[PATCH v5 0/3] Serialize execution environment changes for MHI

[PATCH v5 0/3] Serialize execution environment changes for MHI

[Bhaumik Bhatt]

v5:
-Update commit text for "clear devices when moving execution environments" patch
-Added test platform details that were missed out in the cover letter
-Merged two if checks in to a single one for EE serialization patch

v4:
-Addressed review comments for additional info logging for EE movements
-Updated switch case for EE handling in mhi_intvec_threaded_handler()

v3:
-Update commit text to accurately reflect changes and reasoning based on reviews

v2:
-Add patch to clear devices when moving execution environments

During full boot chain firmware download, the PM state worker downloads the AMSS
image after waiting for the SBL execution environment change in PBL mode itself.
Since getting rid of the firmware load worker thread, this design needs to
change and MHI host must download the AMSS image from the SBL mode of PM state
worker thread instead of blocking waits for SBL EE in PBL transition processing.

Ensure that EE changes are handled only from appropriate places and occur
one after another and handle only PBL or RDDM EE changes as critical events
directly from the interrupt handler and the status callback is given to the
controller drivers promptly.

When moving from SBL to AMSS EE, clear SBL specific client devices by calling
remove callbacks for them so they are not left opened in a different execution
environment.

This patchset was tested on ARM64.

Bhaumik Bhatt (3):
  bus: mhi: core: Clear devices when moving execution environments
  bus: mhi: core: Download AMSS image from appropriate function
  bus: mhi: core: Process execution environment changes serially

 drivers/bus/mhi/core/boot.c     | 48 +++++++++++++++---------------
 drivers/bus/mhi/core/internal.h |  1 +
 drivers/bus/mhi/core/main.c     | 65 ++++++++++++++++++++++++++---------------
 drivers/bus/mhi/core/pm.c       | 10 +++++--
 4 files changed, 75 insertions(+), 49 deletions(-)

-- 
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project

[PATCH v5 1/3] bus: mhi: core: Clear devices when moving execution environments

[Bhaumik Bhatt]

Currently, client driver devices are being created in SBL or AMSS
(mission mode) and only destroyed after power down or SYS_ERROR
occurs. When moving between certain execution environments, there
is no power down or SYS_ERROR processing required. This presents
an issue when moving from SBL to mission mode, for example, where
there is also no remove notification to client drivers operating
in SBL mode. Thus, SBL-specific channels are left open and client
drivers are unaware of the new execution environment where they
cannot operate. Fix this by expanding mhi_destroy_device() to do
an execution environment specific clean up if one is requested.
Close this gap to issue remove callbacks in such scenarios that
allow SBL-specific client drivers to clean-up once device enters
mission mode.

Signed-off-by: Bhaumik Bhatt <bbhatt@codeaurora.org>
---
 drivers/bus/mhi/core/main.c | 27 +++++++++++++++++++++++----
 drivers/bus/mhi/core/pm.c   |  3 +++
 2 files changed, 26 insertions(+), 4 deletions(-)

diff --git a/drivers/bus/mhi/core/main.c b/drivers/bus/mhi/core/main.c
index 4e0131b..58f1425 100644
--- a/drivers/bus/mhi/core/main.c
+++ b/drivers/bus/mhi/core/main.c
@@ -244,8 +244,10 @@ static void mhi_del_ring_element(struct mhi_controller *mhi_cntrl,
 
 int mhi_destroy_device(struct device *dev, void *data)
 {
+	struct mhi_chan *ul_chan, *dl_chan;
 	struct mhi_device *mhi_dev;
 	struct mhi_controller *mhi_cntrl;
+	enum mhi_ee_type ee = MHI_EE_MAX;
 
 	if (dev->bus != &mhi_bus_type)
 		return 0;
@@ -257,6 +259,17 @@ int mhi_destroy_device(struct device *dev, void *data)
 	if (mhi_dev->dev_type == MHI_DEVICE_CONTROLLER)
 		return 0;
 
+	ul_chan = mhi_dev->ul_chan;
+	dl_chan = mhi_dev->dl_chan;
+
+	/*
+	 * If execution environment is specified, remove only those devices that
+	 * started in them based on ee_mask for the channels as we move on to a
+	 * different execution environment
+	 */
+	if (data)
+		ee = *(enum mhi_ee_type *)data;
+
 	/*
 	 * For the suspend and resume case, this function will get called
 	 * without mhi_unregister_controller(). Hence, we need to drop the
@@ -264,11 +277,17 @@ int mhi_destroy_device(struct device *dev, void *data)
 	 * be sure that there will be no instances of mhi_dev left after
 	 * this.
 	 */
-	if (mhi_dev->ul_chan)
-		put_device(&mhi_dev->ul_chan->mhi_dev->dev);
+	if (ul_chan) {
+		if (ee != MHI_EE_MAX && !(ul_chan->ee_mask & BIT(ee)))
+			return 0;
+		put_device(&ul_chan->mhi_dev->dev);
+	}
 
-	if (mhi_dev->dl_chan)
-		put_device(&mhi_dev->dl_chan->mhi_dev->dev);
+	if (dl_chan) {
+		if (ee != MHI_EE_MAX && !(dl_chan->ee_mask & BIT(ee)))
+			return 0;
+		put_device(&dl_chan->mhi_dev->dev);
+	}
 
 	dev_dbg(&mhi_cntrl->mhi_dev->dev, "destroy device for chan:%s\n",
 		 mhi_dev->name);
diff --git a/drivers/bus/mhi/core/pm.c b/drivers/bus/mhi/core/pm.c
index 681960c..8da8806 100644
--- a/drivers/bus/mhi/core/pm.c
+++ b/drivers/bus/mhi/core/pm.c
@@ -377,6 +377,7 @@ static int mhi_pm_mission_mode_transition(struct mhi_controller *mhi_cntrl)
 {
 	struct mhi_event *mhi_event;
 	struct device *dev = &mhi_cntrl->mhi_dev->dev;
+	enum mhi_ee_type ee = MHI_EE_MAX, current_ee = mhi_cntrl->ee;
 	int i, ret;
 
 	dev_dbg(dev, "Processing Mission Mode transition\n");
@@ -395,6 +396,8 @@ static int mhi_pm_mission_mode_transition(struct mhi_controller *mhi_cntrl)
 
 	wake_up_all(&mhi_cntrl->state_event);
 
+	device_for_each_child(&mhi_cntrl->mhi_dev->dev, &current_ee,
+			      mhi_destroy_device);
 	mhi_cntrl->status_cb(mhi_cntrl, MHI_CB_EE_MISSION_MODE);
 
 	/* Force MHI to be in M0 state before continuing */
-- 
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project

[PATCH v5 2/3] bus: mhi: core: Download AMSS image from appropriate function

[Bhaumik Bhatt]

During full boot chain firmware download, the PM state worker
downloads the AMSS image after a blocking wait for the SBL
execution environment change when running in PBL transition
itself. Improve this design by having the host download the AMSS
image from the SBL transition of PM state worker thread when a
DEV_ST_TRANSITION_SBL is queued instead of the blocking wait.

Signed-off-by: Bhaumik Bhatt <bbhatt@codeaurora.org>
---
 drivers/bus/mhi/core/boot.c     | 48 ++++++++++++++++++++---------------------
 drivers/bus/mhi/core/internal.h |  1 +
 drivers/bus/mhi/core/pm.c       |  2 ++
 3 files changed, 27 insertions(+), 24 deletions(-)

diff --git a/drivers/bus/mhi/core/boot.c b/drivers/bus/mhi/core/boot.c
index c2546bf..983e6b5 100644
--- a/drivers/bus/mhi/core/boot.c
+++ b/drivers/bus/mhi/core/boot.c
@@ -389,7 +389,6 @@ static void mhi_firmware_copy(struct mhi_controller *mhi_cntrl,
 void mhi_fw_load_handler(struct mhi_controller *mhi_cntrl)
 {
 	const struct firmware *firmware = NULL;
-	struct image_info *image_info;
 	struct device *dev = &mhi_cntrl->mhi_dev->dev;
 	const char *fw_name;
 	void *buf;
@@ -493,35 +492,15 @@ void mhi_fw_load_handler(struct mhi_controller *mhi_cntrl)
 	ret = mhi_ready_state_transition(mhi_cntrl);
 
 	if (!mhi_cntrl->fbc_download)
-		return;
+		goto exit_fw_load;
 
 	if (ret) {
 		dev_err(dev, "MHI did not enter READY state\n");
 		goto error_ready_state;
 	}
 
-	/* Wait for the SBL event */
-	ret = wait_event_timeout(mhi_cntrl->state_event,
-				 mhi_cntrl->ee == MHI_EE_SBL ||
-				 MHI_PM_IN_ERROR_STATE(mhi_cntrl->pm_state),
-				 msecs_to_jiffies(mhi_cntrl->timeout_ms));
-
-	if (!ret || MHI_PM_IN_ERROR_STATE(mhi_cntrl->pm_state)) {
-		dev_err(dev, "MHI did not enter SBL\n");
-		goto error_ready_state;
-	}
-
-	/* Start full firmware image download */
-	image_info = mhi_cntrl->fbc_image;
-	ret = mhi_fw_load_bhie(mhi_cntrl,
-			       /* Vector table is the last entry */
-			       &image_info->mhi_buf[image_info->entries - 1]);
-	if (ret) {
-		dev_err(dev, "MHI did not load image over BHIe, ret: %d\n",
-			ret);
-		goto error_fw_load;
-	}
-
+exit_fw_load:
+	dev_info(dev, "Wait for device to enter SBL or Mission mode\n");
 	return;
 
 error_ready_state:
@@ -532,3 +511,24 @@ void mhi_fw_load_handler(struct mhi_controller *mhi_cntrl)
 	mhi_cntrl->pm_state = MHI_PM_FW_DL_ERR;
 	wake_up_all(&mhi_cntrl->state_event);
 }
+
+int mhi_download_amss_image(struct mhi_controller *mhi_cntrl)
+{
+	struct image_info *image_info = mhi_cntrl->fbc_image;
+	struct device *dev = &mhi_cntrl->mhi_dev->dev;
+	int ret;
+
+	if (!image_info)
+		return -EIO;
+
+	ret = mhi_fw_load_bhie(mhi_cntrl,
+			       /* Vector table is the last entry */
+			       &image_info->mhi_buf[image_info->entries - 1]);
+	if (ret) {
+		dev_err(dev, "MHI did not load AMSS, ret:%d\n", ret);
+		mhi_cntrl->pm_state = MHI_PM_FW_DL_ERR;
+		wake_up_all(&mhi_cntrl->state_event);
+	}
+
+	return ret;
+}
diff --git a/drivers/bus/mhi/core/internal.h b/drivers/bus/mhi/core/internal.h
index 6f80ec3..6f37439 100644
--- a/drivers/bus/mhi/core/internal.h
+++ b/drivers/bus/mhi/core/internal.h
@@ -619,6 +619,7 @@ int mhi_pm_m3_transition(struct mhi_controller *mhi_cntrl);
 int __mhi_device_get_sync(struct mhi_controller *mhi_cntrl);
 int mhi_send_cmd(struct mhi_controller *mhi_cntrl, struct mhi_chan *mhi_chan,
 		 enum mhi_cmd_type cmd);
+int mhi_download_amss_image(struct mhi_controller *mhi_cntrl);
 static inline bool mhi_is_active(struct mhi_controller *mhi_cntrl)
 {
 	return (mhi_cntrl->dev_state >= MHI_STATE_M0 &&
diff --git a/drivers/bus/mhi/core/pm.c b/drivers/bus/mhi/core/pm.c
index 8da8806..44aa7eb 100644
--- a/drivers/bus/mhi/core/pm.c
+++ b/drivers/bus/mhi/core/pm.c
@@ -758,6 +758,8 @@ void mhi_pm_st_worker(struct work_struct *work)
 			 * either SBL or AMSS states
 			 */
 			mhi_create_devices(mhi_cntrl);
+			if (mhi_cntrl->fbc_download)
+				mhi_download_amss_image(mhi_cntrl);
 			break;
 		case DEV_ST_TRANSITION_MISSION_MODE:
 			mhi_pm_mission_mode_transition(mhi_cntrl);
-- 
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project

[PATCH v5 3/3] bus: mhi: core: Process execution environment changes serially

[Bhaumik Bhatt]

In current design, whenever the BHI interrupt is fired, the
execution environment is updated. This can cause race conditions
and impede ongoing power up/down processing. For example, if a
power down is in progress, MHI host updates to a local "disabled"
execution environment. If a BHI interrupt fires later, that value
gets replaced with one from the BHI EE register. This impacts the
controller as it does not expect multiple RDDM execution
environment change status callbacks as an example. Another issue
would be that the device can enter mission mode and the execution
environment is updated, while device creation for SBL channels is
still going on due to slower PM state worker thread run, leading
to multiple attempts at opening the same channel.

We must handle and wait for SYS_ERROR in any case to facilitate
clean-up for the controller and handle RDDM. Ensure that EE
changes are handled only from appropriate places and occur one
after another and handle only PBL modes or RDDM EE changes as
critical events directly from the interrupt handler. This also
makes sure that we use the correct execution environment to notify
the controller driver when the device resets to one of the PBL
execution environments.

Signed-off-by: Bhaumik Bhatt <bbhatt@codeaurora.org>
---
 drivers/bus/mhi/core/main.c | 38 +++++++++++++++++++-------------------
 drivers/bus/mhi/core/pm.c   |  5 +++--
 2 files changed, 22 insertions(+), 21 deletions(-)

diff --git a/drivers/bus/mhi/core/main.c b/drivers/bus/mhi/core/main.c
index 58f1425..c55d6ec 100644
--- a/drivers/bus/mhi/core/main.c
+++ b/drivers/bus/mhi/core/main.c
@@ -428,7 +428,7 @@ irqreturn_t mhi_intvec_threaded_handler(int irq_number, void *priv)
 	struct device *dev = &mhi_cntrl->mhi_dev->dev;
 	enum mhi_state state = MHI_STATE_MAX;
 	enum mhi_pm_state pm_state = 0;
-	enum mhi_ee_type ee = 0;
+	enum mhi_ee_type ee = MHI_EE_MAX;
 
 	write_lock_irq(&mhi_cntrl->pm_lock);
 	if (!MHI_REG_ACCESS_VALID(mhi_cntrl->pm_state)) {
@@ -437,8 +437,7 @@ irqreturn_t mhi_intvec_threaded_handler(int irq_number, void *priv)
 	}
 
 	state = mhi_get_mhi_state(mhi_cntrl);
-	ee = mhi_cntrl->ee;
-	mhi_cntrl->ee = mhi_get_exec_env(mhi_cntrl);
+	ee = mhi_get_exec_env(mhi_cntrl);
 	dev_dbg(dev, "local ee:%s device ee:%s dev_state:%s\n",
 		TO_MHI_EXEC_STR(mhi_cntrl->ee), TO_MHI_EXEC_STR(ee),
 		TO_MHI_STATE_STR(state));
@@ -450,27 +449,28 @@ irqreturn_t mhi_intvec_threaded_handler(int irq_number, void *priv)
 	}
 	write_unlock_irq(&mhi_cntrl->pm_lock);
 
-	 /* If device supports RDDM don't bother processing SYS error */
-	if (mhi_cntrl->rddm_image) {
-		/* host may be performing a device power down already */
-		if (!mhi_is_active(mhi_cntrl))
-			goto exit_intvec;
+	if (pm_state != MHI_PM_SYS_ERR_DETECT || ee == mhi_cntrl->ee)
+		goto exit_intvec;
 
-		if (mhi_cntrl->ee == MHI_EE_RDDM && mhi_cntrl->ee != ee) {
+	switch (ee) {
+	case MHI_EE_RDDM:
+		/* proceed if power down is not already in progress */
+		if (mhi_cntrl->rddm_image && mhi_is_active(mhi_cntrl)) {
 			mhi_cntrl->status_cb(mhi_cntrl, MHI_CB_EE_RDDM);
+			mhi_cntrl->ee = ee;
 			wake_up_all(&mhi_cntrl->state_event);
 		}
-		goto exit_intvec;
-	}
-
-	if (pm_state == MHI_PM_SYS_ERR_DETECT) {
+		break;
+	case MHI_EE_PBL:
+	case MHI_EE_EDL:
+	case MHI_EE_PTHRU:
+		mhi_cntrl->status_cb(mhi_cntrl, MHI_CB_FATAL_ERROR);
+		mhi_cntrl->ee = ee;
+	/* continue */
+	default:
+		mhi_pm_sys_err_handler(mhi_cntrl);
 		wake_up_all(&mhi_cntrl->state_event);
-
-		/* For fatal errors, we let controller decide next step */
-		if (MHI_IN_PBL(ee))
-			mhi_cntrl->status_cb(mhi_cntrl, MHI_CB_FATAL_ERROR);
-		else
-			mhi_pm_sys_err_handler(mhi_cntrl);
+		break;
 	}
 
 exit_intvec:
diff --git a/drivers/bus/mhi/core/pm.c b/drivers/bus/mhi/core/pm.c
index 44aa7eb..c870fa8 100644
--- a/drivers/bus/mhi/core/pm.c
+++ b/drivers/bus/mhi/core/pm.c
@@ -384,14 +384,15 @@ static int mhi_pm_mission_mode_transition(struct mhi_controller *mhi_cntrl)
 
 	write_lock_irq(&mhi_cntrl->pm_lock);
 	if (MHI_REG_ACCESS_VALID(mhi_cntrl->pm_state))
-		mhi_cntrl->ee = mhi_get_exec_env(mhi_cntrl);
+		ee = mhi_get_exec_env(mhi_cntrl);
 
-	if (!MHI_IN_MISSION_MODE(mhi_cntrl->ee)) {
+	if (!MHI_IN_MISSION_MODE(ee)) {
 		mhi_cntrl->pm_state = MHI_PM_LD_ERR_FATAL_DETECT;
 		write_unlock_irq(&mhi_cntrl->pm_lock);
 		wake_up_all(&mhi_cntrl->state_event);
 		return -EIO;
 	}
+	mhi_cntrl->ee = ee;
 	write_unlock_irq(&mhi_cntrl->pm_lock);
 
 	wake_up_all(&mhi_cntrl->state_event);
-- 
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project

Re: [PATCH v5 3/3] bus: mhi: core: Process execution environment changes serially

[kernel test robot]

[-- Attachment #1: Type: text/plain, Size: 3872 bytes --]

Hi Bhaumik,

Thank you for the patch! Perhaps something to improve:

[auto build test WARNING on linus/master]
[also build test WARNING on v5.11 next-20210219]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]

url:    https://github.com/0day-ci/linux/commits/Bhaumik-Bhatt/Serialize-execution-environment-changes-for-MHI/20210220-071426
base:   https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git f40ddce88593482919761f74910f42f4b84c004b
config: mips-randconfig-r033-20210219 (attached as .config)
compiler: mipsel-linux-gcc (GCC) 9.3.0
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/e38872b38ede9c5c1706cd11bf5792f8dc436fcf
        git remote add linux-review https://github.com/0day-ci/linux
        git fetch --no-tags linux-review Bhaumik-Bhatt/Serialize-execution-environment-changes-for-MHI/20210220-071426
        git checkout e38872b38ede9c5c1706cd11bf5792f8dc436fcf
        # save the attached .config to linux build tree
        COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-9.3.0 make.cross ARCH=mips 

If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>

All warnings (new ones prefixed by >>):

   drivers/bus/mhi/core/main.c: In function 'mhi_intvec_threaded_handler':
>> drivers/bus/mhi/core/main.c:436:17: warning: this statement may fall through [-Wimplicit-fallthrough=]
     436 |   mhi_cntrl->ee = ee;
         |   ~~~~~~~~~~~~~~^~~~
   drivers/bus/mhi/core/main.c:438:2: note: here
     438 |  default:
         |  ^~~~~~~


vim +436 drivers/bus/mhi/core/main.c

   392	
   393	irqreturn_t mhi_intvec_threaded_handler(int irq_number, void *priv)
   394	{
   395		struct mhi_controller *mhi_cntrl = priv;
   396		struct device *dev = &mhi_cntrl->mhi_dev->dev;
   397		enum mhi_state state = MHI_STATE_MAX;
   398		enum mhi_pm_state pm_state = 0;
   399		enum mhi_ee_type ee = MHI_EE_MAX;
   400	
   401		write_lock_irq(&mhi_cntrl->pm_lock);
   402		if (!MHI_REG_ACCESS_VALID(mhi_cntrl->pm_state)) {
   403			write_unlock_irq(&mhi_cntrl->pm_lock);
   404			goto exit_intvec;
   405		}
   406	
   407		state = mhi_get_mhi_state(mhi_cntrl);
   408		ee = mhi_get_exec_env(mhi_cntrl);
   409		dev_dbg(dev, "local ee:%s device ee:%s dev_state:%s\n",
   410			TO_MHI_EXEC_STR(mhi_cntrl->ee), TO_MHI_EXEC_STR(ee),
   411			TO_MHI_STATE_STR(state));
   412	
   413		if (state == MHI_STATE_SYS_ERR) {
   414			dev_dbg(dev, "System error detected\n");
   415			pm_state = mhi_tryset_pm_state(mhi_cntrl,
   416						       MHI_PM_SYS_ERR_DETECT);
   417		}
   418		write_unlock_irq(&mhi_cntrl->pm_lock);
   419	
   420		if (pm_state != MHI_PM_SYS_ERR_DETECT || ee == mhi_cntrl->ee)
   421			goto exit_intvec;
   422	
   423		switch (ee) {
   424		case MHI_EE_RDDM:
   425			/* proceed if power down is not already in progress */
   426			if (mhi_cntrl->rddm_image && mhi_is_active(mhi_cntrl)) {
   427				mhi_cntrl->status_cb(mhi_cntrl, MHI_CB_EE_RDDM);
   428				mhi_cntrl->ee = ee;
   429				wake_up_all(&mhi_cntrl->state_event);
   430			}
   431			break;
   432		case MHI_EE_PBL:
   433		case MHI_EE_EDL:
   434		case MHI_EE_PTHRU:
   435			mhi_cntrl->status_cb(mhi_cntrl, MHI_CB_FATAL_ERROR);
 > 436			mhi_cntrl->ee = ee;
   437		/* continue */
   438		default:
   439			mhi_pm_sys_err_handler(mhi_cntrl);
   440			wake_up_all(&mhi_cntrl->state_event);
   441			break;
   442		}
   443	
   444	exit_intvec:
   445	
   446		return IRQ_HANDLED;
   447	}
   448	

---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org

[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 37426 bytes --]