1e16ed4f..f4a5ba9f9fe 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
@@ -222,10 +222,12 @@ static const struct brcmf_firmware_mapping brcmf_pcie_fwnames[] = {
 #define BRCMF_PCIE_SHARED_DMA_2B_IDX		0x100000
 #define BRCMF_PCIE_SHARED_USE_MAILBOX		0x2000000
 #define BRCMF_PCIE_SHARED_HOSTRDY_DB1		0x10000000
+#define BRCMF_PCIE_SHARED_INBAND_DS		0x40000000
 #define BRCMF_PCIE_SHARED_DAR			0x80000000
 
 #define BRCMF_HOSTCAP_H2D_ENABLE_HOSTRDY	0x400
 #define BRCMF_HOSTCAP_DS_NO_OOB_DW		0x1000
+#define BRCMF_HOSTCAP_DS_INBAND_DW		0x2000
 #define BRCMF_HOSTCAP_H2D_DAR			0x10000
 
 #define BRCMF_PCIE_FLAGS_HTOD_SPLIT		0x4000
@@ -274,6 +276,11 @@ static const struct brcmf_firmware_mapping brcmf_pcie_fwnames[] = {
 #define BRCMF_H2D_HOST_DS_ACK			0x00000002
 #define BRCMF_H2D_HOST_D0_INFORM_IN_USE		0x00000008
 #define BRCMF_H2D_HOST_D0_INFORM		0x00000010
+#define BRCMF_H2D_HOST_DW_DEASSERT		0x00000020
+#define BRCMF_H2D_HOST_DW_ASSERT		0x00000040
+
+#define BRCMF_PCIE_DS_IDLE_MS			200
+#define BRCMF_PCIE_DS_EXIT_TIMEOUT		msecs_to_jiffies(500)
 
 #define BRCMF_PCIE_MBDATA_TIMEOUT		msecs_to_jiffies(2000)
 
@@ -338,6 +345,15 @@ struct brcmf_otp_params {
 	bool valid;
 };
 
+enum brcmf_pcie_ds_state {
+	BRCMF_PCIE_DS_NONE,
+	BRCMF_PCIE_DS_ALLOWED,
+	BRCMF_PCIE_DS_SLEEP_PEND,
+	BRCMF_PCIE_DS_SLEEP,
+	BRCMF_PCIE_DS_EXIT_WAIT,
+	BRCMF_PCIE_DS_AWAKE,
+};
+
 struct brcmf_pciedev_info {
 	enum brcmf_pcie_state state;
 	bool in_irq;
@@ -371,6 +387,16 @@ struct brcmf_pciedev_info {
 	struct brcmf_mp_device *settings;
 	struct brcmf_otp_params otp;
 	bool fwseed;
+	/* protects ds_state, ds_active and ds_suspend */
+	spinlock_t ds_lock;
+	enum brcmf_pcie_ds_state ds_state;
+	int ds_active;
+	bool ds_suspend;
+	/* serializes the deep sleep mailbox messages */
+	struct mutex ds_mutex;
+	struct task_struct *ds_sender;
+	wait_queue_head_t ds_wait;
+	struct delayed_work ds_deassert_work;
 #ifdef DEBUG
 	u32 console_interval;
 	bool console_active;
@@ -892,17 +918,184 @@ brcmf_pcie_send_mb_data(struct brcmf_pciedev_info *devinfo, u32 htod_mb_data)
 }
 
 
+static void brcmf_pcie_ds_send(struct brcmf_pciedev_info *devinfo, u32 data)
+{
+	mutex_lock(&devinfo->ds_mutex);
+	WRITE_ONCE(devinfo->ds_sender, current);
+	brcmf_pcie_send_mb_data(devinfo, data);
+	WRITE_ONCE(devinfo->ds_sender, NULL);
+	mutex_unlock(&devinfo->ds_mutex);
+}
+
+/* The handshake messages themselves go through the hooked rings */
+static bool brcmf_pcie_ds_skip(struct brcmf_pciedev_info *devinfo)
+{
+	return READ_ONCE(devinfo->ds_state) == BRCMF_PCIE_DS_NONE ||
+	       READ_ONCE(devinfo->ds_sender) == current;
+}
+
+static bool brcmf_pcie_ds_idle_locked(struct brcmf_pciedev_info *devinfo)
+{
+	lockdep_assert_held(&devinfo->ds_lock);
+
+	if (devinfo->ds_active || devinfo->ds_suspend)
+		return false;
+
+	if (devinfo->ds_state == BRCMF_PCIE_DS_SLEEP_PEND) {
+		devinfo->ds_state = BRCMF_PCIE_DS_SLEEP;
+		return true;
+	}
+	if (devinfo->ds_state == BRCMF_PCIE_DS_AWAKE)
+		mod_delayed_work(system_dfl_wq, &devinfo->ds_deassert_work,
+				 msecs_to_jiffies(BRCMF_PCIE_DS_IDLE_MS));
+	return false;
+}
+
+static void brcmf_pcie_ds_wake(struct brcmf_pciedev_info *devinfo)
+{
+	bool assert = false, wait;
+
+	if (brcmf_pcie_ds_skip(devinfo))
+		return;
+
+	spin_lock(&devinfo->ds_lock);
+	devinfo->ds_active++;
+	if (devinfo->ds_state == BRCMF_PCIE_DS_SLEEP) {
+		devinfo->ds_state = BRCMF_PCIE_DS_EXIT_WAIT;
+		assert = true;
+	}
+	wait = devinfo->ds_state == BRCMF_PCIE_DS_EXIT_WAIT;
+	spin_unlock(&devinfo->ds_lock);
+
+	if (assert) {
+		brcmf_dbg(PCIE, "deep sleep: assert device wake\n");
+		brcmf_pcie_ds_send(devinfo, BRCMF_H2D_HOST_DW_ASSERT);
+	}
+	if (!wait)
+		return;
+
+	/* The exit note arrives through the interrupt thread itself */
+	if (devinfo->in_irq) {
+		usleep_range(1000, 1100);
+		return;
+	}
+	if (wait_event_timeout(devinfo->ds_wait,
+			       READ_ONCE(devinfo->ds_state) !=
+			       BRCMF_PCIE_DS_EXIT_WAIT,
+			       BRCMF_PCIE_DS_EXIT_TIMEOUT))
+		return;
+
+	brcmf_err(dev_get_drvdata(&devinfo->pdev->dev),
+		  "no deep sleep exit after device wake\n");
+	spin_lock(&devinfo->ds_lock);
+	if (devinfo->ds_state == BRCMF_PCIE_DS_EXIT_WAIT)
+		devinfo->ds_state = BRCMF_PCIE_DS_AWAKE;
+	spin_unlock(&devinfo->ds_lock);
+}
+
+static void brcmf_pcie_ds_idle(struct brcmf_pciedev_info *devinfo)
+{
+	bool ack;
+
+	if (brcmf_pcie_ds_skip(devinfo))
+		return;
+
+	spin_lock(&devinfo->ds_lock);
+	devinfo->ds_active--;
+	ack = brcmf_pcie_ds_idle_locked(devinfo);
+	spin_unlock(&devinfo->ds_lock);
+
+	if (ack) {
+		brcmf_dbg(PCIE, "deep sleep: ack pending request\n");
+		brcmf_pcie_ds_send(devinfo, BRCMF_H2D_HOST_DS_ACK);
+	}
+}
+
+static void brcmf_pcie_ds_deassert_worker(struct work_struct *work)
+{
+	struct brcmf_pciedev_info *devinfo =
+		container_of(work, struct brcmf_pciedev_info,
+			     ds_deassert_work.work);
+	bool deassert = false;
+
+	spin_lock(&devinfo->ds_lock);
+	if (devinfo->ds_state == BRCMF_PCIE_DS_AWAKE && !devinfo->ds_active &&
+	    !devinfo->ds_suspend) {
+		devinfo->ds_state = BRCMF_PCIE_DS_ALLOWED;
+		deassert = true;
+	}
+	spin_unlock(&devinfo->ds_lock);
+
+	if (deassert) {
+		brcmf_dbg(PCIE, "deep sleep: deassert device wake\n");
+		brcmf_pcie_ds_send(devinfo, BRCMF_H2D_HOST_DW_DEASSERT);
+	}
+}
+
+static void brcmf_pcie_ds_enter_req(struct brcmf_pciedev_info *devinfo)
+{
+	bool ack = false;
+
+	if (devinfo->ds_state == BRCMF_PCIE_DS_NONE) {
+		brcmf_pcie_send_mb_data(devinfo, BRCMF_H2D_HOST_DS_ACK);
+		return;
+	}
+
+	spin_lock(&devinfo->ds_lock);
+	if (devinfo->ds_state == BRCMF_PCIE_DS_ALLOWED) {
+		devinfo->ds_state = BRCMF_PCIE_DS_SLEEP_PEND;
+		ack = brcmf_pcie_ds_idle_locked(devinfo);
+	} else {
+		brcmf_dbg(PCIE, "deep sleep request in state %d\n",
+			  devinfo->ds_state);
+	}
+	spin_unlock(&devinfo->ds_lock);
+
+	if (ack)
+		brcmf_pcie_ds_send(devinfo, BRCMF_H2D_HOST_DS_ACK);
+}
+
+static void brcmf_pcie_ds_exit_note(struct brcmf_pciedev_info *devinfo)
+{
+	if (devinfo->ds_state == BRCMF_PCIE_DS_NONE)
+		return;
+
+	spin_lock(&devinfo->ds_lock);
+	if (devinfo->ds_state == BRCMF_PCIE_DS_EXIT_WAIT ||
+	    devinfo->ds_state == BRCMF_PCIE_DS_SLEEP) {
+		devinfo->ds_state = BRCMF_PCIE_DS_AWAKE;
+		brcmf_pcie_ds_idle_locked(devinfo);
+	}
+	spin_unlock(&devinfo->ds_lock);
+	wake_up(&devinfo->ds_wait);
+}
+
+static void brcmf_pcie_ring_ds_wake(void *ctx)
+{
+	struct brcmf_pcie_ringbuf *ring = ctx;
+
+	brcmf_pcie_ds_wake(ring->devinfo);
+}
+
+static void brcmf_pcie_ring_ds_idle(void *ctx)
+{
+	struct brcmf_pcie_ringbuf *ring = ctx;
+
+	brcmf_pcie_ds_idle(ring->devinfo);
+}
+
 static void brcmf_pcie_handle_mb_data(struct brcmf_pciedev_info *devinfo,
 				      u32 dtoh_mb_data)
 {
 	brcmf_dbg(PCIE, "D2H_MB_DATA: 0x%04x\n", dtoh_mb_data);
 	if (dtoh_mb_data & BRCMF_D2H_DEV_DS_ENTER_REQ)  {
 		brcmf_dbg(PCIE, "D2H_MB_DATA: DEEP SLEEP REQ\n");
-		brcmf_pcie_send_mb_data(devinfo, BRCMF_H2D_HOST_DS_ACK);
-		brcmf_dbg(PCIE, "D2H_MB_DATA: sent DEEP SLEEP ACK\n");
+		brcmf_pcie_ds_enter_req(devinfo);
 	}
-	if (dtoh_mb_data & BRCMF_D2H_DEV_DS_EXIT_NOTE)
+	if (dtoh_mb_data & BRCMF_D2H_DEV_DS_EXIT_NOTE) {
 		brcmf_dbg(PCIE, "D2H_MB_DATA: DEEP SLEEP EXIT\n");
+		brcmf_pcie_ds_exit_note(devinfo);
+	}
 	if (dtoh_mb_data & BRCMF_D2H_DEV_D3_ACK) {
 		brcmf_dbg(PCIE, "D2H_MB_DATA: D3 ACK\n");
 		devinfo->mbdata_completed = true;
@@ -1308,6 +1501,10 @@ brcmf_pcie_alloc_dma_and_ring(struct brcmf_pciedev_info *devinfo, u32 ring_id,
 				     brcmf_pcie_ring_mb_update_wptr,
 				     brcmf_pcie_ring_mb_write_rptr,
 				     brcmf_pcie_ring_mb_write_wptr, ring);
+	if (ring_id < BRCMF_NROF_H2D_COMMON_MSGRINGS)
+		brcmf_commonring_register_pm_cb(&ring->commonring,
+						brcmf_pcie_ring_ds_wake,
+						brcmf_pcie_ring_ds_idle);
 
 	return (ring);
 }
@@ -1501,6 +1698,9 @@ static int brcmf_pcie_init_ringbuffers(struct brcmf_pciedev_info *devinfo)
 					     brcmf_pcie_ring_mb_write_rptr,
 					     brcmf_pcie_ring_mb_write_wptr,
 					     ring);
+		brcmf_commonring_register_pm_cb(&ring->commonring,
+						brcmf_pcie_ring_ds_wake,
+						brcmf_pcie_ring_ds_idle);
 		ring->w_idx_addr = h2d_w_idx_ptr;
 		ring->r_idx_addr = h2d_r_idx_ptr;
 		h2d_w_idx_ptr += idx_offset;
@@ -1821,6 +2021,10 @@ brcmf_pcie_init_share_ram_info(struct brcmf_pciedev_info *devinfo,
 		if (shared->flags & BRCMF_PCIE_SHARED_DAR)
 			host_cap |= BRCMF_HOSTCAP_H2D_DAR;
 		host_cap |= BRCMF_HOSTCAP_DS_NO_OOB_DW;
+		if (shared->flags & BRCMF_PCIE_SHARED_INBAND_DS) {
+			host_cap |= BRCMF_HOSTCAP_DS_INBAND_DW;
+			devinfo->ds_state = BRCMF_PCIE_DS_ALLOWED;
+		}
 
 		brcmf_pcie_write_tcm32(devinfo, sharedram_addr +
 				       BRCMF_SHARED_HOST_CAP_OFFSET,
@@ -2630,6 +2834,11 @@ brcmf_pcie_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		return ret;
 
 	devinfo->pdev = pdev;
+	spin_lock_init(&devinfo->ds_lock);
+	mutex_init(&devinfo->ds_mutex);
+	init_waitqueue_head(&devinfo->ds_wait);
+	INIT_DELAYED_WORK(&devinfo->ds_deassert_work,
+			  brcmf_pcie_ds_deassert_worker);
 	pcie_bus_dev = NULL;
 	devinfo->ci = brcmf_chip_attach(devinfo, pdev->device,
 					&brcmf_pcie_buscore_ops);
@@ -2757,6 +2966,8 @@ brcmf_pcie_remove(struct pci_dev *pdev)
 		return;
 
 	devinfo = bus->bus_priv.pcie->devinfo;
+	WRITE_ONCE(devinfo->ds_state, BRCMF_PCIE_DS_NONE);
+	cancel_delayed_work_sync(&devinfo->ds_deassert_work);
 	brcmf_pcie_bus_console_read(devinfo, false);
 	brcmf_pcie_fwcon_timer(devinfo, false);
 
@@ -2811,6 +3022,15 @@ static int brcmf_pcie_pm_enter_D3(struct device *dev)
 	brcmf_pcie_fwcon_timer(devinfo, false);
 	brcmf_bus_change_state(bus, BRCMF_BUS_DOWN);
 
+	if (devinfo->ds_state != BRCMF_PCIE_DS_NONE) {
+		spin_lock(&devinfo->ds_lock);
+		devinfo->ds_suspend = true;
+		spin_unlock(&devinfo->ds_lock);
+		cancel_delayed_work_sync(&devinfo->ds_deassert_work);
+		brcmf_pcie_ds_wake(devinfo);
+		brcmf_pcie_ds_idle(devinfo);
+	}
+
 	devinfo->mbdata_completed = false;
 	brcmf_pcie_send_mb_data(devinfo, BRCMF_H2D_HOST_D3_INFORM);
 
@@ -2861,6 +3081,13 @@ static int brcmf_pcie_pm_leave_D3(struct device *dev)
 		if (brcmf_pcie_send_mb_data(devinfo, BRCMF_H2D_HOST_D0_INFORM))
 			goto cleanup;
 		brcmf_dbg(PCIE, "Hot resume, continue....\n");
+		if (devinfo->ds_state != BRCMF_PCIE_DS_NONE) {
+			spin_lock(&devinfo->ds_lock);
+			devinfo->ds_suspend = false;
+			devinfo->ds_state = BRCMF_PCIE_DS_AWAKE;
+			brcmf_pcie_ds_idle_locked(devinfo);
+			spin_unlock(&devinfo->ds_lock);
+		}
 		brcmf_pcie_select_core(devinfo, BCMA_CORE_PCIE2);
 		brcmf_bus_change_state(bus, BRCMF_BUS_UP);
 		brcmf_pcie_intr_enable(devinfo);