From bb8e97e26ce6437d2f57f37e8ba767a2b9cf0d65 Mon Sep 17 00:00:00 2001
From: Carl Vanderlip <quic_carlv@quicinc.com>
Date: Mon, 16 Oct 2023 11:00:36 -0600
Subject: accel/qaic: Enable 1 MSI fallback mode

Several virtualization use-cases either don't support 32 MultiMSIs
(Xen/VMware) or have significant drawbacks to their use (KVM's vIOMMU,
which is required to support 32 MSI, needs to allocate an alternate
system memory space for each device using vIOMMU (e.g. 8GB VM mem and
2 cards => 8 + 2 * 8 = 24GB host memory required)). Support these
cases by enabling a 1 MSI fallback mode.

Whenever all 32 MSIs requested are not available, a second request for
a single MSI is made. Its success is the initiator of single MSI mode.
This mode causes all interrupts generated by the device to be directed
to the 0th MSI (firmware >=v1.10 will do this as a response to the PCIe
MSI capability configuration). Likewise, all interrupt handlers for the
device are registered to the 0th MSI.

Since the DBC interrupt handler checks if the DBC is in use or if
there is any pending changes, the 'spurious' interrupts are
disregarded. If there is work to be done, the standard threaded IRQ
handler is dispatched.

On every interrupt, the MHI handler wakes up its threaded interrupt
handler, and attempts to wake any waiters for MHI state events.

Performance is within +-0.6% for test cases that typify real world
use. Larger differences ([-4,+132]%, avg +47%) exist for very simple
tasks (e.g. addition) compiled for single NSPs. It is assumed that the
small work and many interrupts typically cause contention (e.g. 16 NSPs
vs 4 CPUs), as evidenced by the standard deviation between runs also
decreasing (r=-0.48 between delta(Performace_test) and
delta(StdDev_test/Avg_test))

Signed-off-by: Carl Vanderlip <quic_carlv@quicinc.com>
Reviewed-by: Pranjal Ramajor Asha Kanojiya <quic_pkanojiy@quicinc.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231016170036.5409-1-quic_jhugo@quicinc.com
---
 drivers/accel/qaic/mhi_controller.c |  6 +++++-
 drivers/accel/qaic/mhi_controller.h |  2 +-
 drivers/accel/qaic/qaic.h           |  2 ++
 drivers/accel/qaic/qaic_data.c      | 25 ++++++++++++++++++-------
 drivers/accel/qaic/qaic_drv.c       | 35 ++++++++++++++++++++++++-----------
 5 files changed, 50 insertions(+), 20 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/qaic/mhi_controller.c b/drivers/accel/qaic/mhi_controller.c
index 5036e58e7235..41be3626587d 100644
--- a/drivers/accel/qaic/mhi_controller.c
+++ b/drivers/accel/qaic/mhi_controller.c
@@ -468,7 +468,7 @@ static int mhi_reset_and_async_power_up(struct mhi_controller *mhi_cntrl)
 }
 
 struct mhi_controller *qaic_mhi_register_controller(struct pci_dev *pci_dev, void __iomem *mhi_bar,
-						    int mhi_irq)
+						    int mhi_irq, bool shared_msi)
 {
 	struct mhi_controller *mhi_cntrl;
 	int ret;
@@ -500,6 +500,10 @@ struct mhi_controller *qaic_mhi_register_controller(struct pci_dev *pci_dev, voi
 		return ERR_PTR(-ENOMEM);
 
 	mhi_cntrl->irq[0] = mhi_irq;
+
+	if (shared_msi) /* MSI shared with data path, no IRQF_NO_SUSPEND */
+		mhi_cntrl->irq_flags = IRQF_SHARED;
+
 	mhi_cntrl->fw_image = "qcom/aic100/sbl.bin";
 
 	/* use latest configured timeout */
diff --git a/drivers/accel/qaic/mhi_controller.h b/drivers/accel/qaic/mhi_controller.h
index 2ae45d768e24..500e7f4af2af 100644
--- a/drivers/accel/qaic/mhi_controller.h
+++ b/drivers/accel/qaic/mhi_controller.h
@@ -8,7 +8,7 @@
 #define MHICONTROLLERQAIC_H_
 
 struct mhi_controller *qaic_mhi_register_controller(struct pci_dev *pci_dev, void __iomem *mhi_bar,
-						    int mhi_irq);
+						    int mhi_irq, bool shared_msi);
 void qaic_mhi_free_controller(struct mhi_controller *mhi_cntrl, bool link_up);
 void qaic_mhi_start_reset(struct mhi_controller *mhi_cntrl);
 void qaic_mhi_reset_done(struct mhi_controller *mhi_cntrl);
diff --git a/drivers/accel/qaic/qaic.h b/drivers/accel/qaic/qaic.h
index e3f4c30f3ffd..01e9dda0cc37 100644
--- a/drivers/accel/qaic/qaic.h
+++ b/drivers/accel/qaic/qaic.h
@@ -123,6 +123,8 @@ struct qaic_device {
 	struct srcu_struct	dev_lock;
 	/* true: Device under reset; false: Device not under reset */
 	bool			in_reset;
+	/* true: single MSI is used to operate device */
+	bool			single_msi;
 	/*
 	 * true: A tx MHI transaction has failed and a rx buffer is still queued
 	 * in control device. Such a buffer is considered lost rx buffer
diff --git a/drivers/accel/qaic/qaic_data.c b/drivers/accel/qaic/qaic_data.c
index 4a8e43a7a6a4..ebc3cca1b094 100644
--- a/drivers/accel/qaic/qaic_data.c
+++ b/drivers/accel/qaic/qaic_data.c
@@ -1466,6 +1466,16 @@ irqreturn_t dbc_irq_handler(int irq, void *data)
 
 	rcu_id = srcu_read_lock(&dbc->ch_lock);
 
+	if (datapath_polling) {
+		srcu_read_unlock(&dbc->ch_lock, rcu_id);
+		/*
+		 * Normally datapath_polling will not have irqs enabled, but
+		 * when running with only one MSI the interrupt is shared with
+		 * MHI so it cannot be disabled. Return ASAP instead.
+		 */
+		return IRQ_HANDLED;
+	}
+
 	if (!dbc->usr) {
 		srcu_read_unlock(&dbc->ch_lock, rcu_id);
 		return IRQ_HANDLED;
@@ -1488,7 +1498,8 @@ irqreturn_t dbc_irq_handler(int irq, void *data)
 		return IRQ_NONE;
 	}
 
-	disable_irq_nosync(irq);
+	if (!dbc->qdev->single_msi)
+		disable_irq_nosync(irq);
 	srcu_read_unlock(&dbc->ch_lock, rcu_id);
 	return IRQ_WAKE_THREAD;
 }
@@ -1559,12 +1570,12 @@ irqreturn_t dbc_irq_threaded_fn(int irq, void *data)
 	u32 tail;
 
 	rcu_id = srcu_read_lock(&dbc->ch_lock);
+	qdev = dbc->qdev;
 
 	head = readl(dbc->dbc_base + RSPHP_OFF);
 	if (head == U32_MAX) /* PCI link error */
 		goto error_out;
 
-	qdev = dbc->qdev;
 read_fifo:
 
 	if (!event_count) {
@@ -1645,14 +1656,14 @@ read_fifo:
 	goto read_fifo;
 
 normal_out:
-	if (likely(!datapath_polling))
+	if (!qdev->single_msi && likely(!datapath_polling))
 		enable_irq(irq);
-	else
+	else if (unlikely(datapath_polling))
 		schedule_work(&dbc->poll_work);
 	/* checking the fifo and enabling irqs is a race, missed event check */
 	tail = readl(dbc->dbc_base + RSPTP_OFF);
 	if (tail != U32_MAX && head != tail) {
-		if (likely(!datapath_polling))
+		if (!qdev->single_msi && likely(!datapath_polling))
 			disable_irq_nosync(irq);
 		goto read_fifo;
 	}
@@ -1661,9 +1672,9 @@ normal_out:
 
 error_out:
 	srcu_read_unlock(&dbc->ch_lock, rcu_id);
-	if (likely(!datapath_polling))
+	if (!qdev->single_msi && likely(!datapath_polling))
 		enable_irq(irq);
-	else
+	else if (unlikely(datapath_polling))
 		schedule_work(&dbc->poll_work);
 
 	return IRQ_HANDLED;
diff --git a/drivers/accel/qaic/qaic_drv.c b/drivers/accel/qaic/qaic_drv.c
index 6f58095767df..5eba5f03d3bf 100644
--- a/drivers/accel/qaic/qaic_drv.c
+++ b/drivers/accel/qaic/qaic_drv.c
@@ -424,14 +424,24 @@ static int init_msi(struct qaic_device *qdev, struct pci_dev *pdev)
 	int i;
 
 	/* Managed release since we use pcim_enable_device */
-	ret = pci_alloc_irq_vectors(pdev, 1, 32, PCI_IRQ_MSI);
-	if (ret < 0)
-		return ret;
+	ret = pci_alloc_irq_vectors(pdev, 32, 32, PCI_IRQ_MSI);
+	if (ret == -ENOSPC) {
+		ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI);
+		if (ret < 0)
+			return ret;
 
-	if (ret < 32) {
-		pci_err(pdev, "%s: Requested 32 MSIs. Obtained %d MSIs which is less than the 32 required.\n",
-			__func__, ret);
-		return -ENODEV;
+		/*
+		 * Operate in one MSI mode. All interrupts will be directed to
+		 * MSI0; every interrupt will wake up all the interrupt handlers
+		 * (MHI and DBC[0-15]). Since the interrupt is now shared, it is
+		 * not disabled during DBC threaded handler, but only one thread
+		 * will be allowed to run per DBC, so while it can be
+		 * interrupted, it shouldn't race with itself.
+		 */
+		qdev->single_msi = true;
+		pci_info(pdev, "Allocating 32 MSIs failed, operating in 1 MSI mode. Performance may be impacted.\n");
+	} else if (ret < 0) {
+		return ret;
 	}
 
 	mhi_irq = pci_irq_vector(pdev, 0);
@@ -439,15 +449,17 @@ static int init_msi(struct qaic_device *qdev, struct pci_dev *pdev)
 		return mhi_irq;
 
 	for (i = 0; i < qdev->num_dbc; ++i) {
-		ret = devm_request_threaded_irq(&pdev->dev, pci_irq_vector(pdev, i + 1),
+		ret = devm_request_threaded_irq(&pdev->dev,
+						pci_irq_vector(pdev, qdev->single_msi ? 0 : i + 1),
 						dbc_irq_handler, dbc_irq_threaded_fn, IRQF_SHARED,
 						"qaic_dbc", &qdev->dbc[i]);
 		if (ret)
 			return ret;
 
 		if (datapath_polling) {
-			qdev->dbc[i].irq = pci_irq_vector(pdev, i + 1);
-			disable_irq_nosync(qdev->dbc[i].irq);
+			qdev->dbc[i].irq = pci_irq_vector(pdev, qdev->single_msi ? 0 : i + 1);
+			if (!qdev->single_msi)
+				disable_irq_nosync(qdev->dbc[i].irq);
 			INIT_WORK(&qdev->dbc[i].poll_work, irq_polling_work);
 		}
 	}
@@ -479,7 +491,8 @@ static int qaic_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto cleanup_qdev;
 	}
 
-	qdev->mhi_cntrl = qaic_mhi_register_controller(pdev, qdev->bar_0, mhi_irq);
+	qdev->mhi_cntrl = qaic_mhi_register_controller(pdev, qdev->bar_0, mhi_irq,
+						       qdev->single_msi);
 	if (IS_ERR(qdev->mhi_cntrl)) {
 		ret = PTR_ERR(qdev->mhi_cntrl);
 		goto cleanup_qdev;
-- 
cgit 


From 6216fb03f8bd0b1439e9e799a306bafd5b462622 Mon Sep 17 00:00:00 2001
From: Ajit Pal Singh <quic_ajitpals@quicinc.com>
Date: Mon, 16 Oct 2023 11:01:13 -0600
Subject: accel/qaic: Add support for periodic timesync

Device and Host have a time synchronization mechanism that happens once
during boot when device is in SBL mode. After that, in mission-mode there
is no timesync. In an experiment after continuous operation, device time
drifted w.r.t. host by approximately 3 seconds per day. This drift leads
to mismatch in timestamp of device and Host logs. To correct this
implement periodic timesync in driver. This timesync is carried out via
QAIC_TIMESYNC_PERIODIC MHI channel.

Signed-off-by: Ajit Pal Singh <quic_ajitpals@quicinc.com>
Signed-off-by: Pranjal Ramajor Asha Kanojiya <quic_pkanojiy@quicinc.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Reviewed-by: Carl Vanderlip <quic_carlv@quicinc.com>
Reviewed-by: Pranjal Ramajor Asha Kanojiya <quic_pkanojiy@quicinc.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231016170114.5446-2-quic_jhugo@quicinc.com
---
 drivers/accel/qaic/Makefile         |   3 +-
 drivers/accel/qaic/mhi_controller.c |  32 +++++
 drivers/accel/qaic/qaic_drv.c       |   6 +
 drivers/accel/qaic/qaic_timesync.c  | 245 ++++++++++++++++++++++++++++++++++++
 drivers/accel/qaic/qaic_timesync.h  |  11 ++
 5 files changed, 296 insertions(+), 1 deletion(-)
 create mode 100644 drivers/accel/qaic/qaic_timesync.c
 create mode 100644 drivers/accel/qaic/qaic_timesync.h

(limited to 'drivers/accel')

diff --git a/drivers/accel/qaic/Makefile b/drivers/accel/qaic/Makefile
index 2418418f7a50..3f7f6dfde7f2 100644
--- a/drivers/accel/qaic/Makefile
+++ b/drivers/accel/qaic/Makefile
@@ -9,4 +9,5 @@ qaic-y := \
 	mhi_controller.o \
 	qaic_control.o \
 	qaic_data.o \
-	qaic_drv.o
+	qaic_drv.o \
+	qaic_timesync.o
diff --git a/drivers/accel/qaic/mhi_controller.c b/drivers/accel/qaic/mhi_controller.c
index 41be3626587d..705898777ec5 100644
--- a/drivers/accel/qaic/mhi_controller.c
+++ b/drivers/accel/qaic/mhi_controller.c
@@ -373,6 +373,38 @@ static struct mhi_channel_config aic100_channels[] = {
 		.auto_queue = false,
 		.wake_capable = false,
 	},
+	{
+		.name = "QAIC_TIMESYNC_PERIODIC",
+		.num = 22,
+		.num_elements = 32,
+		.local_elements = 0,
+		.event_ring = 0,
+		.dir = DMA_TO_DEVICE,
+		.ee_mask = MHI_CH_EE_AMSS,
+		.pollcfg = 0,
+		.doorbell = MHI_DB_BRST_DISABLE,
+		.lpm_notify = false,
+		.offload_channel = false,
+		.doorbell_mode_switch = false,
+		.auto_queue = false,
+		.wake_capable = false,
+	},
+	{
+		.num = 23,
+		.name = "QAIC_TIMESYNC_PERIODIC",
+		.num_elements = 32,
+		.local_elements = 0,
+		.event_ring = 0,
+		.dir = DMA_FROM_DEVICE,
+		.ee_mask = MHI_CH_EE_AMSS,
+		.pollcfg = 0,
+		.doorbell = MHI_DB_BRST_DISABLE,
+		.lpm_notify = false,
+		.offload_channel = false,
+		.doorbell_mode_switch = false,
+		.auto_queue = false,
+		.wake_capable = false,
+	},
 };
 
 static struct mhi_event_config aic100_events[] = {
diff --git a/drivers/accel/qaic/qaic_drv.c b/drivers/accel/qaic/qaic_drv.c
index 5eba5f03d3bf..08d940d3da46 100644
--- a/drivers/accel/qaic/qaic_drv.c
+++ b/drivers/accel/qaic/qaic_drv.c
@@ -27,6 +27,7 @@
 
 #include "mhi_controller.h"
 #include "qaic.h"
+#include "qaic_timesync.h"
 
 MODULE_IMPORT_NS(DMA_BUF);
 
@@ -599,6 +600,10 @@ static int __init qaic_init(void)
 		goto free_pci;
 	}
 
+	ret = qaic_timesync_init();
+	if (ret)
+		pr_debug("qaic: qaic_timesync_init failed %d\n", ret);
+
 	return 0;
 
 free_pci:
@@ -624,6 +629,7 @@ static void __exit qaic_exit(void)
 	 * reinitializing the link_up state after the cleanup is done.
 	 */
 	link_up = true;
+	qaic_timesync_deinit();
 	mhi_driver_unregister(&qaic_mhi_driver);
 	pci_unregister_driver(&qaic_pci_driver);
 }
diff --git a/drivers/accel/qaic/qaic_timesync.c b/drivers/accel/qaic/qaic_timesync.c
new file mode 100644
index 000000000000..769250272c21
--- /dev/null
+++ b/drivers/accel/qaic/qaic_timesync.c
@@ -0,0 +1,245 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved. */
+
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/math64.h>
+#include <linux/mhi.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/time64.h>
+#include <linux/timer.h>
+
+#include "qaic.h"
+#include "qaic_timesync.h"
+
+#define QTIMER_REG_OFFSET			0xa28
+#define QAIC_TIMESYNC_SIGNATURE			0x55aa
+#define QAIC_CONV_QTIMER_TO_US(qtimer)		(mul_u64_u32_div(qtimer, 10, 192))
+
+static unsigned int timesync_delay_ms = 1000; /* 1 sec default */
+module_param(timesync_delay_ms, uint, 0600);
+MODULE_PARM_DESC(timesync_delay_ms, "Delay in ms between two consecutive timesync operations");
+
+enum qts_msg_type {
+	QAIC_TS_SYNC_REQ = 1,
+	QAIC_TS_ACK_TO_HOST,
+	QAIC_TS_MSG_TYPE_MAX
+};
+
+/**
+ * struct qts_hdr - Timesync message header structure.
+ * @signature: Unique signature to identify the timesync message.
+ * @reserved_1: Reserved for future use.
+ * @reserved_2: Reserved for future use.
+ * @msg_type: sub-type of the timesync message.
+ * @reserved_3: Reserved for future use.
+ */
+struct qts_hdr {
+	__le16	signature;
+	__le16	reserved_1;
+	u8	reserved_2;
+	u8	msg_type;
+	__le16	reserved_3;
+} __packed;
+
+/**
+ * struct qts_timeval - Structure to carry time information.
+ * @tv_sec: Seconds part of the time.
+ * @tv_usec: uS (microseconds) part of the time.
+ */
+struct qts_timeval {
+	__le64	tv_sec;
+	__le64	tv_usec;
+} __packed;
+
+/**
+ * struct qts_host_time_sync_msg_data - Structure to denote the timesync message.
+ * @header: Header of the timesync message.
+ * @data: Time information.
+ */
+struct qts_host_time_sync_msg_data {
+	struct	qts_hdr header;
+	struct	qts_timeval data;
+} __packed;
+
+/**
+ * struct mqts_dev - MHI QAIC Timesync Control device.
+ * @qdev: Pointer to the root device struct driven by QAIC driver.
+ * @mhi_dev: Pointer to associated MHI device.
+ * @timer: Timer handle used for timesync.
+ * @qtimer_addr: Device QTimer register pointer.
+ * @buff_in_use: atomic variable to track if the sync_msg buffer is in use.
+ * @dev: Device pointer to qdev->pdev->dev stored for easy access.
+ * @sync_msg: Buffer used to send timesync message over MHI.
+ */
+struct mqts_dev {
+	struct qaic_device *qdev;
+	struct mhi_device *mhi_dev;
+	struct timer_list timer;
+	void __iomem *qtimer_addr;
+	atomic_t buff_in_use;
+	struct device *dev;
+	struct qts_host_time_sync_msg_data *sync_msg;
+};
+
+#ifdef readq
+static u64 read_qtimer(const volatile void __iomem *addr)
+{
+	return readq(addr);
+}
+#else
+static u64 read_qtimer(const volatile void __iomem *addr)
+{
+	u64 low, high;
+
+	low = readl(addr);
+	high = readl(addr + sizeof(u32));
+	return low | (high << 32);
+}
+#endif
+
+static void qaic_timesync_ul_xfer_cb(struct mhi_device *mhi_dev, struct mhi_result *mhi_result)
+{
+	struct mqts_dev *mqtsdev = dev_get_drvdata(&mhi_dev->dev);
+
+	dev_dbg(mqtsdev->dev, "%s status: %d xfer_len: %zu\n", __func__,
+		mhi_result->transaction_status, mhi_result->bytes_xferd);
+
+	atomic_set(&mqtsdev->buff_in_use, 0);
+}
+
+static void qaic_timesync_dl_xfer_cb(struct mhi_device *mhi_dev, struct mhi_result *mhi_result)
+{
+	struct mqts_dev *mqtsdev = dev_get_drvdata(&mhi_dev->dev);
+
+	dev_err(mqtsdev->dev, "%s no data expected on dl channel\n", __func__);
+}
+
+static void qaic_timesync_timer(struct timer_list *t)
+{
+	struct mqts_dev *mqtsdev = from_timer(mqtsdev, t, timer);
+	struct qts_host_time_sync_msg_data *sync_msg;
+	u64 device_qtimer_us;
+	u64 device_qtimer;
+	u64 host_time_us;
+	u64 offset_us;
+	u64 host_sec;
+	int ret;
+
+	if (atomic_read(&mqtsdev->buff_in_use)) {
+		dev_dbg(mqtsdev->dev, "%s buffer not free, schedule next cycle\n", __func__);
+		goto mod_timer;
+	}
+	atomic_set(&mqtsdev->buff_in_use, 1);
+
+	sync_msg = mqtsdev->sync_msg;
+	sync_msg->header.signature = cpu_to_le16(QAIC_TIMESYNC_SIGNATURE);
+	sync_msg->header.msg_type = QAIC_TS_SYNC_REQ;
+	/* Read host UTC time and convert to uS*/
+	host_time_us = div_u64(ktime_get_real_ns(), NSEC_PER_USEC);
+	device_qtimer = read_qtimer(mqtsdev->qtimer_addr);
+	device_qtimer_us = QAIC_CONV_QTIMER_TO_US(device_qtimer);
+	/* Offset between host UTC and device time */
+	offset_us = host_time_us - device_qtimer_us;
+
+	host_sec = div_u64(offset_us, USEC_PER_SEC);
+	sync_msg->data.tv_usec = cpu_to_le64(offset_us - host_sec * USEC_PER_SEC);
+	sync_msg->data.tv_sec = cpu_to_le64(host_sec);
+	ret = mhi_queue_buf(mqtsdev->mhi_dev, DMA_TO_DEVICE, sync_msg, sizeof(*sync_msg), MHI_EOT);
+	if (ret && (ret != -EAGAIN)) {
+		dev_err(mqtsdev->dev, "%s unable to queue to mhi:%d\n", __func__, ret);
+		return;
+	} else if (ret == -EAGAIN) {
+		atomic_set(&mqtsdev->buff_in_use, 0);
+	}
+
+mod_timer:
+	ret = mod_timer(t, jiffies + msecs_to_jiffies(timesync_delay_ms));
+	if (ret)
+		dev_err(mqtsdev->dev, "%s mod_timer error:%d\n", __func__, ret);
+}
+
+static int qaic_timesync_probe(struct mhi_device *mhi_dev, const struct mhi_device_id *id)
+{
+	struct qaic_device *qdev = pci_get_drvdata(to_pci_dev(mhi_dev->mhi_cntrl->cntrl_dev));
+	struct mqts_dev *mqtsdev;
+	struct timer_list *timer;
+	int ret;
+
+	mqtsdev = kzalloc(sizeof(*mqtsdev), GFP_KERNEL);
+	if (!mqtsdev) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	timer = &mqtsdev->timer;
+	mqtsdev->mhi_dev = mhi_dev;
+	mqtsdev->qdev = qdev;
+	mqtsdev->dev = &qdev->pdev->dev;
+
+	mqtsdev->sync_msg = kzalloc(sizeof(*mqtsdev->sync_msg), GFP_KERNEL);
+	if (!mqtsdev->sync_msg) {
+		ret = -ENOMEM;
+		goto free_mqts_dev;
+	}
+	atomic_set(&mqtsdev->buff_in_use, 0);
+
+	ret = mhi_prepare_for_transfer(mhi_dev);
+	if (ret)
+		goto free_sync_msg;
+
+	/* Qtimer register pointer */
+	mqtsdev->qtimer_addr = qdev->bar_0 + QTIMER_REG_OFFSET;
+	timer_setup(timer, qaic_timesync_timer, 0);
+	timer->expires = jiffies + msecs_to_jiffies(timesync_delay_ms);
+	add_timer(timer);
+	dev_set_drvdata(&mhi_dev->dev, mqtsdev);
+
+	return 0;
+
+free_sync_msg:
+	kfree(mqtsdev->sync_msg);
+free_mqts_dev:
+	kfree(mqtsdev);
+out:
+	return ret;
+};
+
+static void qaic_timesync_remove(struct mhi_device *mhi_dev)
+{
+	struct mqts_dev *mqtsdev = dev_get_drvdata(&mhi_dev->dev);
+
+	del_timer_sync(&mqtsdev->timer);
+	mhi_unprepare_from_transfer(mqtsdev->mhi_dev);
+	kfree(mqtsdev->sync_msg);
+	kfree(mqtsdev);
+}
+
+static const struct mhi_device_id qaic_timesync_match_table[] = {
+	{ .chan = "QAIC_TIMESYNC_PERIODIC"},
+	{},
+};
+
+MODULE_DEVICE_TABLE(mhi, qaic_timesync_match_table);
+
+static struct mhi_driver qaic_timesync_driver = {
+	.id_table = qaic_timesync_match_table,
+	.remove = qaic_timesync_remove,
+	.probe = qaic_timesync_probe,
+	.ul_xfer_cb = qaic_timesync_ul_xfer_cb,
+	.dl_xfer_cb = qaic_timesync_dl_xfer_cb,
+	.driver = {
+		.name = "qaic_timesync_periodic",
+	},
+};
+
+int qaic_timesync_init(void)
+{
+	return mhi_driver_register(&qaic_timesync_driver);
+}
+
+void qaic_timesync_deinit(void)
+{
+	mhi_driver_unregister(&qaic_timesync_driver);
+}
diff --git a/drivers/accel/qaic/qaic_timesync.h b/drivers/accel/qaic/qaic_timesync.h
new file mode 100644
index 000000000000..851b7acd43bb
--- /dev/null
+++ b/drivers/accel/qaic/qaic_timesync.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ *
+ * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#ifndef __QAIC_TIMESYNC_H__
+#define __QAIC_TIMESYNC_H__
+
+int qaic_timesync_init(void);
+void qaic_timesync_deinit(void);
+#endif /* __QAIC_TIMESYNC_H__ */
-- 
cgit 


From 41cfbaa47fd7d94df5faf1c416801600f26270d8 Mon Sep 17 00:00:00 2001
From: Pranjal Ramajor Asha Kanojiya <quic_pkanojiy@quicinc.com>
Date: Mon, 16 Oct 2023 11:01:14 -0600
Subject: accel/qaic: Support MHI QAIC_TIMESYNC channel

Use QAIC_TIMESYNC MHI channel to send UTC time to device in SBL
environment. Remove support for QAIC_TIMESYNC MHI channel in AMSS
environment as it is not used in that environment.

Signed-off-by: Pranjal Ramajor Asha Kanojiya <quic_pkanojiy@quicinc.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Reviewed-by: Carl Vanderlip <quic_carlv@quicinc.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231016170114.5446-3-quic_jhugo@quicinc.com
---
 drivers/accel/qaic/mhi_controller.c |   4 +-
 drivers/accel/qaic/qaic.h           |   4 +
 drivers/accel/qaic/qaic_drv.c       |   7 ++
 drivers/accel/qaic/qaic_timesync.c  | 154 +++++++++++++++++++++++++++++++++++-
 4 files changed, 165 insertions(+), 4 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/qaic/mhi_controller.c b/drivers/accel/qaic/mhi_controller.c
index 705898777ec5..5d3cc30009cc 100644
--- a/drivers/accel/qaic/mhi_controller.c
+++ b/drivers/accel/qaic/mhi_controller.c
@@ -348,7 +348,7 @@ static struct mhi_channel_config aic100_channels[] = {
 		.local_elements = 0,
 		.event_ring = 0,
 		.dir = DMA_TO_DEVICE,
-		.ee_mask = MHI_CH_EE_SBL | MHI_CH_EE_AMSS,
+		.ee_mask = MHI_CH_EE_SBL,
 		.pollcfg = 0,
 		.doorbell = MHI_DB_BRST_DISABLE,
 		.lpm_notify = false,
@@ -364,7 +364,7 @@ static struct mhi_channel_config aic100_channels[] = {
 		.local_elements = 0,
 		.event_ring = 0,
 		.dir = DMA_FROM_DEVICE,
-		.ee_mask = MHI_CH_EE_SBL | MHI_CH_EE_AMSS,
+		.ee_mask = MHI_CH_EE_SBL,
 		.pollcfg = 0,
 		.doorbell = MHI_DB_BRST_DISABLE,
 		.lpm_notify = false,
diff --git a/drivers/accel/qaic/qaic.h b/drivers/accel/qaic/qaic.h
index 01e9dda0cc37..bc40d52dc010 100644
--- a/drivers/accel/qaic/qaic.h
+++ b/drivers/accel/qaic/qaic.h
@@ -139,6 +139,10 @@ struct qaic_device {
 	u32 (*gen_crc)(void *msg);
 	/* Validate the CRC of a control message */
 	bool (*valid_crc)(void *msg);
+	/* MHI "QAIC_TIMESYNC" channel device */
+	struct mhi_device	*qts_ch;
+	/* Work queue for tasks related to MHI "QAIC_TIMESYNC" channel */
+	struct workqueue_struct	*qts_wq;
 };
 
 struct qaic_drm_device {
diff --git a/drivers/accel/qaic/qaic_drv.c b/drivers/accel/qaic/qaic_drv.c
index 08d940d3da46..b12226385003 100644
--- a/drivers/accel/qaic/qaic_drv.c
+++ b/drivers/accel/qaic/qaic_drv.c
@@ -325,6 +325,7 @@ static void cleanup_qdev(struct qaic_device *qdev)
 	cleanup_srcu_struct(&qdev->dev_lock);
 	pci_set_drvdata(qdev->pdev, NULL);
 	destroy_workqueue(qdev->cntl_wq);
+	destroy_workqueue(qdev->qts_wq);
 }
 
 static struct qaic_device *create_qdev(struct pci_dev *pdev, const struct pci_device_id *id)
@@ -348,6 +349,12 @@ static struct qaic_device *create_qdev(struct pci_dev *pdev, const struct pci_de
 	if (!qdev->cntl_wq)
 		return NULL;
 
+	qdev->qts_wq = alloc_workqueue("qaic_ts", WQ_UNBOUND, 0);
+	if (!qdev->qts_wq) {
+		destroy_workqueue(qdev->cntl_wq);
+		return NULL;
+	}
+
 	pci_set_drvdata(pdev, qdev);
 	qdev->pdev = pdev;
 
diff --git a/drivers/accel/qaic/qaic_timesync.c b/drivers/accel/qaic/qaic_timesync.c
index 769250272c21..301f4462d51b 100644
--- a/drivers/accel/qaic/qaic_timesync.c
+++ b/drivers/accel/qaic/qaic_timesync.c
@@ -22,7 +22,8 @@ module_param(timesync_delay_ms, uint, 0600);
 MODULE_PARM_DESC(timesync_delay_ms, "Delay in ms between two consecutive timesync operations");
 
 enum qts_msg_type {
-	QAIC_TS_SYNC_REQ = 1,
+	QAIC_TS_CMD_TO_HOST,
+	QAIC_TS_SYNC_REQ,
 	QAIC_TS_ACK_TO_HOST,
 	QAIC_TS_MSG_TYPE_MAX
 };
@@ -83,6 +84,16 @@ struct mqts_dev {
 	struct qts_host_time_sync_msg_data *sync_msg;
 };
 
+struct qts_resp_msg {
+	struct qts_hdr	hdr;
+} __packed;
+
+struct qts_resp {
+	struct qts_resp_msg	data;
+	struct work_struct	work;
+	struct qaic_device	*qdev;
+};
+
 #ifdef readq
 static u64 read_qtimer(const volatile void __iomem *addr)
 {
@@ -234,12 +245,151 @@ static struct mhi_driver qaic_timesync_driver = {
 	},
 };
 
+static void qaic_boot_timesync_worker(struct work_struct *work)
+{
+	struct qts_resp *resp = container_of(work, struct qts_resp, work);
+	struct qts_host_time_sync_msg_data *req;
+	struct qts_resp_msg data = resp->data;
+	struct qaic_device *qdev = resp->qdev;
+	struct mhi_device *mhi_dev;
+	struct timespec64 ts;
+	int ret;
+
+	mhi_dev = qdev->qts_ch;
+	/* Queue the response message beforehand to avoid race conditions */
+	ret = mhi_queue_buf(mhi_dev, DMA_FROM_DEVICE, &resp->data, sizeof(resp->data), MHI_EOT);
+	if (ret) {
+		kfree(resp);
+		dev_warn(&mhi_dev->dev, "Failed to re-queue response buffer %d\n", ret);
+		return;
+	}
+
+	switch (data.hdr.msg_type) {
+	case QAIC_TS_CMD_TO_HOST:
+		req = kzalloc(sizeof(*req), GFP_KERNEL);
+		if (!req)
+			break;
+
+		req->header = data.hdr;
+		req->header.msg_type = QAIC_TS_SYNC_REQ;
+		ktime_get_real_ts64(&ts);
+		req->data.tv_sec = cpu_to_le64(ts.tv_sec);
+		req->data.tv_usec = cpu_to_le64(div_u64(ts.tv_nsec, NSEC_PER_USEC));
+
+		ret = mhi_queue_buf(mhi_dev, DMA_TO_DEVICE, req, sizeof(*req), MHI_EOT);
+		if (ret) {
+			kfree(req);
+			dev_dbg(&mhi_dev->dev, "Failed to send request message. Error %d\n", ret);
+		}
+		break;
+	case QAIC_TS_ACK_TO_HOST:
+		dev_dbg(&mhi_dev->dev, "ACK received from device\n");
+		break;
+	default:
+		dev_err(&mhi_dev->dev, "Invalid message type %u.\n", data.hdr.msg_type);
+	}
+}
+
+static int qaic_boot_timesync_queue_resp(struct mhi_device *mhi_dev, struct qaic_device *qdev)
+{
+	struct qts_resp *resp;
+	int ret;
+
+	resp = kzalloc(sizeof(*resp), GFP_KERNEL);
+	if (!resp)
+		return -ENOMEM;
+
+	resp->qdev = qdev;
+	INIT_WORK(&resp->work, qaic_boot_timesync_worker);
+
+	ret = mhi_queue_buf(mhi_dev, DMA_FROM_DEVICE, &resp->data, sizeof(resp->data), MHI_EOT);
+	if (ret) {
+		kfree(resp);
+		dev_warn(&mhi_dev->dev, "Failed to queue response buffer %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void qaic_boot_timesync_remove(struct mhi_device *mhi_dev)
+{
+	struct qaic_device *qdev;
+
+	qdev = dev_get_drvdata(&mhi_dev->dev);
+	mhi_unprepare_from_transfer(qdev->qts_ch);
+	qdev->qts_ch = NULL;
+}
+
+static int qaic_boot_timesync_probe(struct mhi_device *mhi_dev, const struct mhi_device_id *id)
+{
+	struct qaic_device *qdev = pci_get_drvdata(to_pci_dev(mhi_dev->mhi_cntrl->cntrl_dev));
+	int ret;
+
+	ret = mhi_prepare_for_transfer(mhi_dev);
+	if (ret)
+		return ret;
+
+	qdev->qts_ch = mhi_dev;
+	dev_set_drvdata(&mhi_dev->dev, qdev);
+
+	ret = qaic_boot_timesync_queue_resp(mhi_dev, qdev);
+	if (ret) {
+		dev_set_drvdata(&mhi_dev->dev, NULL);
+		qdev->qts_ch = NULL;
+		mhi_unprepare_from_transfer(mhi_dev);
+	}
+
+	return ret;
+}
+
+static void qaic_boot_timesync_ul_xfer_cb(struct mhi_device *mhi_dev, struct mhi_result *mhi_result)
+{
+	kfree(mhi_result->buf_addr);
+}
+
+static void qaic_boot_timesync_dl_xfer_cb(struct mhi_device *mhi_dev, struct mhi_result *mhi_result)
+{
+	struct qts_resp *resp = container_of(mhi_result->buf_addr, struct qts_resp, data);
+
+	if (mhi_result->transaction_status || mhi_result->bytes_xferd != sizeof(resp->data)) {
+		kfree(resp);
+		return;
+	}
+
+	queue_work(resp->qdev->qts_wq, &resp->work);
+}
+
+static const struct mhi_device_id qaic_boot_timesync_match_table[] = {
+	{ .chan = "QAIC_TIMESYNC"},
+	{},
+};
+
+static struct mhi_driver qaic_boot_timesync_driver = {
+	.id_table = qaic_boot_timesync_match_table,
+	.remove = qaic_boot_timesync_remove,
+	.probe = qaic_boot_timesync_probe,
+	.ul_xfer_cb = qaic_boot_timesync_ul_xfer_cb,
+	.dl_xfer_cb = qaic_boot_timesync_dl_xfer_cb,
+	.driver = {
+		.name = "qaic_timesync",
+	},
+};
+
 int qaic_timesync_init(void)
 {
-	return mhi_driver_register(&qaic_timesync_driver);
+	int ret;
+
+	ret = mhi_driver_register(&qaic_timesync_driver);
+	if (ret)
+		return ret;
+	ret = mhi_driver_register(&qaic_boot_timesync_driver);
+
+	return ret;
 }
 
 void qaic_timesync_deinit(void)
 {
+	mhi_driver_unregister(&qaic_boot_timesync_driver);
 	mhi_driver_unregister(&qaic_timesync_driver);
 }
-- 
cgit 


From 1470acbef122c7e2e588f6346ce459c26d0568a2 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 27 Oct 2023 17:26:23 +0200
Subject: accel/ivpu: avoid build failure with CONFIG_PM=n

The usage count of struct dev_pm_info is an implementation detail that
is only available if CONFIG_PM is enabled, so printing it in a debug message
causes a build failure in configurations without PM:

In file included from include/linux/device.h:15,
                 from include/linux/pci.h:37,
                 from drivers/accel/ivpu/ivpu_pm.c:8:
drivers/accel/ivpu/ivpu_pm.c: In function 'ivpu_rpm_get_if_active':
drivers/accel/ivpu/ivpu_pm.c:254:51: error: 'struct dev_pm_info' has no member named 'usage_count'
  254 |                  atomic_read(&vdev->drm.dev->power.usage_count));
      |                                                   ^
include/linux/dev_printk.h:129:48: note: in definition of macro 'dev_printk'
  129 |                 _dev_printk(level, dev, fmt, ##__VA_ARGS__);            \
      |                                                ^~~~~~~~~~~
drivers/accel/ivpu/ivpu_drv.h:75:17: note: in expansion of macro 'dev_dbg'
   75 |                 dev_dbg((vdev)->drm.dev, "[%s] " fmt, #type, ##args);          \
      |                 ^~~~~~~
drivers/accel/ivpu/ivpu_pm.c:253:9: note: in expansion of macro 'ivpu_dbg'
  253 |         ivpu_dbg(vdev, RPM, "rpm_get_if_active count %d\n",
      |         ^~~~~~~~

The print message does not seem essential, so the easiest workaround is
to just remove it.

Fixes: c39dc15191c4 ("accel/ivpu: Read clock rate only if device is up")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231027152633.528490-1-arnd@kernel.org
---
 drivers/accel/ivpu/ivpu_pm.c | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c
index d14b6fd796b4..568e4295dc56 100644
--- a/drivers/accel/ivpu/ivpu_pm.c
+++ b/drivers/accel/ivpu/ivpu_pm.c
@@ -250,9 +250,6 @@ int ivpu_rpm_get_if_active(struct ivpu_device *vdev)
 {
 	int ret;
 
-	ivpu_dbg(vdev, RPM, "rpm_get_if_active count %d\n",
-		 atomic_read(&vdev->drm.dev->power.usage_count));
-
 	ret = pm_runtime_get_if_active(vdev->drm.dev, false);
 	drm_WARN_ON(&vdev->drm, ret < 0);
 
-- 
cgit 


From 8c63b47412ad3f015db47b380916722299511cc3 Mon Sep 17 00:00:00 2001
From: Krystian Pradzynski <krystian.pradzynski@linux.intel.com>
Date: Sat, 28 Oct 2023 15:34:05 +0200
Subject: accel/ivpu: Update FW API

Bump boot API to 4.20
Bump JSM API to 3.15

Signed-off-by: Krystian Pradzynski <krystian.pradzynski@linux.intel.com>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231028133415.1169975-2-stanislaw.gruszka@linux.intel.com
---
 drivers/accel/ivpu/ivpu_jsm_msg.c |  17 +++
 drivers/accel/ivpu/vpu_boot_api.h |  90 +++++++++--
 drivers/accel/ivpu/vpu_jsm_api.h  | 309 ++++++++++++++++++++++++++++++++++++--
 3 files changed, 392 insertions(+), 24 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/ivpu/ivpu_jsm_msg.c b/drivers/accel/ivpu/ivpu_jsm_msg.c
index 0c2fe7142024..35a689475c68 100644
--- a/drivers/accel/ivpu/ivpu_jsm_msg.c
+++ b/drivers/accel/ivpu/ivpu_jsm_msg.c
@@ -36,6 +36,17 @@ const char *ivpu_jsm_msg_type_to_str(enum vpu_ipc_msg_type type)
 	IVPU_CASE_TO_STR(VPU_JSM_MSG_DESTROY_CMD_QUEUE);
 	IVPU_CASE_TO_STR(VPU_JSM_MSG_SET_CONTEXT_SCHED_PROPERTIES);
 	IVPU_CASE_TO_STR(VPU_JSM_MSG_HWS_REGISTER_DB);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_HWS_RESUME_CMDQ);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_HWS_SUSPEND_CMDQ);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_HWS_RESUME_CMDQ_RSP);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_HWS_SUSPEND_CMDQ_DONE);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_HWS_SET_SCHEDULING_LOG);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_HWS_SET_SCHEDULING_LOG_RSP);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_HWS_SCHEDULING_LOG_NOTIFICATION);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_HWS_ENGINE_RESUME);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_HWS_RESUME_ENGINE_DONE);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_STATE_DUMP);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_STATE_DUMP_RSP);
 	IVPU_CASE_TO_STR(VPU_JSM_MSG_BLOB_DEINIT);
 	IVPU_CASE_TO_STR(VPU_JSM_MSG_DYNDBG_CONTROL);
 	IVPU_CASE_TO_STR(VPU_JSM_MSG_JOB_DONE);
@@ -65,6 +76,12 @@ const char *ivpu_jsm_msg_type_to_str(enum vpu_ipc_msg_type type)
 	IVPU_CASE_TO_STR(VPU_JSM_MSG_SET_CONTEXT_SCHED_PROPERTIES_RSP);
 	IVPU_CASE_TO_STR(VPU_JSM_MSG_BLOB_DEINIT_DONE);
 	IVPU_CASE_TO_STR(VPU_JSM_MSG_DYNDBG_CONTROL_RSP);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_PWR_D0I3_ENTER);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_PWR_D0I3_ENTER_DONE);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_DCT_ENABLE);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_DCT_ENABLE_DONE);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_DCT_DISABLE);
+	IVPU_CASE_TO_STR(VPU_JSM_MSG_DCT_DISABLE_DONE);
 	}
 	#undef IVPU_CASE_TO_STR
 
diff --git a/drivers/accel/ivpu/vpu_boot_api.h b/drivers/accel/ivpu/vpu_boot_api.h
index 6b71be92ba65..04c954258563 100644
--- a/drivers/accel/ivpu/vpu_boot_api.h
+++ b/drivers/accel/ivpu/vpu_boot_api.h
@@ -11,7 +11,10 @@
  *  The bellow values will be used to construct the version info this way:
  *  fw_bin_header->api_version[VPU_BOOT_API_VER_ID] = (VPU_BOOT_API_VER_MAJOR << 16) |
  *  VPU_BOOT_API_VER_MINOR;
- *  VPU_BOOT_API_VER_PATCH will be ignored. KMD and compatibility is not affected if this changes.
+ *  VPU_BOOT_API_VER_PATCH will be ignored. KMD and compatibility is not affected if this changes
+ *  This information is collected by using vpuip_2/application/vpuFirmware/make_std_fw_image.py
+ *  If a header is missing this info we ignore the header, if a header is missing or contains
+ *  partial info a build error will be generated.
  */
 
 /*
@@ -24,12 +27,12 @@
  * Minor version changes when API backward compatibility is preserved.
  * Resets to 0 if Major version is incremented.
  */
-#define VPU_BOOT_API_VER_MINOR 12
+#define VPU_BOOT_API_VER_MINOR 20
 
 /*
  * API header changed (field names, documentation, formatting) but API itself has not been changed
  */
-#define VPU_BOOT_API_VER_PATCH 2
+#define VPU_BOOT_API_VER_PATCH 4
 
 /*
  * Index in the API version table
@@ -63,6 +66,12 @@ struct vpu_firmware_header {
 	/* Size of memory require for firmware execution */
 	u32 runtime_size;
 	u32 shave_nn_fw_size;
+	/* Size of primary preemption buffer. */
+	u32 preemption_buffer_1_size;
+	/* Size of secondary preemption buffer. */
+	u32 preemption_buffer_2_size;
+	/* Space reserved for future preemption-related fields. */
+	u32 preemption_reserved[6];
 };
 
 /*
@@ -89,6 +98,14 @@ enum VPU_BOOT_L2_CACHE_CFG_TYPE {
 	VPU_BOOT_L2_CACHE_CFG_NUM = 2
 };
 
+/** VPU MCA ECC signalling mode. By default, no signalling is used */
+enum VPU_BOOT_MCA_ECC_SIGNAL_TYPE {
+	VPU_BOOT_MCA_ECC_NONE = 0,
+	VPU_BOOT_MCA_ECC_CORR = 1,
+	VPU_BOOT_MCA_ECC_FATAL = 2,
+	VPU_BOOT_MCA_ECC_BOTH = 3
+};
+
 /**
  * Logging destinations.
  *
@@ -131,9 +148,11 @@ enum vpu_trace_destination {
 #define VPU_TRACE_PROC_BIT_ACT_SHV_3 22
 #define VPU_TRACE_PROC_NO_OF_HW_DEVS 23
 
-/* KMB HW component IDs are sequential, so define first and last IDs. */
-#define VPU_TRACE_PROC_BIT_KMB_FIRST VPU_TRACE_PROC_BIT_LRT
-#define VPU_TRACE_PROC_BIT_KMB_LAST  VPU_TRACE_PROC_BIT_SHV_15
+/* VPU 30xx HW component IDs are sequential, so define first and last IDs. */
+#define VPU_TRACE_PROC_BIT_30XX_FIRST VPU_TRACE_PROC_BIT_LRT
+#define VPU_TRACE_PROC_BIT_30XX_LAST  VPU_TRACE_PROC_BIT_SHV_15
+#define VPU_TRACE_PROC_BIT_KMB_FIRST  VPU_TRACE_PROC_BIT_30XX_FIRST
+#define VPU_TRACE_PROC_BIT_KMB_LAST   VPU_TRACE_PROC_BIT_30XX_LAST
 
 struct vpu_boot_l2_cache_config {
 	u8 use;
@@ -148,6 +167,25 @@ struct vpu_warm_boot_section {
 	u32 is_clear_op;
 };
 
+/*
+ * When HW scheduling mode is enabled, a present period is defined.
+ * It will be used by VPU to swap between normal and focus priorities
+ * to prevent starving of normal priority band (when implemented).
+ * Host must provide a valid value at boot time in
+ * `vpu_focus_present_timer_ms`. If the value provided by the host is not within the
+ * defined range a default value will be used. Here we define the min. and max.
+ * allowed values and the and default value of the present period. Units are milliseconds.
+ */
+#define VPU_PRESENT_CALL_PERIOD_MS_DEFAULT 50
+#define VPU_PRESENT_CALL_PERIOD_MS_MIN	   16
+#define VPU_PRESENT_CALL_PERIOD_MS_MAX	   10000
+
+/**
+ * Macros to enable various operation modes within the VPU.
+ * To be defined as part of 32 bit mask.
+ */
+#define VPU_OP_MODE_SURVIVABILITY 0x1
+
 struct vpu_boot_params {
 	u32 magic;
 	u32 vpu_id;
@@ -218,6 +256,7 @@ struct vpu_boot_params {
 	 * the threshold will not be logged); applies to every enabled logging
 	 * destination and loggable HW component. See 'mvLog_t' enum for acceptable
 	 * values.
+	 * TODO: EISW-33556: Move log level definition (mvLog_t) to this file.
 	 */
 	u32 default_trace_level;
 	u32 boot_type;
@@ -249,7 +288,36 @@ struct vpu_boot_params {
 	u32 temp_sensor_period_ms;
 	/** PLL ratio for efficient clock frequency */
 	u32 pn_freq_pll_ratio;
-	u32 pad4[28];
+	/** DVFS Mode: Default: 0, Max Performance: 1, On Demand: 2, Power Save: 3 */
+	u32 dvfs_mode;
+	/**
+	 * Depending on DVFS Mode:
+	 * On-demand: Default if 0.
+	 *    Bit 0-7   - uint8_t: Highest residency percent
+	 *    Bit 8-15  - uint8_t: High residency percent
+	 *    Bit 16-23 - uint8_t: Low residency percent
+	 *    Bit 24-31 - uint8_t: Lowest residency percent
+	 *    Bit 32-35 - unsigned 4b: PLL Ratio increase amount on highest residency
+	 *    Bit 36-39 - unsigned 4b: PLL Ratio increase amount on high residency
+	 *    Bit 40-43 - unsigned 4b: PLL Ratio decrease amount on low residency
+	 *    Bit 44-47 - unsigned 4b: PLL Ratio decrease amount on lowest frequency
+	 *    Bit 48-55 - uint8_t: Period (ms) for residency decisions
+	 *    Bit 56-63 - uint8_t: Averaging windows (as multiples of period. Max: 30 decimal)
+	 * Power Save/Max Performance: Unused
+	 */
+	u64 dvfs_param;
+	/**
+	 * D0i3 delayed entry
+	 * Bit0: Disable CPU state save on D0i2 entry flow.
+	 *       0: Every D0i2 entry saves state. Save state IPC message ignored.
+	 *       1: IPC message required to save state on D0i3 entry flow.
+	 */
+	u32 d0i3_delayed_entry;
+	/* Time spent by VPU in D0i3 state */
+	u64 d0i3_residency_time_us;
+	/* Value of VPU perf counter at the time of entering D0i3 state . */
+	u64 d0i3_entry_vpu_ts;
+	u32 pad4[20];
 	/* Warm boot information: 0x400 - 0x43F */
 	u32 warm_boot_sections_count;
 	u32 warm_boot_start_address_reference;
@@ -274,8 +342,12 @@ struct vpu_boot_params {
 	u32 vpu_scheduling_mode;
 	/* Present call period in milliseconds. */
 	u32 vpu_focus_present_timer_ms;
-	/* Unused/reserved: 0x478 - 0xFFF */
-	u32 pad6[738];
+	/* VPU ECC Signaling */
+	u32 vpu_uses_ecc_mca_signal;
+	/* Values defined by VPU_OP_MODE* macros */
+	u32 vpu_operation_mode;
+	/* Unused/reserved: 0x480 - 0xFFF */
+	u32 pad6[736];
 };
 
 /*
diff --git a/drivers/accel/ivpu/vpu_jsm_api.h b/drivers/accel/ivpu/vpu_jsm_api.h
index 2949ec8365bd..7da7622742be 100644
--- a/drivers/accel/ivpu/vpu_jsm_api.h
+++ b/drivers/accel/ivpu/vpu_jsm_api.h
@@ -22,12 +22,12 @@
 /*
  * Minor version changes when API backward compatibility is preserved.
  */
-#define VPU_JSM_API_VER_MINOR 0
+#define VPU_JSM_API_VER_MINOR 15
 
 /*
  * API header changed (field names, documentation, formatting) but API itself has not been changed
  */
-#define VPU_JSM_API_VER_PATCH 1
+#define VPU_JSM_API_VER_PATCH 0
 
 /*
  * Index in the API version table
@@ -84,11 +84,13 @@
  * Job flags bit masks.
  */
 #define VPU_JOB_FLAGS_NULL_SUBMISSION_MASK 0x00000001
+#define VPU_JOB_FLAGS_PRIVATE_DATA_MASK	   0xFF000000
 
 /*
  * Sizes of the reserved areas in jobs, in bytes.
  */
-#define VPU_JOB_RESERVED_BYTES	     16
+#define VPU_JOB_RESERVED_BYTES 8
+
 /*
  * Sizes of the reserved areas in job queues, in bytes.
  */
@@ -108,6 +110,20 @@
  */
 #define VPU_DYNDBG_CMD_MAX_LEN 96
 
+/*
+ * For HWS command queue scheduling, we can prioritise command queues inside the
+ * same process with a relative in-process priority. Valid values for relative
+ * priority are given below - max and min.
+ */
+#define VPU_HWS_COMMAND_QUEUE_MAX_IN_PROCESS_PRIORITY 7
+#define VPU_HWS_COMMAND_QUEUE_MIN_IN_PROCESS_PRIORITY -7
+
+/*
+ * For HWS priority scheduling, we can have multiple realtime priority bands.
+ * They are numbered 0 to a MAX.
+ */
+#define VPU_HWS_MAX_REALTIME_PRIORITY_LEVEL 31U
+
 /*
  * Job format.
  */
@@ -117,8 +133,14 @@ struct vpu_job_queue_entry {
 	u32 flags; /**< Flags bit field, see VPU_JOB_FLAGS_* above */
 	u64 root_page_table_addr; /**< Address of root page table to use for this job */
 	u64 root_page_table_update_counter; /**< Page tables update events counter */
-	u64 preemption_buffer_address; /**< Address of the preemption buffer to use for this job */
-	u64 preemption_buffer_size; /**< Size of the preemption buffer to use for this job */
+	u64 primary_preempt_buf_addr;
+	/**< Address of the primary preemption buffer to use for this job */
+	u32 primary_preempt_buf_size;
+	/**< Size of the primary preemption buffer to use for this job */
+	u32 secondary_preempt_buf_size;
+	/**< Size of secondary preemption buffer to use for this job */
+	u64 secondary_preempt_buf_addr;
+	/**< Address of secondary preemption buffer to use for this job */
 	u8 reserved_0[VPU_JOB_RESERVED_BYTES];
 };
 
@@ -152,6 +174,46 @@ enum vpu_trace_entity_type {
 	VPU_TRACE_ENTITY_TYPE_HW_COMPONENT = 2,
 };
 
+/*
+ * HWS specific log buffer header details.
+ * Total size is 32 bytes.
+ */
+struct vpu_hws_log_buffer_header {
+	/* Written by VPU after adding a log entry. Initialised by host to 0. */
+	u32 first_free_entry_index;
+	/* Incremented by VPU every time the VPU overwrites the 0th entry;
+	 * initialised by host to 0.
+	 */
+	u32 wraparound_count;
+	/*
+	 * This is the number of buffers that can be stored in the log buffer provided by the host.
+	 * It is written by host before passing buffer to VPU. VPU should consider it read-only.
+	 */
+	u64 num_of_entries;
+	u64 reserved[2];
+};
+
+/*
+ * HWS specific log buffer entry details.
+ * Total size is 32 bytes.
+ */
+struct vpu_hws_log_buffer_entry {
+	/* VPU timestamp must be an invariant timer tick (not impacted by DVFS) */
+	u64 vpu_timestamp;
+	/*
+	 * Operation type:
+	 *     0 - context state change
+	 *     1 - queue new work
+	 *     2 - queue unwait sync object
+	 *     3 - queue no more work
+	 *     4 - queue wait sync object
+	 */
+	u32 operation_type;
+	u32 reserved;
+	/* Operation data depends on operation type */
+	u64 operation_data[2];
+};
+
 /*
  * Host <-> VPU IPC messages types.
  */
@@ -228,6 +290,23 @@ enum vpu_ipc_msg_type {
 	 * deallocated or reassigned to another context.
 	 */
 	VPU_JSM_MSG_HWS_REGISTER_DB = 0x1117,
+	/** Control command: Log buffer setting */
+	VPU_JSM_MSG_HWS_SET_SCHEDULING_LOG = 0x1118,
+	/* Control command: Suspend command queue. */
+	VPU_JSM_MSG_HWS_SUSPEND_CMDQ = 0x1119,
+	/* Control command: Resume command queue */
+	VPU_JSM_MSG_HWS_RESUME_CMDQ = 0x111a,
+	/* Control command: Resume engine after reset */
+	VPU_JSM_MSG_HWS_ENGINE_RESUME = 0x111b,
+	/* Control command: Enable survivability/DCT mode */
+	VPU_JSM_MSG_DCT_ENABLE = 0x111c,
+	/* Control command: Disable survivability/DCT mode */
+	VPU_JSM_MSG_DCT_DISABLE = 0x111d,
+	/**
+	 * Dump VPU state. To be used for debug purposes only.
+	 * NOTE: Please introduce new ASYNC commands before this one. *
+	 */
+	VPU_JSM_MSG_STATE_DUMP = 0x11FF,
 	/* IPC Host -> Device, General commands */
 	VPU_JSM_MSG_GENERAL_CMD = 0x1200,
 	VPU_JSM_MSG_BLOB_DEINIT = VPU_JSM_MSG_GENERAL_CMD,
@@ -236,6 +315,10 @@ enum vpu_ipc_msg_type {
 	 * Linux command: `echo '<dyndbg_cmd>' > <debugfs>/dynamic_debug/control`.
 	 */
 	VPU_JSM_MSG_DYNDBG_CONTROL = 0x1201,
+	/**
+	 * Perform the save procedure for the D0i3 entry
+	 */
+	VPU_JSM_MSG_PWR_D0I3_ENTER = 0x1202,
 	/* IPC Device -> Host, Job completion */
 	VPU_JSM_MSG_JOB_DONE = 0x2100,
 	/* IPC Device -> Host, Async command completion */
@@ -304,11 +387,35 @@ enum vpu_ipc_msg_type {
 	VPU_JSM_MSG_DESTROY_CMD_QUEUE_RSP = 0x2216,
 	/** Response to control command: Set context scheduling properties */
 	VPU_JSM_MSG_SET_CONTEXT_SCHED_PROPERTIES_RSP = 0x2217,
+	/** Response to control command: Log buffer setting */
+	VPU_JSM_MSG_HWS_SET_SCHEDULING_LOG_RSP = 0x2218,
+	/* IPC Device -> Host, HWS notify index entry of log buffer written */
+	VPU_JSM_MSG_HWS_SCHEDULING_LOG_NOTIFICATION = 0x2219,
+	/* IPC Device -> Host, HWS completion of a context suspend request */
+	VPU_JSM_MSG_HWS_SUSPEND_CMDQ_DONE = 0x221a,
+	/* Response to control command: Resume command queue */
+	VPU_JSM_MSG_HWS_RESUME_CMDQ_RSP = 0x221b,
+	/* Response to control command: Resume engine command response */
+	VPU_JSM_MSG_HWS_RESUME_ENGINE_DONE = 0x221c,
+	/* Response to control command: Enable survivability/DCT mode */
+	VPU_JSM_MSG_DCT_ENABLE_DONE = 0x221d,
+	/* Response to control command: Disable survivability/DCT mode */
+	VPU_JSM_MSG_DCT_DISABLE_DONE = 0x221e,
+	/**
+	 * Response to state dump control command.
+	 * NOTE: Please introduce new ASYNC responses before this one. *
+	 */
+	VPU_JSM_MSG_STATE_DUMP_RSP = 0x22FF,
 	/* IPC Device -> Host, General command completion */
 	VPU_JSM_MSG_GENERAL_CMD_DONE = 0x2300,
 	VPU_JSM_MSG_BLOB_DEINIT_DONE = VPU_JSM_MSG_GENERAL_CMD_DONE,
 	/** Response to VPU_JSM_MSG_DYNDBG_CONTROL. */
 	VPU_JSM_MSG_DYNDBG_CONTROL_RSP = 0x2301,
+	/**
+	 * Acknowledgment of completion of the save procedure initiated by
+	 * VPU_JSM_MSG_PWR_D0I3_ENTER
+	 */
+	VPU_JSM_MSG_PWR_D0I3_ENTER_DONE = 0x2302,
 };
 
 enum vpu_ipc_msg_status { VPU_JSM_MSG_FREE, VPU_JSM_MSG_ALLOCATED };
@@ -593,12 +700,12 @@ struct vpu_ipc_msg_payload_hws_priority_band_setup {
 	 * Default quantum in 100ns units for scheduling across processes
 	 * within a priority band
 	 */
-	u64 process_quantum[VPU_HWS_NUM_PRIORITY_BANDS];
+	u32 process_quantum[VPU_HWS_NUM_PRIORITY_BANDS];
 	/*
 	 * Default grace period in 100ns units for processes that preempt each
 	 * other within a priority band
 	 */
-	u64 process_grace_period[VPU_HWS_NUM_PRIORITY_BANDS];
+	u32 process_grace_period[VPU_HWS_NUM_PRIORITY_BANDS];
 	/*
 	 * For normal priority band, specifies the target VPU percentage
 	 * in situations when it's starved by the focus band.
@@ -608,32 +715,51 @@ struct vpu_ipc_msg_payload_hws_priority_band_setup {
 	u32 reserved_0;
 };
 
-/* HWS create command queue request */
+/*
+ * @brief HWS create command queue request.
+ * Host will create a command queue via this command.
+ * Note: Cmdq group is a handle of an object which
+ * may contain one or more command queues.
+ * @see VPU_JSM_MSG_CREATE_CMD_QUEUE
+ * @see VPU_JSM_MSG_CREATE_CMD_QUEUE_RSP
+ */
 struct vpu_ipc_msg_payload_hws_create_cmdq {
 	/* Process id */
 	u64 process_id;
 	/* Host SSID */
 	u32 host_ssid;
-	/* Zero Padding */
-	u32 reserved;
+	/* Engine for which queue is being created */
+	u32 engine_idx;
+	/*
+	 * Cmdq group may be set to 0 or equal to
+	 * cmdq_id while each priority band contains
+	 * only single engine instances.
+	 */
+	u64 cmdq_group;
 	/* Command queue id */
 	u64 cmdq_id;
 	/* Command queue base */
 	u64 cmdq_base;
 	/* Command queue size */
 	u32 cmdq_size;
-	/* Reserved */
+	/* Zero padding */
 	u32 reserved_0;
 };
 
-/* HWS create command queue response */
+/*
+ * @brief HWS create command queue response.
+ * @see VPU_JSM_MSG_CREATE_CMD_QUEUE
+ * @see VPU_JSM_MSG_CREATE_CMD_QUEUE_RSP
+ */
 struct vpu_ipc_msg_payload_hws_create_cmdq_rsp {
 	/* Process id */
 	u64 process_id;
 	/* Host SSID */
 	u32 host_ssid;
-	/* Zero Padding */
-	u32 reserved;
+	/* Engine for which queue is being created */
+	u32 engine_idx;
+	/* Command queue group */
+	u64 cmdq_group;
 	/* Command queue id */
 	u64 cmdq_id;
 };
@@ -661,7 +787,7 @@ struct vpu_ipc_msg_payload_hws_set_context_sched_properties {
 	/* Inside realtime band assigns a further priority */
 	u32 realtime_priority_level;
 	/* Priority relative to other contexts in the same process */
-	u32 in_process_priority;
+	s32 in_process_priority;
 	/* Zero padding / Reserved */
 	u32 reserved_1;
 	/* Context quantum relative to other contexts of same priority in the same process */
@@ -694,6 +820,123 @@ struct vpu_jsm_hws_register_db {
 	u64 cmdq_size;
 };
 
+/*
+ * @brief Structure to set another buffer to be used for scheduling-related logging.
+ * The size of the logging buffer and the number of entries is defined as part of the
+ * buffer itself as described next.
+ * The log buffer received from the host is made up of;
+ *   - header:     32 bytes in size, as shown in 'struct vpu_hws_log_buffer_header'.
+ *                 The header contains the number of log entries in the buffer.
+ *   - log entry:  0 to n-1, each log entry is 32 bytes in size, as shown in
+ *                 'struct vpu_hws_log_buffer_entry'.
+ *                 The entry contains the VPU timestamp, operation type and data.
+ * The host should provide the notify index value of log buffer to VPU. This is a
+ * value defined within the log buffer and when written to will generate the
+ * scheduling log notification.
+ * The host should set engine_idx and vpu_log_buffer_va to 0 to disable logging
+ * for a particular engine.
+ * VPU will handle one log buffer for each of supported engines.
+ * VPU should allow the logging to consume one host_ssid.
+ * @see VPU_JSM_MSG_HWS_SET_SCHEDULING_LOG
+ * @see VPU_JSM_MSG_HWS_SET_SCHEDULING_LOG_RSP
+ * @see VPU_JSM_MSG_HWS_SCHEDULING_LOG_NOTIFICATION
+ */
+struct vpu_ipc_msg_payload_hws_set_scheduling_log {
+	/* Engine ordinal */
+	u32 engine_idx;
+	/* Host SSID */
+	u32 host_ssid;
+	/*
+	 * VPU log buffer virtual address.
+	 * Set to 0 to disable logging for this engine.
+	 */
+	u64 vpu_log_buffer_va;
+	/*
+	 * Notify index of log buffer. VPU_JSM_MSG_HWS_SCHEDULING_LOG_NOTIFICATION
+	 * is generated when an event log is written to this index.
+	 */
+	u64 notify_index;
+};
+
+/*
+ * @brief The scheduling log notification is generated by VPU when it writes
+ * an event into the log buffer at the notify_index. VPU notifies host with
+ * VPU_JSM_MSG_HWS_SCHEDULING_LOG_NOTIFICATION. This is an asynchronous
+ * message from VPU to host.
+ * @see VPU_JSM_MSG_HWS_SCHEDULING_LOG_NOTIFICATION
+ * @see VPU_JSM_MSG_HWS_SET_SCHEDULING_LOG
+ */
+struct vpu_ipc_msg_payload_hws_scheduling_log_notification {
+	/* Engine ordinal */
+	u32 engine_idx;
+	/* Zero Padding */
+	u32 reserved_0;
+};
+
+/*
+ * @brief HWS suspend command queue request and done structure.
+ * Host will request the suspend of contexts and VPU will;
+ *   - Suspend all work on this context
+ *   - Preempt any running work
+ *   - Asynchronously perform the above and return success immediately once
+ *     all items above are started successfully
+ *   - Notify the host of completion of these operations via
+ *     VPU_JSM_MSG_HWS_SUSPEND_CMDQ_DONE
+ *   - Reject any other context operations on a context with an in-flight
+ *     suspend request running
+ * Same structure used when VPU notifies host of completion of a context suspend
+ * request. The ids and suspend fence value reported in this command will match
+ * the one in the request from the host to suspend the context. Once suspend is
+ * complete, VPU will not access any data relating to this command queue until
+ * it is resumed.
+ * @see VPU_JSM_MSG_HWS_SUSPEND_CMDQ
+ * @see VPU_JSM_MSG_HWS_SUSPEND_CMDQ_DONE
+ */
+struct vpu_ipc_msg_payload_hws_suspend_cmdq {
+	/* Host SSID */
+	u32 host_ssid;
+	/* Zero Padding */
+	u32 reserved_0;
+	/* Command queue id */
+	u64 cmdq_id;
+	/*
+	 * Suspend fence value - reported by the VPU suspend context
+	 * completed once suspend is complete.
+	 */
+	u64 suspend_fence_value;
+};
+
+/*
+ * @brief HWS Resume command queue request / response structure.
+ * Host will request the resume of a context;
+ *  - VPU will resume all work on this context
+ *  - Scheduler will allow this context to be scheduled
+ * @see VPU_JSM_MSG_HWS_RESUME_CMDQ
+ * @see VPU_JSM_MSG_HWS_RESUME_CMDQ_RSP
+ */
+struct vpu_ipc_msg_payload_hws_resume_cmdq {
+	/* Host SSID */
+	u32 host_ssid;
+	/* Zero Padding */
+	u32 reserved_0;
+	/* Command queue id */
+	u64 cmdq_id;
+};
+
+/*
+ * @brief HWS Resume engine request / response structure.
+ * After a HWS engine reset, all scheduling is stopped on VPU until a engine resume.
+ * Host shall send this command to resume scheduling of any valid queue.
+ * @see VPU_JSM_MSG_HWS_RESUME_ENGINE
+ * @see VPU_JSM_MSG_HWS_RESUME_ENGINE_DONE
+ */
+struct vpu_ipc_msg_payload_hws_resume_engine {
+	/* Engine to be resumed */
+	u32 engine_idx;
+	/* Reserved */
+	u32 reserved_0;
+};
+
 /**
  * Payload for VPU_JSM_MSG_TRACE_SET_CONFIG[_RSP] and
  * VPU_JSM_MSG_TRACE_GET_CONFIG_RSP messages.
@@ -938,6 +1181,35 @@ struct vpu_ipc_msg_payload_dyndbg_control {
 	char dyndbg_cmd[VPU_DYNDBG_CMD_MAX_LEN];
 };
 
+/**
+ * Payload for VPU_JSM_MSG_PWR_D0I3_ENTER
+ *
+ * This is a bi-directional payload.
+ */
+struct vpu_ipc_msg_payload_pwr_d0i3_enter {
+	/**
+	 * 0: VPU_JSM_MSG_PWR_D0I3_ENTER_DONE is not sent to the host driver
+	 *    The driver will poll for D0i2 Idle state transitions.
+	 * 1: VPU_JSM_MSG_PWR_D0I3_ENTER_DONE is sent after VPU state save is complete
+	 */
+	u32 send_response;
+	u32 reserved_0;
+};
+
+/**
+ * Payload for VPU_JSM_MSG_DCT_ENABLE message.
+ *
+ * Default values for DCT active/inactive times are 5.3ms and 30ms respectively,
+ * corresponding to a 85% duty cycle. This payload allows the host to tune these
+ * values according to application requirements.
+ */
+struct vpu_ipc_msg_payload_pwr_dct_control {
+	/** Duty cycle active time in microseconds */
+	u32 dct_active_us;
+	/** Duty cycle inactive time in microseconds */
+	u32 dct_inactive_us;
+};
+
 /*
  * Payloads union, used to define complete message format.
  */
@@ -974,6 +1246,13 @@ union vpu_ipc_msg_payload {
 	struct vpu_ipc_msg_payload_hws_destroy_cmdq hws_destroy_cmdq;
 	struct vpu_ipc_msg_payload_hws_set_context_sched_properties
 		hws_set_context_sched_properties;
+	struct vpu_ipc_msg_payload_hws_set_scheduling_log hws_set_scheduling_log;
+	struct vpu_ipc_msg_payload_hws_scheduling_log_notification hws_scheduling_log_notification;
+	struct vpu_ipc_msg_payload_hws_suspend_cmdq hws_suspend_cmdq;
+	struct vpu_ipc_msg_payload_hws_resume_cmdq hws_resume_cmdq;
+	struct vpu_ipc_msg_payload_hws_resume_engine hws_resume_engine;
+	struct vpu_ipc_msg_payload_pwr_d0i3_enter pwr_d0i3_enter;
+	struct vpu_ipc_msg_payload_pwr_dct_control pwr_dct_control;
 };
 
 /*
-- 
cgit 


From 9692b1dcefe79ea47f7d5a94acff74303c6563c6 Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Date: Sat, 28 Oct 2023 15:34:06 +0200
Subject: accel/ivpu: Remove unneeded drm_driver declaration

Cleanup drm_driver declaration leftover.

Reviewed-by: Krystian Pradzynski <krystian.pradzynski@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231028133415.1169975-3-stanislaw.gruszka@linux.intel.com
---
 drivers/accel/ivpu/ivpu_drv.c | 2 --
 1 file changed, 2 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c
index b6aa8893ff1c..8f5655dfd83f 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -31,8 +31,6 @@
 			   __stringify(DRM_IVPU_DRIVER_MINOR) "."
 #endif
 
-static const struct drm_driver driver;
-
 static struct lock_class_key submitted_jobs_xa_lock_class_key;
 
 int ivpu_dbg_mask;
-- 
cgit 


From f13108fc7bae7085616805ed176b2114cdf4bd55 Mon Sep 17 00:00:00 2001
From: Tomasz Rusinowicz <tomasz.rusinowicz@intel.com>
Date: Sat, 28 Oct 2023 15:34:07 +0200
Subject: accel/ivpu: Add dvfs_mode file to debugfs

Add new debugfs file to set dvfs_mode FW boot parameter and restart
the FW to allow experimenting with DVFS (dynamic voltage & frequency
scaling).

Signed-off-by: Tomasz Rusinowicz <tomasz.rusinowicz@intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231028133415.1169975-4-stanislaw.gruszka@linux.intel.com
---
 drivers/accel/ivpu/ivpu_debugfs.c | 28 ++++++++++++++++++++++++++++
 drivers/accel/ivpu/ivpu_fw.c      |  5 +++++
 drivers/accel/ivpu/ivpu_fw.h      |  1 +
 3 files changed, 34 insertions(+)

(limited to 'drivers/accel')

diff --git a/drivers/accel/ivpu/ivpu_debugfs.c b/drivers/accel/ivpu/ivpu_debugfs.c
index ea453b985b49..6e0d56823024 100644
--- a/drivers/accel/ivpu/ivpu_debugfs.c
+++ b/drivers/accel/ivpu/ivpu_debugfs.c
@@ -115,6 +115,31 @@ static const struct drm_debugfs_info vdev_debugfs_list[] = {
 	{"reset_pending", reset_pending_show, 0},
 };
 
+static ssize_t
+dvfs_mode_fops_write(struct file *file, const char __user *user_buf, size_t size, loff_t *pos)
+{
+	struct ivpu_device *vdev = file->private_data;
+	struct ivpu_fw_info *fw = vdev->fw;
+	u32 dvfs_mode;
+	int ret;
+
+	ret = kstrtou32_from_user(user_buf, size, 0, &dvfs_mode);
+	if (ret < 0)
+		return ret;
+
+	fw->dvfs_mode = dvfs_mode;
+
+	ivpu_pm_schedule_recovery(vdev);
+
+	return size;
+}
+
+static const struct file_operations dvfs_mode_fops = {
+	.owner = THIS_MODULE,
+	.open = simple_open,
+	.write = dvfs_mode_fops_write,
+};
+
 static int fw_log_show(struct seq_file *s, void *v)
 {
 	struct ivpu_device *vdev = s->private;
@@ -280,6 +305,9 @@ void ivpu_debugfs_init(struct ivpu_device *vdev)
 	debugfs_create_file("force_recovery", 0200, debugfs_root, vdev,
 			    &ivpu_force_recovery_fops);
 
+	debugfs_create_file("dvfs_mode", 0200, debugfs_root, vdev,
+			    &dvfs_mode_fops);
+
 	debugfs_create_file("fw_log", 0644, debugfs_root, vdev,
 			    &fw_log_fops);
 	debugfs_create_file("fw_trace_destination_mask", 0200, debugfs_root, vdev,
diff --git a/drivers/accel/ivpu/ivpu_fw.c b/drivers/accel/ivpu/ivpu_fw.c
index 6142b09cf55a..b81827540db9 100644
--- a/drivers/accel/ivpu/ivpu_fw.c
+++ b/drivers/accel/ivpu/ivpu_fw.c
@@ -182,6 +182,8 @@ static int ivpu_fw_parse(struct ivpu_device *vdev)
 	fw->trace_destination_mask = VPU_TRACE_DESTINATION_VERBOSE_TRACING;
 	fw->trace_hw_component_mask = -1;
 
+	fw->dvfs_mode = 0;
+
 	ivpu_dbg(vdev, FW_BOOT, "Size: file %lu image %u runtime %u shavenn %u\n",
 		 fw->file->size, fw->image_size, fw->runtime_size, fw->shave_nn_size);
 	ivpu_dbg(vdev, FW_BOOT, "Address: runtime 0x%llx, load 0x%llx, entry point 0x%llx\n",
@@ -422,6 +424,8 @@ static void ivpu_fw_boot_params_print(struct ivpu_device *vdev, struct vpu_boot_
 		 boot_params->punit_telemetry_sram_size);
 	ivpu_dbg(vdev, FW_BOOT, "boot_params.vpu_telemetry_enable = 0x%x\n",
 		 boot_params->vpu_telemetry_enable);
+	ivpu_dbg(vdev, FW_BOOT, "boot_params.dvfs_mode = %u\n",
+		 boot_params->dvfs_mode);
 }
 
 void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params *boot_params)
@@ -492,6 +496,7 @@ void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params
 	boot_params->punit_telemetry_sram_base = ivpu_hw_reg_telemetry_offset_get(vdev);
 	boot_params->punit_telemetry_sram_size = ivpu_hw_reg_telemetry_size_get(vdev);
 	boot_params->vpu_telemetry_enable = ivpu_hw_reg_telemetry_enable_get(vdev);
+	boot_params->dvfs_mode = vdev->fw->dvfs_mode;
 
 	wmb(); /* Flush WC buffers after writing bootparams */
 
diff --git a/drivers/accel/ivpu/ivpu_fw.h b/drivers/accel/ivpu/ivpu_fw.h
index 10ae2847f0ef..66b60fa161b5 100644
--- a/drivers/accel/ivpu/ivpu_fw.h
+++ b/drivers/accel/ivpu/ivpu_fw.h
@@ -27,6 +27,7 @@ struct ivpu_fw_info {
 	u32 trace_level;
 	u32 trace_destination_mask;
 	u64 trace_hw_component_mask;
+	u32 dvfs_mode;
 };
 
 int ivpu_fw_init(struct ivpu_device *vdev);
-- 
cgit 


From bacc130d4671a9568352b8d7606cfe7a50d38a56 Mon Sep 17 00:00:00 2001
From: Karol Wachowski <karol.wachowski@linux.intel.com>
Date: Sat, 28 Oct 2023 15:34:08 +0200
Subject: accel/ivpu: Remove reset from power up sequence

Setting a non-zero work point resets the IP hence IP_RESET
trigger is redundant.

Signed-off-by: Karol Wachowski <karol.wachowski@linux.intel.com>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231028133415.1169975-5-stanislaw.gruszka@linux.intel.com
---
 drivers/accel/ivpu/ivpu_hw_37xx.c | 4 ----
 drivers/accel/ivpu/ivpu_hw_40xx.c | 6 ------
 2 files changed, 10 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/ivpu/ivpu_hw_37xx.c b/drivers/accel/ivpu/ivpu_hw_37xx.c
index e5cb9d8acb82..8340c84ed6de 100644
--- a/drivers/accel/ivpu/ivpu_hw_37xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_37xx.c
@@ -651,10 +651,6 @@ static int ivpu_hw_37xx_power_up(struct ivpu_device *vdev)
 {
 	int ret;
 
-	ret = ivpu_hw_37xx_reset(vdev);
-	if (ret)
-		ivpu_warn(vdev, "Failed to reset HW: %d\n", ret);
-
 	ret = ivpu_hw_37xx_d0i3_disable(vdev);
 	if (ret)
 		ivpu_warn(vdev, "Failed to disable D0I3: %d\n", ret);
diff --git a/drivers/accel/ivpu/ivpu_hw_40xx.c b/drivers/accel/ivpu/ivpu_hw_40xx.c
index 4bf4c8780044..eb8218d15f01 100644
--- a/drivers/accel/ivpu/ivpu_hw_40xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_40xx.c
@@ -811,12 +811,6 @@ static int ivpu_hw_40xx_power_up(struct ivpu_device *vdev)
 {
 	int ret;
 
-	ret = ivpu_hw_40xx_reset(vdev);
-	if (ret) {
-		ivpu_err(vdev, "Failed to reset HW: %d\n", ret);
-		return ret;
-	}
-
 	ret = ivpu_hw_40xx_d0i3_disable(vdev);
 	if (ret)
 		ivpu_warn(vdev, "Failed to disable D0I3: %d\n", ret);
-- 
cgit 


From 61ab485f0eb1e5b7e2be10ec657a054d36ef5035 Mon Sep 17 00:00:00 2001
From: Andrzej Kacprowski <andrzej.kacprowski@linux.intel.com>
Date: Sat, 28 Oct 2023 15:34:09 +0200
Subject: accel/ivpu: Add support for VPU_JOB_FLAGS_NULL_SUBMISSION_MASK

Add test_mode = 3 that add VPU_JOB_FLAGS_NULL_SUBMISSION_MASK
flag to the job send to the VPU device. Then the VPU will process
the job but won't execute commands (except the command to signal
the fence).

This can be used to estimate job processing overhead in the host
software and VPU firmware.

Unlike the null hardware mode, the null submission mode will
still work even if UMD uses VPU fences to track job completion.

Signed-off-by: Andrzej Kacprowski <andrzej.kacprowski@linux.intel.com>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231028133415.1169975-6-stanislaw.gruszka@linux.intel.com
---
 drivers/accel/ivpu/ivpu_drv.c | 2 +-
 drivers/accel/ivpu/ivpu_drv.h | 7 ++++---
 drivers/accel/ivpu/ivpu_job.c | 2 ++
 3 files changed, 7 insertions(+), 4 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c
index 8f5655dfd83f..4ec8d25a120c 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -39,7 +39,7 @@ MODULE_PARM_DESC(dbg_mask, "Driver debug mask. See IVPU_DBG_* macros.");
 
 int ivpu_test_mode;
 module_param_named_unsafe(test_mode, ivpu_test_mode, int, 0644);
-MODULE_PARM_DESC(test_mode, "Test mode: 0 - normal operation, 1 - fw unit test, 2 - null hw");
+MODULE_PARM_DESC(test_mode, "Test mode: 0 - disabled , 1 - fw unit test, 2 - null hw, 3 - null submission");
 
 u8 ivpu_pll_min_ratio;
 module_param_named(pll_min_ratio, ivpu_pll_min_ratio, byte, 0644);
diff --git a/drivers/accel/ivpu/ivpu_drv.h b/drivers/accel/ivpu/ivpu_drv.h
index 12a63f8a73e8..fdec8272da8c 100644
--- a/drivers/accel/ivpu/ivpu_drv.h
+++ b/drivers/accel/ivpu/ivpu_drv.h
@@ -147,9 +147,10 @@ extern u8 ivpu_pll_min_ratio;
 extern u8 ivpu_pll_max_ratio;
 extern bool ivpu_disable_mmu_cont_pages;
 
-#define IVPU_TEST_MODE_DISABLED  0
-#define IVPU_TEST_MODE_FW_TEST   1
-#define IVPU_TEST_MODE_NULL_HW   2
+#define IVPU_TEST_MODE_DISABLED        0
+#define IVPU_TEST_MODE_FW_TEST         1
+#define IVPU_TEST_MODE_NULL_HW         2
+#define IVPU_TEST_MODE_NULL_SUBMISSION 3
 extern int ivpu_test_mode;
 
 struct ivpu_file_priv *ivpu_file_priv_get(struct ivpu_file_priv *file_priv);
diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c
index 689dc0d13b8f..646b8f812901 100644
--- a/drivers/accel/ivpu/ivpu_job.c
+++ b/drivers/accel/ivpu/ivpu_job.c
@@ -196,6 +196,8 @@ static int ivpu_cmdq_push_job(struct ivpu_cmdq *cmdq, struct ivpu_job *job)
 	entry->batch_buf_addr = job->cmd_buf_vpu_addr;
 	entry->job_id = job->job_id;
 	entry->flags = 0;
+	if (unlikely(ivpu_test_mode == IVPU_TEST_MODE_NULL_SUBMISSION))
+		entry->flags = VPU_JOB_FLAGS_NULL_SUBMISSION_MASK;
 	wmb(); /* Ensure that tail is updated after filling entry */
 	header->tail = next_entry;
 	wmb(); /* Flush WC buffer for jobq header */
-- 
cgit 


From 8b5cec3c2ccf0b12121cb151560c2876219d87e5 Mon Sep 17 00:00:00 2001
From: Karol Wachowski <karol.wachowski@linux.intel.com>
Date: Sat, 28 Oct 2023 15:34:10 +0200
Subject: accel/ivpu: Change test_mode module param to bitmask

Change meaning of test_mode module parameter from integer value
to bitmask allowing setting different test features with corresponding
bits.

Signed-off-by: Karol Wachowski <karol.wachowski@linux.intel.com>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231028133415.1169975-7-stanislaw.gruszka@linux.intel.com
---
 drivers/accel/ivpu/ivpu_drv.c | 4 ++--
 drivers/accel/ivpu/ivpu_drv.h | 7 +++----
 drivers/accel/ivpu/ivpu_job.c | 4 ++--
 3 files changed, 7 insertions(+), 8 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c
index 4ec8d25a120c..39bac45d88b5 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -39,7 +39,7 @@ MODULE_PARM_DESC(dbg_mask, "Driver debug mask. See IVPU_DBG_* macros.");
 
 int ivpu_test_mode;
 module_param_named_unsafe(test_mode, ivpu_test_mode, int, 0644);
-MODULE_PARM_DESC(test_mode, "Test mode: 0 - disabled , 1 - fw unit test, 2 - null hw, 3 - null submission");
+MODULE_PARM_DESC(test_mode, "Test mode mask. See IVPU_TEST_MODE_* macros.");
 
 u8 ivpu_pll_min_ratio;
 module_param_named(pll_min_ratio, ivpu_pll_min_ratio, byte, 0644);
@@ -315,7 +315,7 @@ static int ivpu_wait_for_ready(struct ivpu_device *vdev)
 	unsigned long timeout;
 	int ret;
 
-	if (ivpu_test_mode == IVPU_TEST_MODE_FW_TEST)
+	if (ivpu_test_mode & IVPU_TEST_MODE_FW_TEST)
 		return 0;
 
 	ivpu_ipc_consumer_add(vdev, &cons, IVPU_IPC_CHAN_BOOT_MSG);
diff --git a/drivers/accel/ivpu/ivpu_drv.h b/drivers/accel/ivpu/ivpu_drv.h
index fdec8272da8c..ada43ba565c4 100644
--- a/drivers/accel/ivpu/ivpu_drv.h
+++ b/drivers/accel/ivpu/ivpu_drv.h
@@ -147,10 +147,9 @@ extern u8 ivpu_pll_min_ratio;
 extern u8 ivpu_pll_max_ratio;
 extern bool ivpu_disable_mmu_cont_pages;
 
-#define IVPU_TEST_MODE_DISABLED        0
-#define IVPU_TEST_MODE_FW_TEST         1
-#define IVPU_TEST_MODE_NULL_HW         2
-#define IVPU_TEST_MODE_NULL_SUBMISSION 3
+#define IVPU_TEST_MODE_FW_TEST         BIT(0)
+#define IVPU_TEST_MODE_NULL_HW         BIT(1)
+#define IVPU_TEST_MODE_NULL_SUBMISSION BIT(2)
 extern int ivpu_test_mode;
 
 struct ivpu_file_priv *ivpu_file_priv_get(struct ivpu_file_priv *file_priv);
diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c
index 646b8f812901..6e96c921547d 100644
--- a/drivers/accel/ivpu/ivpu_job.c
+++ b/drivers/accel/ivpu/ivpu_job.c
@@ -196,7 +196,7 @@ static int ivpu_cmdq_push_job(struct ivpu_cmdq *cmdq, struct ivpu_job *job)
 	entry->batch_buf_addr = job->cmd_buf_vpu_addr;
 	entry->job_id = job->job_id;
 	entry->flags = 0;
-	if (unlikely(ivpu_test_mode == IVPU_TEST_MODE_NULL_SUBMISSION))
+	if (unlikely(ivpu_test_mode & IVPU_TEST_MODE_NULL_SUBMISSION))
 		entry->flags = VPU_JOB_FLAGS_NULL_SUBMISSION_MASK;
 	wmb(); /* Ensure that tail is updated after filling entry */
 	header->tail = next_entry;
@@ -404,7 +404,7 @@ static int ivpu_direct_job_submission(struct ivpu_job *job)
 		 job->job_id, job->cmd_buf_vpu_addr, file_priv->ctx.id,
 		 job->engine_idx, cmdq->jobq->header.tail);
 
-	if (ivpu_test_mode == IVPU_TEST_MODE_NULL_HW) {
+	if (ivpu_test_mode & IVPU_TEST_MODE_NULL_HW) {
 		ivpu_job_done(vdev, job->job_id, VPU_JSM_STATUS_SUCCESS);
 		cmdq->jobq->header.head = cmdq->jobq->header.tail;
 		wmb(); /* Flush WC buffer for jobq header */
-- 
cgit 


From db37a5bfe97588992c75c29c1f0e19c88d364ce5 Mon Sep 17 00:00:00 2001
From: Andrzej Kacprowski <andrzej.kacprowski@linux.intel.com>
Date: Sat, 28 Oct 2023 15:34:11 +0200
Subject: accel/ivpu/40xx: Capture D0i3 entry host and device timestamps

The driver needs to capture the D0i3 entry timestamp to
calculate D0i3 residency time.

The D0i3 residency time and the VPU timestamp are passed
to the firmware at D0i3 exit (warm boot).

Signed-off-by: Andrzej Kacprowski <andrzej.kacprowski@linux.intel.com>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231028133415.1169975-8-stanislaw.gruszka@linux.intel.com
---
 drivers/accel/ivpu/ivpu_hw_40xx.c | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'drivers/accel')

diff --git a/drivers/accel/ivpu/ivpu_hw_40xx.c b/drivers/accel/ivpu/ivpu_hw_40xx.c
index eb8218d15f01..0eb9c827f6dc 100644
--- a/drivers/accel/ivpu/ivpu_hw_40xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_40xx.c
@@ -879,10 +879,18 @@ static bool ivpu_hw_40xx_is_idle(struct ivpu_device *vdev)
 	       REG_TEST_FLD(VPU_40XX_BUTTRESS_VPU_STATUS, IDLE, val);
 }
 
+static void ivpu_hw_40xx_save_d0i3_entry_timestamp(struct ivpu_device *vdev)
+{
+	vdev->hw->d0i3_entry_host_ts = ktime_get_boottime();
+	vdev->hw->d0i3_entry_vpu_ts = REGV_RD64(VPU_40XX_CPU_SS_TIM_PERF_EXT_FREE_CNT);
+}
+
 static int ivpu_hw_40xx_power_down(struct ivpu_device *vdev)
 {
 	int ret = 0;
 
+	ivpu_hw_40xx_save_d0i3_entry_timestamp(vdev);
+
 	if (!ivpu_hw_40xx_is_idle(vdev) && ivpu_hw_40xx_reset(vdev))
 		ivpu_warn(vdev, "Failed to reset the VPU\n");
 
-- 
cgit 


From 3de6d9597892ef899d7e90f589e23c9298013134 Mon Sep 17 00:00:00 2001
From: Andrzej Kacprowski <andrzej.kacprowski@linux.intel.com>
Date: Sat, 28 Oct 2023 15:34:12 +0200
Subject: accel/ivpu: Pass D0i3 residency time to the VPU firmware

The firmware needs to know the time spent in D0i3/D3 to
calculate telemetry data. The D0i3/D3 residency time is
calculated by the driver and passed to the firmware
in the boot parameters.

The driver also passes VPU perf counter value captured
right before entering D0i3 - this allows the VPU firmware
to generate monotonic timestamps for the logs.

Signed-off-by: Andrzej Kacprowski <andrzej.kacprowski@linux.intel.com>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231028133415.1169975-9-stanislaw.gruszka@linux.intel.com
---
 drivers/accel/ivpu/ivpu_fw.c          | 17 ++++++++++++++++-
 drivers/accel/ivpu/ivpu_hw.h          |  2 ++
 drivers/accel/ivpu/ivpu_hw_37xx.c     |  8 ++++++++
 drivers/accel/ivpu/ivpu_hw_37xx_reg.h |  2 ++
 4 files changed, 28 insertions(+), 1 deletion(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/ivpu/ivpu_fw.c b/drivers/accel/ivpu/ivpu_fw.c
index b81827540db9..383e4d9b97c8 100644
--- a/drivers/accel/ivpu/ivpu_fw.c
+++ b/drivers/accel/ivpu/ivpu_fw.c
@@ -426,14 +426,27 @@ static void ivpu_fw_boot_params_print(struct ivpu_device *vdev, struct vpu_boot_
 		 boot_params->vpu_telemetry_enable);
 	ivpu_dbg(vdev, FW_BOOT, "boot_params.dvfs_mode = %u\n",
 		 boot_params->dvfs_mode);
+	ivpu_dbg(vdev, FW_BOOT, "boot_params.d0i3_residency_time_us = %lld\n",
+		 boot_params->d0i3_residency_time_us);
+	ivpu_dbg(vdev, FW_BOOT, "boot_params.d0i3_entry_vpu_ts = %llu\n",
+		 boot_params->d0i3_entry_vpu_ts);
 }
 
 void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params *boot_params)
 {
 	struct ivpu_bo *ipc_mem_rx = vdev->ipc->mem_rx;
 
-	/* In case of warm boot we only have to reset the entrypoint addr */
+	/* In case of warm boot only update variable params */
 	if (!ivpu_fw_is_cold_boot(vdev)) {
+		boot_params->d0i3_residency_time_us =
+			ktime_us_delta(ktime_get_boottime(), vdev->hw->d0i3_entry_host_ts);
+		boot_params->d0i3_entry_vpu_ts = vdev->hw->d0i3_entry_vpu_ts;
+
+		ivpu_dbg(vdev, FW_BOOT, "boot_params.d0i3_residency_time_us = %lld\n",
+			 boot_params->d0i3_residency_time_us);
+		ivpu_dbg(vdev, FW_BOOT, "boot_params.d0i3_entry_vpu_ts = %llu\n",
+			 boot_params->d0i3_entry_vpu_ts);
+
 		boot_params->save_restore_ret_address = 0;
 		vdev->pm->is_warmboot = true;
 		return;
@@ -497,6 +510,8 @@ void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params
 	boot_params->punit_telemetry_sram_size = ivpu_hw_reg_telemetry_size_get(vdev);
 	boot_params->vpu_telemetry_enable = ivpu_hw_reg_telemetry_enable_get(vdev);
 	boot_params->dvfs_mode = vdev->fw->dvfs_mode;
+	boot_params->d0i3_residency_time_us = 0;
+	boot_params->d0i3_entry_vpu_ts = 0;
 
 	wmb(); /* Flush WC buffers after writing bootparams */
 
diff --git a/drivers/accel/ivpu/ivpu_hw.h b/drivers/accel/ivpu/ivpu_hw.h
index ab341237bcf9..fd4809b56168 100644
--- a/drivers/accel/ivpu/ivpu_hw.h
+++ b/drivers/accel/ivpu/ivpu_hw.h
@@ -57,6 +57,8 @@ struct ivpu_hw_info {
 	u32 sku;
 	u16 config;
 	int dma_bits;
+	ktime_t d0i3_entry_host_ts;
+	u64 d0i3_entry_vpu_ts;
 };
 
 extern const struct ivpu_hw_ops ivpu_hw_37xx_ops;
diff --git a/drivers/accel/ivpu/ivpu_hw_37xx.c b/drivers/accel/ivpu/ivpu_hw_37xx.c
index 8340c84ed6de..451c9777b237 100644
--- a/drivers/accel/ivpu/ivpu_hw_37xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_37xx.c
@@ -714,10 +714,18 @@ static bool ivpu_hw_37xx_is_idle(struct ivpu_device *vdev)
 	       REG_TEST_FLD(VPU_37XX_BUTTRESS_VPU_STATUS, IDLE, val);
 }
 
+static void ivpu_hw_37xx_save_d0i3_entry_timestamp(struct ivpu_device *vdev)
+{
+	vdev->hw->d0i3_entry_host_ts = ktime_get_boottime();
+	vdev->hw->d0i3_entry_vpu_ts = REGV_RD64(VPU_37XX_CPU_SS_TIM_PERF_FREE_CNT);
+}
+
 static int ivpu_hw_37xx_power_down(struct ivpu_device *vdev)
 {
 	int ret = 0;
 
+	ivpu_hw_37xx_save_d0i3_entry_timestamp(vdev);
+
 	if (!ivpu_hw_37xx_is_idle(vdev) && ivpu_hw_37xx_reset(vdev))
 		ivpu_err(vdev, "Failed to reset the VPU\n");
 
diff --git a/drivers/accel/ivpu/ivpu_hw_37xx_reg.h b/drivers/accel/ivpu/ivpu_hw_37xx_reg.h
index 4083beb5e9db..f6fec1919202 100644
--- a/drivers/accel/ivpu/ivpu_hw_37xx_reg.h
+++ b/drivers/accel/ivpu/ivpu_hw_37xx_reg.h
@@ -240,6 +240,8 @@
 #define VPU_37XX_CPU_SS_TIM_GEN_CONFIG					0x06021008u
 #define VPU_37XX_CPU_SS_TIM_GEN_CONFIG_WDOG_TO_INT_CLR_MASK		BIT_MASK(9)
 
+#define VPU_37XX_CPU_SS_TIM_PERF_FREE_CNT				0x06029000u
+
 #define VPU_37XX_CPU_SS_DOORBELL_0					0x06300000u
 #define VPU_37XX_CPU_SS_DOORBELL_0_SET_MASK				BIT_MASK(0)
 
-- 
cgit 


From 45e45362e0955fc3b0b622e8a0d788097f3de902 Mon Sep 17 00:00:00 2001
From: Karol Wachowski <karol.wachowski@linux.intel.com>
Date: Sat, 28 Oct 2023 15:34:13 +0200
Subject: accel/ivpu: Introduce ivpu_ipc_send_receive_active()

Split ivpu_ipc_send_receive() implementation to have a version
that does not call pm_runtime_resume_and_get(). That implementation
can be invoked when device is up and runtime resume is prohibited
(for example at the end of boot sequence).

The new function will be used for D0i3 entry IPC message addition
in the separate change.

Signed-off-by: Karol Wachowski <karol.wachowski@linux.intel.com>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231028133415.1169975-10-stanislaw.gruszka@linux.intel.com
---
 drivers/accel/ivpu/ivpu_ipc.c | 33 ++++++++++++++++++++++-----------
 drivers/accel/ivpu/ivpu_ipc.h |  8 +++++---
 2 files changed, 27 insertions(+), 14 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/ivpu/ivpu_ipc.c b/drivers/accel/ivpu/ivpu_ipc.c
index 6e213a5afb8c..d069d1e1f91d 100644
--- a/drivers/accel/ivpu/ivpu_ipc.c
+++ b/drivers/accel/ivpu/ivpu_ipc.c
@@ -288,23 +288,20 @@ consumer_del:
 	return ret;
 }
 
-int ivpu_ipc_send_receive(struct ivpu_device *vdev, struct vpu_jsm_msg *req,
-			  enum vpu_ipc_msg_type expected_resp_type,
-			  struct vpu_jsm_msg *resp, u32 channel,
-			  unsigned long timeout_ms)
+int ivpu_ipc_send_receive_active(struct ivpu_device *vdev, struct vpu_jsm_msg *req,
+				 enum vpu_ipc_msg_type expected_resp, struct vpu_jsm_msg *resp,
+				 u32 channel, unsigned long timeout_ms)
 {
 	struct vpu_jsm_msg hb_req = { .type = VPU_JSM_MSG_QUERY_ENGINE_HB };
 	struct vpu_jsm_msg hb_resp;
 	int ret, hb_ret;
 
-	ret = ivpu_rpm_get(vdev);
-	if (ret < 0)
-		return ret;
+	drm_WARN_ON(&vdev->drm,
+		    vdev->drm.dev->power.runtime_status == RPM_SUSPENDED);
 
-	ret = ivpu_ipc_send_receive_internal(vdev, req, expected_resp_type, resp,
-					     channel, timeout_ms);
+	ret = ivpu_ipc_send_receive_internal(vdev, req, expected_resp, resp, channel, timeout_ms);
 	if (ret != -ETIMEDOUT)
-		goto rpm_put;
+		return ret;
 
 	hb_ret = ivpu_ipc_send_receive_internal(vdev, &hb_req, VPU_JSM_MSG_QUERY_ENGINE_HB_DONE,
 						&hb_resp, VPU_IPC_CHAN_ASYNC_CMD,
@@ -314,7 +311,21 @@ int ivpu_ipc_send_receive(struct ivpu_device *vdev, struct vpu_jsm_msg *req,
 		ivpu_pm_schedule_recovery(vdev);
 	}
 
-rpm_put:
+	return ret;
+}
+
+int ivpu_ipc_send_receive(struct ivpu_device *vdev, struct vpu_jsm_msg *req,
+			  enum vpu_ipc_msg_type expected_resp, struct vpu_jsm_msg *resp,
+			  u32 channel, unsigned long timeout_ms)
+{
+	int ret;
+
+	ret = ivpu_rpm_get(vdev);
+	if (ret < 0)
+		return ret;
+
+	ret = ivpu_ipc_send_receive_active(vdev, req, expected_resp, resp, channel, timeout_ms);
+
 	ivpu_rpm_put(vdev);
 	return ret;
 }
diff --git a/drivers/accel/ivpu/ivpu_ipc.h b/drivers/accel/ivpu/ivpu_ipc.h
index 68f5b6668e00..6918db23daa4 100644
--- a/drivers/accel/ivpu/ivpu_ipc.h
+++ b/drivers/accel/ivpu/ivpu_ipc.h
@@ -85,9 +85,11 @@ int ivpu_ipc_receive(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
 		     struct ivpu_ipc_hdr *ipc_buf, struct vpu_jsm_msg *ipc_payload,
 		     unsigned long timeout_ms);
 
+int ivpu_ipc_send_receive_active(struct ivpu_device *vdev, struct vpu_jsm_msg *req,
+				 enum vpu_ipc_msg_type expected_resp, struct vpu_jsm_msg *resp,
+				 u32 channel, unsigned long timeout_ms);
 int ivpu_ipc_send_receive(struct ivpu_device *vdev, struct vpu_jsm_msg *req,
-			  enum vpu_ipc_msg_type expected_resp_type,
-			  struct vpu_jsm_msg *resp, u32 channel,
-			  unsigned long timeout_ms);
+			  enum vpu_ipc_msg_type expected_resp, struct vpu_jsm_msg *resp,
+			  u32 channel, unsigned long timeout_ms);
 
 #endif /* __IVPU_IPC_H__ */
-- 
cgit 


From cc19fedab8bdbe0f81d320ff9a6fdb3b5b01be83 Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Date: Sat, 28 Oct 2023 15:34:14 +0200
Subject: accel/ivpu/37xx: Print warning when VPUIP is not idle during power
 down

Print warning if VPUIP is not idle during power down.

Use warn log level also when we fail to enter reset state
as this is not really an error but unexpected behavior.

Reviewed-by: Krystian Pradzynski <krystian.pradzynski@linux.intel.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231028133415.1169975-11-stanislaw.gruszka@linux.intel.com
---
 drivers/accel/ivpu/ivpu_hw_37xx.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/ivpu/ivpu_hw_37xx.c b/drivers/accel/ivpu/ivpu_hw_37xx.c
index 451c9777b237..1b47d77b4c6e 100644
--- a/drivers/accel/ivpu/ivpu_hw_37xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_37xx.c
@@ -726,8 +726,11 @@ static int ivpu_hw_37xx_power_down(struct ivpu_device *vdev)
 
 	ivpu_hw_37xx_save_d0i3_entry_timestamp(vdev);
 
-	if (!ivpu_hw_37xx_is_idle(vdev) && ivpu_hw_37xx_reset(vdev))
-		ivpu_err(vdev, "Failed to reset the VPU\n");
+	if (!ivpu_hw_37xx_is_idle(vdev)) {
+		ivpu_warn(vdev, "VPU not idle during power down\n");
+		if (ivpu_hw_37xx_reset(vdev))
+			ivpu_warn(vdev, "Failed to reset the VPU\n");
+	}
 
 	if (ivpu_pll_disable(vdev)) {
 		ivpu_err(vdev, "Failed to disable PLL\n");
-- 
cgit 


From 3198a62eb8f8411b605501cb78c2298c67ecee91 Mon Sep 17 00:00:00 2001
From: Andrzej Kacprowski <andrzej.kacprowski@linux.intel.com>
Date: Sat, 28 Oct 2023 15:34:15 +0200
Subject: accel/ivpu: Add support for delayed D0i3 entry message

Currently the VPU firmware prepares for D0i3 every time the VPU
is entering D0i2 Idle state. This is not optimal as we might not
enter D0i3 every time we enter D0i2 Idle and this preparation
is quite costly.

This optimization moves D0i3 preparation to a dedicated
message sent from the host driver only when the driver is about
to enter D0i3 - this reduces power consumption and latency for
certain workloads, for example audio workloads that submit
inference every 10 ms.

The VPU needs non zero time to enter IDLE state after responding to
D0i3 entry message. If the driver does not wait for the VPU to enter
IDLE state it could cause warm boot failures.

Signed-off-by: Andrzej Kacprowski <andrzej.kacprowski@linux.intel.com>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231028133415.1169975-12-stanislaw.gruszka@linux.intel.com
---
 drivers/accel/ivpu/ivpu_drv.h     | 10 +++++---
 drivers/accel/ivpu/ivpu_fw.c      | 48 ++++++++++++++++++++++++++++++++++++---
 drivers/accel/ivpu/ivpu_hw.h      |  6 +++++
 drivers/accel/ivpu/ivpu_hw_37xx.c |  9 +++++++-
 drivers/accel/ivpu/ivpu_hw_40xx.c | 10 ++++++++
 drivers/accel/ivpu/ivpu_jsm_msg.c | 21 +++++++++++++++++
 drivers/accel/ivpu/ivpu_jsm_msg.h |  1 +
 drivers/accel/ivpu/ivpu_pm.c      | 11 ++++++++-
 8 files changed, 108 insertions(+), 8 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/ivpu/ivpu_drv.h b/drivers/accel/ivpu/ivpu_drv.h
index ada43ba565c4..1b482d1d66d9 100644
--- a/drivers/accel/ivpu/ivpu_drv.h
+++ b/drivers/accel/ivpu/ivpu_drv.h
@@ -87,6 +87,7 @@ struct ivpu_wa_table {
 	bool d3hot_after_power_off;
 	bool interrupt_clear_with_0;
 	bool disable_clock_relinquish;
+	bool disable_d0i3_msg;
 };
 
 struct ivpu_hw_info;
@@ -125,6 +126,7 @@ struct ivpu_device {
 		int tdr;
 		int reschedule_suspend;
 		int autosuspend;
+		int d0i3_entry_msg;
 	} timeout;
 };
 
@@ -147,9 +149,11 @@ extern u8 ivpu_pll_min_ratio;
 extern u8 ivpu_pll_max_ratio;
 extern bool ivpu_disable_mmu_cont_pages;
 
-#define IVPU_TEST_MODE_FW_TEST         BIT(0)
-#define IVPU_TEST_MODE_NULL_HW         BIT(1)
-#define IVPU_TEST_MODE_NULL_SUBMISSION BIT(2)
+#define IVPU_TEST_MODE_FW_TEST            BIT(0)
+#define IVPU_TEST_MODE_NULL_HW            BIT(1)
+#define IVPU_TEST_MODE_NULL_SUBMISSION    BIT(2)
+#define IVPU_TEST_MODE_D0I3_MSG_DISABLE   BIT(4)
+#define IVPU_TEST_MODE_D0I3_MSG_ENABLE    BIT(5)
 extern int ivpu_test_mode;
 
 struct ivpu_file_priv *ivpu_file_priv_get(struct ivpu_file_priv *file_priv);
diff --git a/drivers/accel/ivpu/ivpu_fw.c b/drivers/accel/ivpu/ivpu_fw.c
index 383e4d9b97c8..4a21be3a0c59 100644
--- a/drivers/accel/ivpu/ivpu_fw.c
+++ b/drivers/accel/ivpu/ivpu_fw.c
@@ -33,12 +33,17 @@
 
 #define ADDR_TO_L2_CACHE_CFG(addr) ((addr) >> 31)
 
-#define IVPU_FW_CHECK_API(vdev, fw_hdr, name, min_major) \
+/* Check if FW API is compatible with the driver */
+#define IVPU_FW_CHECK_API_COMPAT(vdev, fw_hdr, name, min_major) \
 	ivpu_fw_check_api(vdev, fw_hdr, #name, \
 			  VPU_##name##_API_VER_INDEX, \
 			  VPU_##name##_API_VER_MAJOR, \
 			  VPU_##name##_API_VER_MINOR, min_major)
 
+/* Check if API version is lower that the given version */
+#define IVPU_FW_CHECK_API_VER_LT(vdev, fw_hdr, name, major, minor) \
+	ivpu_fw_check_api_ver_lt(vdev, fw_hdr, #name, VPU_##name##_API_VER_INDEX, major, minor)
+
 static char *ivpu_firmware;
 module_param_named_unsafe(firmware, ivpu_firmware, charp, 0644);
 MODULE_PARM_DESC(firmware, "VPU firmware binary in /lib/firmware/..");
@@ -105,6 +110,19 @@ ivpu_fw_check_api(struct ivpu_device *vdev, const struct vpu_firmware_header *fw
 	return 0;
 }
 
+static bool
+ivpu_fw_check_api_ver_lt(struct ivpu_device *vdev, const struct vpu_firmware_header *fw_hdr,
+			 const char *str, int index, u16 major, u16 minor)
+{
+	u16 fw_major = (u16)(fw_hdr->api_version[index] >> 16);
+	u16 fw_minor = (u16)(fw_hdr->api_version[index]);
+
+	if (fw_major < major || (fw_major == major && fw_minor < minor))
+		return true;
+
+	return false;
+}
+
 static int ivpu_fw_parse(struct ivpu_device *vdev)
 {
 	struct ivpu_fw_info *fw = vdev->fw;
@@ -164,9 +182,9 @@ static int ivpu_fw_parse(struct ivpu_device *vdev)
 	ivpu_info(vdev, "Firmware: %s, version: %s", fw->name,
 		  (const char *)fw_hdr + VPU_FW_HEADER_SIZE);
 
-	if (IVPU_FW_CHECK_API(vdev, fw_hdr, BOOT, 3))
+	if (IVPU_FW_CHECK_API_COMPAT(vdev, fw_hdr, BOOT, 3))
 		return -EINVAL;
-	if (IVPU_FW_CHECK_API(vdev, fw_hdr, JSM, 3))
+	if (IVPU_FW_CHECK_API_COMPAT(vdev, fw_hdr, JSM, 3))
 		return -EINVAL;
 
 	fw->runtime_addr = runtime_addr;
@@ -197,6 +215,24 @@ static void ivpu_fw_release(struct ivpu_device *vdev)
 	release_firmware(vdev->fw->file);
 }
 
+/* Initialize workarounds that depend on FW version */
+static void
+ivpu_fw_init_wa(struct ivpu_device *vdev)
+{
+	const struct vpu_firmware_header *fw_hdr = (const void *)vdev->fw->file->data;
+
+	if (IVPU_FW_CHECK_API_VER_LT(vdev, fw_hdr, BOOT, 3, 17) ||
+	    (ivpu_hw_gen(vdev) > IVPU_HW_37XX) ||
+	    (ivpu_test_mode & IVPU_TEST_MODE_D0I3_MSG_DISABLE))
+		vdev->wa.disable_d0i3_msg = true;
+
+	/* Force enable the feature for testing purposes */
+	if (ivpu_test_mode & IVPU_TEST_MODE_D0I3_MSG_ENABLE)
+		vdev->wa.disable_d0i3_msg = false;
+
+	IVPU_PRINT_WA(disable_d0i3_msg);
+}
+
 static int ivpu_fw_update_global_range(struct ivpu_device *vdev)
 {
 	struct ivpu_fw_info *fw = vdev->fw;
@@ -299,6 +335,8 @@ int ivpu_fw_init(struct ivpu_device *vdev)
 	if (ret)
 		goto err_fw_release;
 
+	ivpu_fw_init_wa(vdev);
+
 	ret = ivpu_fw_mem_init(vdev);
 	if (ret)
 		goto err_fw_release;
@@ -426,6 +464,8 @@ static void ivpu_fw_boot_params_print(struct ivpu_device *vdev, struct vpu_boot_
 		 boot_params->vpu_telemetry_enable);
 	ivpu_dbg(vdev, FW_BOOT, "boot_params.dvfs_mode = %u\n",
 		 boot_params->dvfs_mode);
+	ivpu_dbg(vdev, FW_BOOT, "boot_params.d0i3_delayed_entry = %d\n",
+		 boot_params->d0i3_delayed_entry);
 	ivpu_dbg(vdev, FW_BOOT, "boot_params.d0i3_residency_time_us = %lld\n",
 		 boot_params->d0i3_residency_time_us);
 	ivpu_dbg(vdev, FW_BOOT, "boot_params.d0i3_entry_vpu_ts = %llu\n",
@@ -510,6 +550,8 @@ void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params
 	boot_params->punit_telemetry_sram_size = ivpu_hw_reg_telemetry_size_get(vdev);
 	boot_params->vpu_telemetry_enable = ivpu_hw_reg_telemetry_enable_get(vdev);
 	boot_params->dvfs_mode = vdev->fw->dvfs_mode;
+	if (!IVPU_WA(disable_d0i3_msg))
+		boot_params->d0i3_delayed_entry = 1;
 	boot_params->d0i3_residency_time_us = 0;
 	boot_params->d0i3_entry_vpu_ts = 0;
 
diff --git a/drivers/accel/ivpu/ivpu_hw.h b/drivers/accel/ivpu/ivpu_hw.h
index fd4809b56168..b7694b1cbc02 100644
--- a/drivers/accel/ivpu/ivpu_hw.h
+++ b/drivers/accel/ivpu/ivpu_hw.h
@@ -14,6 +14,7 @@ struct ivpu_hw_ops {
 	int (*boot_fw)(struct ivpu_device *vdev);
 	int (*power_down)(struct ivpu_device *vdev);
 	bool (*is_idle)(struct ivpu_device *vdev);
+	int (*wait_for_idle)(struct ivpu_device *vdev);
 	void (*wdt_disable)(struct ivpu_device *vdev);
 	void (*diagnose_failure)(struct ivpu_device *vdev);
 	u32 (*reg_pll_freq_get)(struct ivpu_device *vdev);
@@ -86,6 +87,11 @@ static inline bool ivpu_hw_is_idle(struct ivpu_device *vdev)
 	return vdev->hw->ops->is_idle(vdev);
 };
 
+static inline int ivpu_hw_wait_for_idle(struct ivpu_device *vdev)
+{
+	return vdev->hw->ops->wait_for_idle(vdev);
+};
+
 static inline int ivpu_hw_power_down(struct ivpu_device *vdev)
 {
 	ivpu_dbg(vdev, PM, "HW power down\n");
diff --git a/drivers/accel/ivpu/ivpu_hw_37xx.c b/drivers/accel/ivpu/ivpu_hw_37xx.c
index 1b47d77b4c6e..1c8c5715095b 100644
--- a/drivers/accel/ivpu/ivpu_hw_37xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_37xx.c
@@ -37,7 +37,7 @@
 #define TIMEOUT_US		     (150 * USEC_PER_MSEC)
 #define PWR_ISLAND_STATUS_TIMEOUT_US (5 * USEC_PER_MSEC)
 #define PLL_TIMEOUT_US		     (1500 * USEC_PER_MSEC)
-#define IDLE_TIMEOUT_US		     (500 * USEC_PER_MSEC)
+#define IDLE_TIMEOUT_US		     (5 * USEC_PER_MSEC)
 
 #define ICB_0_IRQ_MASK ((REG_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, HOST_IPC_FIFO_INT)) | \
 			(REG_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, MMU_IRQ_0_INT)) | \
@@ -90,6 +90,7 @@ static void ivpu_hw_timeouts_init(struct ivpu_device *vdev)
 	vdev->timeout.tdr = 2000;
 	vdev->timeout.reschedule_suspend = 10;
 	vdev->timeout.autosuspend = 10;
+	vdev->timeout.d0i3_entry_msg = 5;
 }
 
 static int ivpu_pll_wait_for_cmd_send(struct ivpu_device *vdev)
@@ -714,6 +715,11 @@ static bool ivpu_hw_37xx_is_idle(struct ivpu_device *vdev)
 	       REG_TEST_FLD(VPU_37XX_BUTTRESS_VPU_STATUS, IDLE, val);
 }
 
+static int ivpu_hw_37xx_wait_for_idle(struct ivpu_device *vdev)
+{
+	return REGB_POLL_FLD(VPU_37XX_BUTTRESS_VPU_STATUS, IDLE, 0x1, IDLE_TIMEOUT_US);
+}
+
 static void ivpu_hw_37xx_save_d0i3_entry_timestamp(struct ivpu_device *vdev)
 {
 	vdev->hw->d0i3_entry_host_ts = ktime_get_boottime();
@@ -1001,6 +1007,7 @@ const struct ivpu_hw_ops ivpu_hw_37xx_ops = {
 	.info_init = ivpu_hw_37xx_info_init,
 	.power_up = ivpu_hw_37xx_power_up,
 	.is_idle = ivpu_hw_37xx_is_idle,
+	.wait_for_idle = ivpu_hw_37xx_wait_for_idle,
 	.power_down = ivpu_hw_37xx_power_down,
 	.boot_fw = ivpu_hw_37xx_boot_fw,
 	.wdt_disable = ivpu_hw_37xx_wdt_disable,
diff --git a/drivers/accel/ivpu/ivpu_hw_40xx.c b/drivers/accel/ivpu/ivpu_hw_40xx.c
index 0eb9c827f6dc..6a9672f650d1 100644
--- a/drivers/accel/ivpu/ivpu_hw_40xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_40xx.c
@@ -39,6 +39,7 @@
 #define TIMEOUT_US		     (150 * USEC_PER_MSEC)
 #define PWR_ISLAND_STATUS_TIMEOUT_US (5 * USEC_PER_MSEC)
 #define PLL_TIMEOUT_US		     (1500 * USEC_PER_MSEC)
+#define IDLE_TIMEOUT_US		     (5 * USEC_PER_MSEC)
 
 #define WEIGHTS_DEFAULT              0xf711f711u
 #define WEIGHTS_ATS_DEFAULT          0x0000f711u
@@ -140,18 +141,21 @@ static void ivpu_hw_timeouts_init(struct ivpu_device *vdev)
 		vdev->timeout.tdr = 2000000;
 		vdev->timeout.reschedule_suspend = 1000;
 		vdev->timeout.autosuspend = -1;
+		vdev->timeout.d0i3_entry_msg = 500;
 	} else if (ivpu_is_simics(vdev)) {
 		vdev->timeout.boot = 50;
 		vdev->timeout.jsm = 500;
 		vdev->timeout.tdr = 10000;
 		vdev->timeout.reschedule_suspend = 10;
 		vdev->timeout.autosuspend = -1;
+		vdev->timeout.d0i3_entry_msg = 100;
 	} else {
 		vdev->timeout.boot = 1000;
 		vdev->timeout.jsm = 500;
 		vdev->timeout.tdr = 2000;
 		vdev->timeout.reschedule_suspend = 10;
 		vdev->timeout.autosuspend = 10;
+		vdev->timeout.d0i3_entry_msg = 5;
 	}
 }
 
@@ -879,6 +883,11 @@ static bool ivpu_hw_40xx_is_idle(struct ivpu_device *vdev)
 	       REG_TEST_FLD(VPU_40XX_BUTTRESS_VPU_STATUS, IDLE, val);
 }
 
+static int ivpu_hw_40xx_wait_for_idle(struct ivpu_device *vdev)
+{
+	return REGB_POLL_FLD(VPU_40XX_BUTTRESS_VPU_STATUS, IDLE, 0x1, IDLE_TIMEOUT_US);
+}
+
 static void ivpu_hw_40xx_save_d0i3_entry_timestamp(struct ivpu_device *vdev)
 {
 	vdev->hw->d0i3_entry_host_ts = ktime_get_boottime();
@@ -1168,6 +1177,7 @@ const struct ivpu_hw_ops ivpu_hw_40xx_ops = {
 	.info_init = ivpu_hw_40xx_info_init,
 	.power_up = ivpu_hw_40xx_power_up,
 	.is_idle = ivpu_hw_40xx_is_idle,
+	.wait_for_idle = ivpu_hw_40xx_wait_for_idle,
 	.power_down = ivpu_hw_40xx_power_down,
 	.boot_fw = ivpu_hw_40xx_boot_fw,
 	.wdt_disable = ivpu_hw_40xx_wdt_disable,
diff --git a/drivers/accel/ivpu/ivpu_jsm_msg.c b/drivers/accel/ivpu/ivpu_jsm_msg.c
index 35a689475c68..8cea0dd731b9 100644
--- a/drivers/accel/ivpu/ivpu_jsm_msg.c
+++ b/drivers/accel/ivpu/ivpu_jsm_msg.c
@@ -4,6 +4,7 @@
  */
 
 #include "ivpu_drv.h"
+#include "ivpu_hw.h"
 #include "ivpu_ipc.h"
 #include "ivpu_jsm_msg.h"
 
@@ -260,3 +261,23 @@ int ivpu_jsm_context_release(struct ivpu_device *vdev, u32 host_ssid)
 	return ivpu_ipc_send_receive(vdev, &req, VPU_JSM_MSG_SSID_RELEASE_DONE, &resp,
 				     VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm);
 }
+
+int ivpu_jsm_pwr_d0i3_enter(struct ivpu_device *vdev)
+{
+	struct vpu_jsm_msg req = { .type = VPU_JSM_MSG_PWR_D0I3_ENTER };
+	struct vpu_jsm_msg resp;
+	int ret;
+
+	if (IVPU_WA(disable_d0i3_msg))
+		return 0;
+
+	req.payload.pwr_d0i3_enter.send_response = 1;
+
+	ret = ivpu_ipc_send_receive_active(vdev, &req, VPU_JSM_MSG_PWR_D0I3_ENTER_DONE,
+					   &resp, VPU_IPC_CHAN_GEN_CMD,
+					   vdev->timeout.d0i3_entry_msg);
+	if (ret)
+		return ret;
+
+	return ivpu_hw_wait_for_idle(vdev);
+}
diff --git a/drivers/accel/ivpu/ivpu_jsm_msg.h b/drivers/accel/ivpu/ivpu_jsm_msg.h
index 66979a948c7c..ae75e5dbcc41 100644
--- a/drivers/accel/ivpu/ivpu_jsm_msg.h
+++ b/drivers/accel/ivpu/ivpu_jsm_msg.h
@@ -22,4 +22,5 @@ int ivpu_jsm_trace_get_capability(struct ivpu_device *vdev, u32 *trace_destinati
 int ivpu_jsm_trace_set_config(struct ivpu_device *vdev, u32 trace_level, u32 trace_destination_mask,
 			      u64 trace_hw_component_mask);
 int ivpu_jsm_context_release(struct ivpu_device *vdev, u32 host_ssid);
+int ivpu_jsm_pwr_d0i3_enter(struct ivpu_device *vdev);
 #endif
diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c
index 568e4295dc56..2d05fb9e3197 100644
--- a/drivers/accel/ivpu/ivpu_pm.c
+++ b/drivers/accel/ivpu/ivpu_pm.c
@@ -15,6 +15,7 @@
 #include "ivpu_fw.h"
 #include "ivpu_ipc.h"
 #include "ivpu_job.h"
+#include "ivpu_jsm_msg.h"
 #include "ivpu_mmu.h"
 #include "ivpu_pm.h"
 
@@ -153,6 +154,8 @@ int ivpu_pm_suspend_cb(struct device *dev)
 		}
 	}
 
+	ivpu_jsm_pwr_d0i3_enter(vdev);
+
 	ivpu_suspend(vdev);
 	ivpu_pm_prepare_warm_boot(vdev);
 
@@ -188,6 +191,7 @@ int ivpu_pm_runtime_suspend_cb(struct device *dev)
 {
 	struct drm_device *drm = dev_get_drvdata(dev);
 	struct ivpu_device *vdev = to_ivpu_device(drm);
+	bool hw_is_idle = true;
 	int ret;
 
 	ivpu_dbg(vdev, PM, "Runtime suspend..\n");
@@ -200,11 +204,16 @@ int ivpu_pm_runtime_suspend_cb(struct device *dev)
 		return -EAGAIN;
 	}
 
+	if (!vdev->pm->suspend_reschedule_counter)
+		hw_is_idle = false;
+	else if (ivpu_jsm_pwr_d0i3_enter(vdev))
+		hw_is_idle = false;
+
 	ret = ivpu_suspend(vdev);
 	if (ret)
 		ivpu_err(vdev, "Failed to set suspend VPU: %d\n", ret);
 
-	if (!vdev->pm->suspend_reschedule_counter) {
+	if (!hw_is_idle) {
 		ivpu_warn(vdev, "VPU failed to enter idle, force suspended.\n");
 		ivpu_pm_prepare_cold_boot(vdev);
 	} else {
-- 
cgit 


From bfc87f90614523612ae7e94d06798e82bc78ade6 Mon Sep 17 00:00:00 2001
From: Krystian Pradzynski <krystian.pradzynski@linux.intel.com>
Date: Sat, 28 Oct 2023 17:59:29 +0200
Subject: accel/ivpu/40xx: Allow to change profiling frequency

Profiling freq is a debug firmware feature. It switches default clock
to higher resolution for fine-grained and more accurate firmware task
profiling. We already configure it during boot up of VPU4.

Add debugfs knob and helpers per HW generation that allow to change it.
For vpu37xx the implementation is empty as profiling frequency can only
be changed on VPU4 or newer.

Signed-off-by: Krystian Pradzynski <krystian.pradzynski@linux.intel.com>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231028155936.1183342-2-stanislaw.gruszka@linux.intel.com
---
 drivers/accel/ivpu/ivpu_debugfs.c | 29 +++++++++++++++++++++++++++++
 drivers/accel/ivpu/ivpu_fw.c      |  7 +++++++
 drivers/accel/ivpu/ivpu_hw.h      | 12 ++++++++++++
 drivers/accel/ivpu/ivpu_hw_37xx.c | 13 +++++++++++++
 drivers/accel/ivpu/ivpu_hw_40xx.c | 15 +++++++++++++++
 5 files changed, 76 insertions(+)

(limited to 'drivers/accel')

diff --git a/drivers/accel/ivpu/ivpu_debugfs.c b/drivers/accel/ivpu/ivpu_debugfs.c
index 6e0d56823024..19035230563d 100644
--- a/drivers/accel/ivpu/ivpu_debugfs.c
+++ b/drivers/accel/ivpu/ivpu_debugfs.c
@@ -14,6 +14,7 @@
 #include "ivpu_fw.h"
 #include "ivpu_fw_log.h"
 #include "ivpu_gem.h"
+#include "ivpu_hw.h"
 #include "ivpu_jsm_msg.h"
 #include "ivpu_pm.h"
 
@@ -176,6 +177,30 @@ static const struct file_operations fw_log_fops = {
 	.release = single_release,
 };
 
+static ssize_t
+fw_profiling_freq_fops_write(struct file *file, const char __user *user_buf,
+			     size_t size, loff_t *pos)
+{
+	struct ivpu_device *vdev = file->private_data;
+	bool enable;
+	int ret;
+
+	ret = kstrtobool_from_user(user_buf, size, &enable);
+	if (ret < 0)
+		return ret;
+
+	ivpu_hw_profiling_freq_drive(vdev, enable);
+	ivpu_pm_schedule_recovery(vdev);
+
+	return size;
+}
+
+static const struct file_operations fw_profiling_freq_fops = {
+	.owner = THIS_MODULE,
+	.open = simple_open,
+	.write = fw_profiling_freq_fops_write,
+};
+
 static ssize_t
 fw_trace_destination_mask_fops_write(struct file *file, const char __user *user_buf,
 				     size_t size, loff_t *pos)
@@ -319,4 +344,8 @@ void ivpu_debugfs_init(struct ivpu_device *vdev)
 
 	debugfs_create_file("reset_engine", 0200, debugfs_root, vdev,
 			    &ivpu_reset_engine_fops);
+
+	if (ivpu_hw_gen(vdev) >= IVPU_HW_40XX)
+		debugfs_create_file("fw_profiling_freq_drive", 0200,
+				    debugfs_root, vdev, &fw_profiling_freq_fops);
 }
diff --git a/drivers/accel/ivpu/ivpu_fw.c b/drivers/accel/ivpu/ivpu_fw.c
index 4a21be3a0c59..3fd74cd4205f 100644
--- a/drivers/accel/ivpu/ivpu_fw.c
+++ b/drivers/accel/ivpu/ivpu_fw.c
@@ -498,6 +498,13 @@ void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params
 	boot_params->vpu_id = to_pci_dev(vdev->drm.dev)->bus->number;
 	boot_params->frequency = ivpu_hw_reg_pll_freq_get(vdev);
 
+	/*
+	 * This param is a debug firmware feature.  It switches default clock
+	 * to higher resolution one for fine-grained and more accurate firmware
+	 * task profiling.
+	 */
+	boot_params->perf_clk_frequency = ivpu_hw_profiling_freq_get(vdev);
+
 	/*
 	 * Uncached region of VPU address space, covers IPC buffers, job queues
 	 * and log buffers, programmable to L2$ Uncached by VPU MTRR
diff --git a/drivers/accel/ivpu/ivpu_hw.h b/drivers/accel/ivpu/ivpu_hw.h
index b7694b1cbc02..aa52e5c29a65 100644
--- a/drivers/accel/ivpu/ivpu_hw.h
+++ b/drivers/accel/ivpu/ivpu_hw.h
@@ -17,6 +17,8 @@ struct ivpu_hw_ops {
 	int (*wait_for_idle)(struct ivpu_device *vdev);
 	void (*wdt_disable)(struct ivpu_device *vdev);
 	void (*diagnose_failure)(struct ivpu_device *vdev);
+	u32 (*profiling_freq_get)(struct ivpu_device *vdev);
+	void (*profiling_freq_drive)(struct ivpu_device *vdev, bool enable);
 	u32 (*reg_pll_freq_get)(struct ivpu_device *vdev);
 	u32 (*reg_telemetry_offset_get)(struct ivpu_device *vdev);
 	u32 (*reg_telemetry_size_get)(struct ivpu_device *vdev);
@@ -104,6 +106,16 @@ static inline void ivpu_hw_wdt_disable(struct ivpu_device *vdev)
 	vdev->hw->ops->wdt_disable(vdev);
 };
 
+static inline u32 ivpu_hw_profiling_freq_get(struct ivpu_device *vdev)
+{
+	return vdev->hw->ops->profiling_freq_get(vdev);
+};
+
+static inline void ivpu_hw_profiling_freq_drive(struct ivpu_device *vdev, bool enable)
+{
+	return vdev->hw->ops->profiling_freq_drive(vdev, enable);
+};
+
 /* Register indirect accesses */
 static inline u32 ivpu_hw_reg_pll_freq_get(struct ivpu_device *vdev)
 {
diff --git a/drivers/accel/ivpu/ivpu_hw_37xx.c b/drivers/accel/ivpu/ivpu_hw_37xx.c
index 1c8c5715095b..81f81046d39a 100644
--- a/drivers/accel/ivpu/ivpu_hw_37xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_37xx.c
@@ -29,6 +29,7 @@
 
 #define PLL_REF_CLK_FREQ	     (50 * 1000000)
 #define PLL_SIMULATION_FREQ	     (10 * 1000000)
+#define PLL_PROF_CLK_FREQ	     (38400 * 1000)
 #define PLL_DEFAULT_EPP_VALUE	     0x80
 
 #define TIM_SAFE_ENABLE		     0xf1d0dead
@@ -769,6 +770,16 @@ static void ivpu_hw_37xx_wdt_disable(struct ivpu_device *vdev)
 	REGV_WR32(VPU_37XX_CPU_SS_TIM_GEN_CONFIG, val);
 }
 
+static u32 ivpu_hw_37xx_profiling_freq_get(struct ivpu_device *vdev)
+{
+	return PLL_PROF_CLK_FREQ;
+}
+
+static void ivpu_hw_37xx_profiling_freq_drive(struct ivpu_device *vdev, bool enable)
+{
+	/* Profiling freq - is a debug feature. Unavailable on VPU 37XX. */
+}
+
 static u32 ivpu_hw_37xx_pll_to_freq(u32 ratio, u32 config)
 {
 	u32 pll_clock = PLL_REF_CLK_FREQ * ratio;
@@ -1012,6 +1023,8 @@ const struct ivpu_hw_ops ivpu_hw_37xx_ops = {
 	.boot_fw = ivpu_hw_37xx_boot_fw,
 	.wdt_disable = ivpu_hw_37xx_wdt_disable,
 	.diagnose_failure = ivpu_hw_37xx_diagnose_failure,
+	.profiling_freq_get = ivpu_hw_37xx_profiling_freq_get,
+	.profiling_freq_drive = ivpu_hw_37xx_profiling_freq_drive,
 	.reg_pll_freq_get = ivpu_hw_37xx_reg_pll_freq_get,
 	.reg_telemetry_offset_get = ivpu_hw_37xx_reg_telemetry_offset_get,
 	.reg_telemetry_size_get = ivpu_hw_37xx_reg_telemetry_size_get,
diff --git a/drivers/accel/ivpu/ivpu_hw_40xx.c b/drivers/accel/ivpu/ivpu_hw_40xx.c
index 6a9672f650d1..a779b905f8b1 100644
--- a/drivers/accel/ivpu/ivpu_hw_40xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_40xx.c
@@ -931,6 +931,19 @@ static void ivpu_hw_40xx_wdt_disable(struct ivpu_device *vdev)
 	REGV_WR32(VPU_40XX_CPU_SS_TIM_GEN_CONFIG, val);
 }
 
+static u32 ivpu_hw_40xx_profiling_freq_get(struct ivpu_device *vdev)
+{
+	return vdev->hw->pll.profiling_freq;
+}
+
+static void ivpu_hw_40xx_profiling_freq_drive(struct ivpu_device *vdev, bool enable)
+{
+	if (enable)
+		vdev->hw->pll.profiling_freq = PLL_PROFILING_FREQ_HIGH;
+	else
+		vdev->hw->pll.profiling_freq = PLL_PROFILING_FREQ_DEFAULT;
+}
+
 /* Register indirect accesses */
 static u32 ivpu_hw_40xx_reg_pll_freq_get(struct ivpu_device *vdev)
 {
@@ -1182,6 +1195,8 @@ const struct ivpu_hw_ops ivpu_hw_40xx_ops = {
 	.boot_fw = ivpu_hw_40xx_boot_fw,
 	.wdt_disable = ivpu_hw_40xx_wdt_disable,
 	.diagnose_failure = ivpu_hw_40xx_diagnose_failure,
+	.profiling_freq_get = ivpu_hw_40xx_profiling_freq_get,
+	.profiling_freq_drive = ivpu_hw_40xx_profiling_freq_drive,
 	.reg_pll_freq_get = ivpu_hw_40xx_reg_pll_freq_get,
 	.reg_telemetry_offset_get = ivpu_hw_40xx_reg_telemetry_offset_get,
 	.reg_telemetry_size_get = ivpu_hw_40xx_reg_telemetry_size_get,
-- 
cgit 


From a06eb9be49a66e16e0c7819c630c1267c25b36dc Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Date: Sat, 28 Oct 2023 17:59:30 +0200
Subject: accel/ivpu: Assure device is off if power up sequence fail

We should not leave device half enabled if there is failure somewhere
it power up sequence. Fix device init and resume paths.

Reviewed-by: Karol Wachowski <karol.wachowski@linux.intel.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231028155936.1183342-3-stanislaw.gruszka@linux.intel.com
---
 drivers/accel/ivpu/ivpu_drv.c |  2 +-
 drivers/accel/ivpu/ivpu_pm.c  | 30 +++++++++++++++++-------------
 2 files changed, 18 insertions(+), 14 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c
index 39bac45d88b5..064cabef41bb 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -543,7 +543,7 @@ static int ivpu_dev_init(struct ivpu_device *vdev)
 	/* Power up early so the rest of init code can access VPU registers */
 	ret = ivpu_hw_power_up(vdev);
 	if (ret)
-		goto err_xa_destroy;
+		goto err_power_down;
 
 	ret = ivpu_mmu_global_context_init(vdev);
 	if (ret)
diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c
index 2d05fb9e3197..33d7c7731fe3 100644
--- a/drivers/accel/ivpu/ivpu_pm.c
+++ b/drivers/accel/ivpu/ivpu_pm.c
@@ -70,27 +70,31 @@ retry:
 	ret = ivpu_hw_power_up(vdev);
 	if (ret) {
 		ivpu_err(vdev, "Failed to power up HW: %d\n", ret);
-		return ret;
+		goto err_power_down;
 	}
 
 	ret = ivpu_mmu_enable(vdev);
 	if (ret) {
 		ivpu_err(vdev, "Failed to resume MMU: %d\n", ret);
-		ivpu_hw_power_down(vdev);
-		return ret;
+		goto err_power_down;
 	}
 
 	ret = ivpu_boot(vdev);
-	if (ret) {
-		ivpu_mmu_disable(vdev);
-		ivpu_hw_power_down(vdev);
-		if (!ivpu_fw_is_cold_boot(vdev)) {
-			ivpu_warn(vdev, "Failed to resume the FW: %d. Retrying cold boot..\n", ret);
-			ivpu_pm_prepare_cold_boot(vdev);
-			goto retry;
-		} else {
-			ivpu_err(vdev, "Failed to resume the FW: %d\n", ret);
-		}
+	if (ret)
+		goto err_mmu_disable;
+
+	return 0;
+
+err_mmu_disable:
+	ivpu_mmu_disable(vdev);
+err_power_down:
+	ivpu_hw_power_down(vdev);
+
+	if (!ivpu_fw_is_cold_boot(vdev)) {
+		ivpu_pm_prepare_cold_boot(vdev);
+		goto retry;
+	} else {
+		ivpu_err(vdev, "Failed to resume the FW: %d\n", ret);
 	}
 
 	return ret;
-- 
cgit 


From 57c7e3e4800ad65048a7044b03723cd85d9595af Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Date: Sat, 28 Oct 2023 17:59:31 +0200
Subject: accel/ivpu: Stop job_done_thread on suspend

Stop job_done thread when going to suspend. Use kthread_park() instead
of kthread_stop() to avoid memory allocation and potential failure
on resume.

Use separate function as thread wake up condition. Use spin lock to assure
rx_msg_list is properly protected against concurrent access. This avoid
race condition when the rx_msg_list list is modified and read in
ivpu_ipc_recive() at the same time.

Reviewed-by: Karol Wachowski <karol.wachowski@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231028155936.1183342-4-stanislaw.gruszka@linux.intel.com
---
 drivers/accel/ivpu/ivpu_drv.c |  2 ++
 drivers/accel/ivpu/ivpu_ipc.c | 17 +++++++++++++++--
 drivers/accel/ivpu/ivpu_job.c | 20 ++++++++++++++++----
 drivers/accel/ivpu/ivpu_job.h |  2 ++
 4 files changed, 35 insertions(+), 6 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c
index 064cabef41bb..60277ff6af69 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -378,6 +378,7 @@ int ivpu_boot(struct ivpu_device *vdev)
 	enable_irq(vdev->irq);
 	ivpu_hw_irq_enable(vdev);
 	ivpu_ipc_enable(vdev);
+	ivpu_job_done_thread_enable(vdev);
 	return 0;
 }
 
@@ -389,6 +390,7 @@ int ivpu_shutdown(struct ivpu_device *vdev)
 	disable_irq(vdev->irq);
 	ivpu_ipc_disable(vdev);
 	ivpu_mmu_disable(vdev);
+	ivpu_job_done_thread_disable(vdev);
 
 	ret = ivpu_hw_power_down(vdev);
 	if (ret)
diff --git a/drivers/accel/ivpu/ivpu_ipc.c b/drivers/accel/ivpu/ivpu_ipc.c
index d069d1e1f91d..270caef789bf 100644
--- a/drivers/accel/ivpu/ivpu_ipc.c
+++ b/drivers/accel/ivpu/ivpu_ipc.c
@@ -202,6 +202,20 @@ unlock:
 	return ret;
 }
 
+static int ivpu_ipc_rx_need_wakeup(struct ivpu_ipc_consumer *cons)
+{
+	int ret = 0;
+
+	if (IS_KTHREAD())
+		ret |= (kthread_should_stop() || kthread_should_park());
+
+	spin_lock_irq(&cons->rx_msg_lock);
+	ret |= !list_empty(&cons->rx_msg_list);
+	spin_unlock_irq(&cons->rx_msg_lock);
+
+	return ret;
+}
+
 int ivpu_ipc_receive(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
 		     struct ivpu_ipc_hdr *ipc_buf,
 		     struct vpu_jsm_msg *ipc_payload, unsigned long timeout_ms)
@@ -211,8 +225,7 @@ int ivpu_ipc_receive(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
 	int wait_ret, ret = 0;
 
 	wait_ret = wait_event_interruptible_timeout(cons->rx_msg_wq,
-						    (IS_KTHREAD() && kthread_should_stop()) ||
-						    !list_empty(&cons->rx_msg_list),
+						    ivpu_ipc_rx_need_wakeup(cons),
 						    msecs_to_jiffies(timeout_ms));
 
 	if (IS_KTHREAD() && kthread_should_stop())
diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c
index 6e96c921547d..a245b2d44db7 100644
--- a/drivers/accel/ivpu/ivpu_job.c
+++ b/drivers/accel/ivpu/ivpu_job.c
@@ -590,6 +590,11 @@ static int ivpu_job_done_thread(void *arg)
 				ivpu_pm_schedule_recovery(vdev);
 			}
 		}
+		if (kthread_should_park()) {
+			ivpu_dbg(vdev, JOB, "Parked %s\n", __func__);
+			kthread_parkme();
+			ivpu_dbg(vdev, JOB, "Unparked %s\n", __func__);
+		}
 	}
 
 	ivpu_ipc_consumer_del(vdev, &cons);
@@ -610,9 +615,6 @@ int ivpu_job_done_thread_init(struct ivpu_device *vdev)
 		return -EIO;
 	}
 
-	get_task_struct(thread);
-	wake_up_process(thread);
-
 	vdev->job_done_thread = thread;
 
 	return 0;
@@ -620,6 +622,16 @@ int ivpu_job_done_thread_init(struct ivpu_device *vdev)
 
 void ivpu_job_done_thread_fini(struct ivpu_device *vdev)
 {
+	kthread_unpark(vdev->job_done_thread);
 	kthread_stop(vdev->job_done_thread);
-	put_task_struct(vdev->job_done_thread);
+}
+
+void ivpu_job_done_thread_disable(struct ivpu_device *vdev)
+{
+	kthread_park(vdev->job_done_thread);
+}
+
+void ivpu_job_done_thread_enable(struct ivpu_device *vdev)
+{
+	kthread_unpark(vdev->job_done_thread);
 }
diff --git a/drivers/accel/ivpu/ivpu_job.h b/drivers/accel/ivpu/ivpu_job.h
index aa1f0b9479b0..a8e914e5affc 100644
--- a/drivers/accel/ivpu/ivpu_job.h
+++ b/drivers/accel/ivpu/ivpu_job.h
@@ -61,6 +61,8 @@ void ivpu_cmdq_reset_all_contexts(struct ivpu_device *vdev);
 
 int ivpu_job_done_thread_init(struct ivpu_device *vdev);
 void ivpu_job_done_thread_fini(struct ivpu_device *vdev);
+void ivpu_job_done_thread_disable(struct ivpu_device *vdev);
+void ivpu_job_done_thread_enable(struct ivpu_device *vdev);
 
 void ivpu_jobs_abort_all(struct ivpu_device *vdev);
 
-- 
cgit 


From ba6b035daac8c4fa5da1f14f262d97e0ffa45a6d Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Date: Sat, 28 Oct 2023 17:59:32 +0200
Subject: accel/ivpu: Abort pending rx ipc on reset

Waking up process, which wait for particular condition, will go to
sleep again on wake_up() if the condition is not met. Add abort flag
to wake up IPC receivers, which will finish with -ECANCELED error.

This is only needed for reset, run time power management prevent to
suspend VPU when there is pending IPC processing or pending job.

Reviewed-by: Karol Wachowski <karol.wachowski@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231028155936.1183342-5-stanislaw.gruszka@linux.intel.com
---
 drivers/accel/ivpu/ivpu_ipc.c | 20 +++++++++++++++++---
 drivers/accel/ivpu/ivpu_ipc.h |  3 ++-
 drivers/accel/ivpu/ivpu_job.c |  1 +
 3 files changed, 20 insertions(+), 4 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/ivpu/ivpu_ipc.c b/drivers/accel/ivpu/ivpu_ipc.c
index 270caef789bf..255f2b8b0b5e 100644
--- a/drivers/accel/ivpu/ivpu_ipc.c
+++ b/drivers/accel/ivpu/ivpu_ipc.c
@@ -148,6 +148,7 @@ ivpu_ipc_consumer_add(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
 	cons->channel = channel;
 	cons->tx_vpu_addr = 0;
 	cons->request_id = 0;
+	cons->aborted = false;
 	spin_lock_init(&cons->rx_msg_lock);
 	INIT_LIST_HEAD(&cons->rx_msg_list);
 	init_waitqueue_head(&cons->rx_msg_wq);
@@ -169,7 +170,8 @@ void ivpu_ipc_consumer_del(struct ivpu_device *vdev, struct ivpu_ipc_consumer *c
 	spin_lock_irq(&cons->rx_msg_lock);
 	list_for_each_entry_safe(rx_msg, r, &cons->rx_msg_list, link) {
 		list_del(&rx_msg->link);
-		ivpu_ipc_rx_mark_free(vdev, rx_msg->ipc_hdr, rx_msg->jsm_msg);
+		if (!cons->aborted)
+			ivpu_ipc_rx_mark_free(vdev, rx_msg->ipc_hdr, rx_msg->jsm_msg);
 		atomic_dec(&ipc->rx_msg_count);
 		kfree(rx_msg);
 	}
@@ -210,7 +212,7 @@ static int ivpu_ipc_rx_need_wakeup(struct ivpu_ipc_consumer *cons)
 		ret |= (kthread_should_stop() || kthread_should_park());
 
 	spin_lock_irq(&cons->rx_msg_lock);
-	ret |= !list_empty(&cons->rx_msg_list);
+	ret |= !list_empty(&cons->rx_msg_list) || cons->aborted;
 	spin_unlock_irq(&cons->rx_msg_lock);
 
 	return ret;
@@ -244,6 +246,12 @@ int ivpu_ipc_receive(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
 		return -EAGAIN;
 	}
 	list_del(&rx_msg->link);
+	if (cons->aborted) {
+		spin_unlock_irq(&cons->rx_msg_lock);
+		ret = -ECANCELED;
+		goto out;
+	}
+
 	spin_unlock_irq(&cons->rx_msg_lock);
 
 	if (ipc_buf)
@@ -261,6 +269,7 @@ int ivpu_ipc_receive(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
 	}
 
 	ivpu_ipc_rx_mark_free(vdev, rx_msg->ipc_hdr, rx_msg->jsm_msg);
+out:
 	atomic_dec(&ipc->rx_msg_count);
 	kfree(rx_msg);
 
@@ -522,8 +531,12 @@ void ivpu_ipc_disable(struct ivpu_device *vdev)
 	mutex_unlock(&ipc->lock);
 
 	spin_lock_irqsave(&ipc->cons_list_lock, flags);
-	list_for_each_entry_safe(cons, c, &ipc->cons_list, link)
+	list_for_each_entry_safe(cons, c, &ipc->cons_list, link) {
+		spin_lock(&cons->rx_msg_lock);
+		cons->aborted = true;
+		spin_unlock(&cons->rx_msg_lock);
 		wake_up(&cons->rx_msg_wq);
+	}
 	spin_unlock_irqrestore(&ipc->cons_list_lock, flags);
 }
 
@@ -532,6 +545,7 @@ void ivpu_ipc_reset(struct ivpu_device *vdev)
 	struct ivpu_ipc_info *ipc = vdev->ipc;
 
 	mutex_lock(&ipc->lock);
+	drm_WARN_ON(&vdev->drm, ipc->on);
 
 	memset(ivpu_bo_vaddr(ipc->mem_tx), 0, ivpu_bo_size(ipc->mem_tx));
 	memset(ivpu_bo_vaddr(ipc->mem_rx), 0, ivpu_bo_size(ipc->mem_rx));
diff --git a/drivers/accel/ivpu/ivpu_ipc.h b/drivers/accel/ivpu/ivpu_ipc.h
index 6918db23daa4..a380787f7222 100644
--- a/drivers/accel/ivpu/ivpu_ipc.h
+++ b/drivers/accel/ivpu/ivpu_ipc.h
@@ -47,8 +47,9 @@ struct ivpu_ipc_consumer {
 	u32 channel;
 	u32 tx_vpu_addr;
 	u32 request_id;
+	bool aborted;
 
-	spinlock_t rx_msg_lock; /* Protects rx_msg_list */
+	spinlock_t rx_msg_lock; /* Protects rx_msg_list and aborted */
 	struct list_head rx_msg_list;
 	wait_queue_head_t rx_msg_wq;
 };
diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c
index a245b2d44db7..15a408fad494 100644
--- a/drivers/accel/ivpu/ivpu_job.c
+++ b/drivers/accel/ivpu/ivpu_job.c
@@ -578,6 +578,7 @@ static int ivpu_job_done_thread(void *arg)
 	ivpu_ipc_consumer_add(vdev, &cons, VPU_IPC_CHAN_JOB_RET);
 
 	while (!kthread_should_stop()) {
+		cons.aborted = false;
 		timeout = ivpu_tdr_timeout_ms ? ivpu_tdr_timeout_ms : vdev->timeout.tdr;
 		jobs_submitted = !xa_empty(&vdev->submitted_jobs_xa);
 		ret = ivpu_ipc_receive(vdev, &cons, NULL, &jsm_msg, timeout);
-- 
cgit 


From e013aa9ab01b400cccc6c3e8b969b8e7f10bc6cb Mon Sep 17 00:00:00 2001
From: Karol Wachowski <karol.wachowski@linux.intel.com>
Date: Sat, 28 Oct 2023 17:59:33 +0200
Subject: accel/ivpu: Print CMDQ errors after consumer timeout

Add checking of error reason bits in IVPU_MMU_CMDQ_CONS
register when waiting for consumer timeout occurred.

Signed-off-by: Karol Wachowski <karol.wachowski@linux.intel.com>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231028155936.1183342-6-stanislaw.gruszka@linux.intel.com
---
 drivers/accel/ivpu/ivpu_mmu.c | 34 +++++++++++++++++++++++++++++++---
 1 file changed, 31 insertions(+), 3 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/ivpu/ivpu_mmu.c b/drivers/accel/ivpu/ivpu_mmu.c
index 2538c78fbebe..b15cf9cc9c43 100644
--- a/drivers/accel/ivpu/ivpu_mmu.c
+++ b/drivers/accel/ivpu/ivpu_mmu.c
@@ -230,7 +230,12 @@
 				  (REG_FLD(IVPU_MMU_REG_GERROR, MSI_PRIQ_ABT)) | \
 				  (REG_FLD(IVPU_MMU_REG_GERROR, MSI_ABT)))
 
-static char *ivpu_mmu_event_to_str(u32 cmd)
+#define IVPU_MMU_CERROR_NONE         0x0
+#define IVPU_MMU_CERROR_ILL          0x1
+#define IVPU_MMU_CERROR_ABT          0x2
+#define IVPU_MMU_CERROR_ATC_INV_SYNC 0x3
+
+static const char *ivpu_mmu_event_to_str(u32 cmd)
 {
 	switch (cmd) {
 	case IVPU_MMU_EVT_F_UUT:
@@ -276,6 +281,22 @@ static char *ivpu_mmu_event_to_str(u32 cmd)
 	}
 }
 
+static const char *ivpu_mmu_cmdq_err_to_str(u32 err)
+{
+	switch (err) {
+	case IVPU_MMU_CERROR_NONE:
+		return "No CMDQ Error";
+	case IVPU_MMU_CERROR_ILL:
+		return "Illegal command";
+	case IVPU_MMU_CERROR_ABT:
+		return "External abort on CMDQ read";
+	case IVPU_MMU_CERROR_ATC_INV_SYNC:
+		return "Sync failed to complete ATS invalidation";
+	default:
+		return "Unknown CMDQ Error";
+	}
+}
+
 static void ivpu_mmu_config_check(struct ivpu_device *vdev)
 {
 	u32 val_ref;
@@ -492,8 +513,15 @@ static int ivpu_mmu_cmdq_sync(struct ivpu_device *vdev)
 	REGV_WR32(IVPU_MMU_REG_CMDQ_PROD, q->prod);
 
 	ret = ivpu_mmu_cmdq_wait_for_cons(vdev);
-	if (ret)
-		ivpu_err(vdev, "Timed out waiting for consumer: %d\n", ret);
+	if (ret) {
+		u32 err;
+
+		val = REGV_RD32(IVPU_MMU_REG_CMDQ_CONS);
+		err = REG_GET_FLD(IVPU_MMU_REG_CMDQ_CONS, ERR, val);
+
+		ivpu_err(vdev, "Timed out waiting for MMU consumer: %d, error: %s\n", ret,
+			 ivpu_mmu_cmdq_err_to_str(err));
+	}
 
 	return ret;
 }
-- 
cgit 


From 3bcc5209ba6af1019487b54b30fc226ecf79193d Mon Sep 17 00:00:00 2001
From: Karol Wachowski <karol.wachowski@linux.intel.com>
Date: Sat, 28 Oct 2023 17:59:34 +0200
Subject: accel/ivpu: Make DMA allocations for MMU600 write combined

Previously using dma_alloc_wc() API we created cache coherent
(mapped as write-back) mappings.

Because we disable MMU600 snooping it was required to do costly
page walk and cache flushes after each page table modification.

With write-combined buffers it's possible to do a single write memory
barrier to flush write-combined buffer to memory which simplifies the
driver and significantly reduce time of map/unmap operations.

Mapping time of 255 MB is reduced from 2.5 ms to 500 us.

Signed-off-by: Karol Wachowski <karol.wachowski@linux.intel.com>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231028155936.1183342-7-stanislaw.gruszka@linux.intel.com
---
 drivers/accel/ivpu/ivpu_mmu_context.c | 115 +++++++++++++++++++---------------
 1 file changed, 63 insertions(+), 52 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/ivpu/ivpu_mmu_context.c b/drivers/accel/ivpu/ivpu_mmu_context.c
index 0c8c65351919..7d8005bc78d2 100644
--- a/drivers/accel/ivpu/ivpu_mmu_context.c
+++ b/drivers/accel/ivpu/ivpu_mmu_context.c
@@ -5,6 +5,9 @@
 
 #include <linux/bitfield.h>
 #include <linux/highmem.h>
+#include <linux/set_memory.h>
+
+#include <drm/drm_cache.h>
 
 #include "ivpu_drv.h"
 #include "ivpu_hw.h"
@@ -38,12 +41,57 @@
 #define IVPU_MMU_ENTRY_MAPPED  (IVPU_MMU_ENTRY_FLAG_AF | IVPU_MMU_ENTRY_FLAG_USER | \
 				IVPU_MMU_ENTRY_FLAG_NG | IVPU_MMU_ENTRY_VALID)
 
+static void *ivpu_pgtable_alloc_page(struct ivpu_device *vdev, dma_addr_t *dma)
+{
+	dma_addr_t dma_addr;
+	struct page *page;
+	void *cpu;
+
+	page = alloc_page(GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO);
+	if (!page)
+		return NULL;
+
+	set_pages_array_wc(&page, 1);
+
+	dma_addr = dma_map_page(vdev->drm.dev, page, 0, PAGE_SIZE, DMA_BIDIRECTIONAL);
+	if (dma_mapping_error(vdev->drm.dev, dma_addr))
+		goto err_free_page;
+
+	cpu = vmap(&page, 1, VM_MAP, pgprot_writecombine(PAGE_KERNEL));
+	if (!cpu)
+		goto err_dma_unmap_page;
+
+
+	*dma = dma_addr;
+	return cpu;
+
+err_dma_unmap_page:
+	dma_unmap_page(vdev->drm.dev, dma_addr, PAGE_SIZE, DMA_BIDIRECTIONAL);
+
+err_free_page:
+	put_page(page);
+	return NULL;
+}
+
+static void ivpu_pgtable_free_page(struct ivpu_device *vdev, u64 *cpu_addr, dma_addr_t dma_addr)
+{
+	struct page *page;
+
+	if (cpu_addr) {
+		page = vmalloc_to_page(cpu_addr);
+		vunmap(cpu_addr);
+		dma_unmap_page(vdev->drm.dev, dma_addr & ~IVPU_MMU_ENTRY_FLAGS_MASK, PAGE_SIZE,
+			       DMA_BIDIRECTIONAL);
+		set_pages_array_wb(&page, 1);
+		put_page(page);
+	}
+}
+
 static int ivpu_mmu_pgtable_init(struct ivpu_device *vdev, struct ivpu_mmu_pgtable *pgtable)
 {
 	dma_addr_t pgd_dma;
 
-	pgtable->pgd_dma_ptr = dma_alloc_coherent(vdev->drm.dev, IVPU_MMU_PGTABLE_SIZE, &pgd_dma,
-						  GFP_KERNEL);
+	pgtable->pgd_dma_ptr = ivpu_pgtable_alloc_page(vdev, &pgd_dma);
 	if (!pgtable->pgd_dma_ptr)
 		return -ENOMEM;
 
@@ -52,13 +100,6 @@ static int ivpu_mmu_pgtable_init(struct ivpu_device *vdev, struct ivpu_mmu_pgtab
 	return 0;
 }
 
-static void ivpu_mmu_pgtable_free(struct ivpu_device *vdev, u64 *cpu_addr, dma_addr_t dma_addr)
-{
-	if (cpu_addr)
-		dma_free_coherent(vdev->drm.dev, IVPU_MMU_PGTABLE_SIZE, cpu_addr,
-				  dma_addr & ~IVPU_MMU_ENTRY_FLAGS_MASK);
-}
-
 static void ivpu_mmu_pgtables_free(struct ivpu_device *vdev, struct ivpu_mmu_pgtable *pgtable)
 {
 	int pgd_idx, pud_idx, pmd_idx;
@@ -83,19 +124,19 @@ static void ivpu_mmu_pgtables_free(struct ivpu_device *vdev, struct ivpu_mmu_pgt
 				pte_dma_ptr = pgtable->pte_ptrs[pgd_idx][pud_idx][pmd_idx];
 				pte_dma = pgtable->pmd_ptrs[pgd_idx][pud_idx][pmd_idx];
 
-				ivpu_mmu_pgtable_free(vdev, pte_dma_ptr, pte_dma);
+				ivpu_pgtable_free_page(vdev, pte_dma_ptr, pte_dma);
 			}
 
 			kfree(pgtable->pte_ptrs[pgd_idx][pud_idx]);
-			ivpu_mmu_pgtable_free(vdev, pmd_dma_ptr, pmd_dma);
+			ivpu_pgtable_free_page(vdev, pmd_dma_ptr, pmd_dma);
 		}
 
 		kfree(pgtable->pmd_ptrs[pgd_idx]);
 		kfree(pgtable->pte_ptrs[pgd_idx]);
-		ivpu_mmu_pgtable_free(vdev, pud_dma_ptr, pud_dma);
+		ivpu_pgtable_free_page(vdev, pud_dma_ptr, pud_dma);
 	}
 
-	ivpu_mmu_pgtable_free(vdev, pgtable->pgd_dma_ptr, pgtable->pgd_dma);
+	ivpu_pgtable_free_page(vdev, pgtable->pgd_dma_ptr, pgtable->pgd_dma);
 }
 
 static u64*
@@ -107,7 +148,7 @@ ivpu_mmu_ensure_pud(struct ivpu_device *vdev, struct ivpu_mmu_pgtable *pgtable,
 	if (pud_dma_ptr)
 		return pud_dma_ptr;
 
-	pud_dma_ptr = dma_alloc_wc(vdev->drm.dev, IVPU_MMU_PGTABLE_SIZE, &pud_dma, GFP_KERNEL);
+	pud_dma_ptr = ivpu_pgtable_alloc_page(vdev, &pud_dma);
 	if (!pud_dma_ptr)
 		return NULL;
 
@@ -130,7 +171,7 @@ err_free_pmd_ptrs:
 	kfree(pgtable->pmd_ptrs[pgd_idx]);
 
 err_free_pud_dma_ptr:
-	ivpu_mmu_pgtable_free(vdev, pud_dma_ptr, pud_dma);
+	ivpu_pgtable_free_page(vdev, pud_dma_ptr, pud_dma);
 	return NULL;
 }
 
@@ -144,7 +185,7 @@ ivpu_mmu_ensure_pmd(struct ivpu_device *vdev, struct ivpu_mmu_pgtable *pgtable,
 	if (pmd_dma_ptr)
 		return pmd_dma_ptr;
 
-	pmd_dma_ptr = dma_alloc_wc(vdev->drm.dev, IVPU_MMU_PGTABLE_SIZE, &pmd_dma, GFP_KERNEL);
+	pmd_dma_ptr = ivpu_pgtable_alloc_page(vdev, &pmd_dma);
 	if (!pmd_dma_ptr)
 		return NULL;
 
@@ -159,7 +200,7 @@ ivpu_mmu_ensure_pmd(struct ivpu_device *vdev, struct ivpu_mmu_pgtable *pgtable,
 	return pmd_dma_ptr;
 
 err_free_pmd_dma_ptr:
-	ivpu_mmu_pgtable_free(vdev, pmd_dma_ptr, pmd_dma);
+	ivpu_pgtable_free_page(vdev, pmd_dma_ptr, pmd_dma);
 	return NULL;
 }
 
@@ -173,7 +214,7 @@ ivpu_mmu_ensure_pte(struct ivpu_device *vdev, struct ivpu_mmu_pgtable *pgtable,
 	if (pte_dma_ptr)
 		return pte_dma_ptr;
 
-	pte_dma_ptr = dma_alloc_wc(vdev->drm.dev, IVPU_MMU_PGTABLE_SIZE, &pte_dma, GFP_KERNEL);
+	pte_dma_ptr = ivpu_pgtable_alloc_page(vdev, &pte_dma);
 	if (!pte_dma_ptr)
 		return NULL;
 
@@ -248,38 +289,6 @@ static void ivpu_mmu_context_unmap_page(struct ivpu_mmu_context *ctx, u64 vpu_ad
 	ctx->pgtable.pte_ptrs[pgd_idx][pud_idx][pmd_idx][pte_idx] = IVPU_MMU_ENTRY_INVALID;
 }
 
-static void
-ivpu_mmu_context_flush_page_tables(struct ivpu_mmu_context *ctx, u64 vpu_addr, size_t size)
-{
-	struct ivpu_mmu_pgtable *pgtable = &ctx->pgtable;
-	u64 end_addr = vpu_addr + size;
-
-	/* Align to PMD entry (2 MB) */
-	vpu_addr &= ~(IVPU_MMU_PTE_MAP_SIZE - 1);
-
-	while (vpu_addr < end_addr) {
-		int pgd_idx = FIELD_GET(IVPU_MMU_PGD_INDEX_MASK, vpu_addr);
-		u64 pud_end = (pgd_idx + 1) * (u64)IVPU_MMU_PUD_MAP_SIZE;
-
-		while (vpu_addr < end_addr && vpu_addr < pud_end) {
-			int pud_idx = FIELD_GET(IVPU_MMU_PUD_INDEX_MASK, vpu_addr);
-			u64 pmd_end = (pud_idx + 1) * (u64)IVPU_MMU_PMD_MAP_SIZE;
-
-			while (vpu_addr < end_addr && vpu_addr < pmd_end) {
-				int pmd_idx = FIELD_GET(IVPU_MMU_PMD_INDEX_MASK, vpu_addr);
-
-				clflush_cache_range(pgtable->pte_ptrs[pgd_idx][pud_idx][pmd_idx],
-						    IVPU_MMU_PGTABLE_SIZE);
-				vpu_addr += IVPU_MMU_PTE_MAP_SIZE;
-			}
-			clflush_cache_range(pgtable->pmd_ptrs[pgd_idx][pud_idx],
-					    IVPU_MMU_PGTABLE_SIZE);
-		}
-		clflush_cache_range(pgtable->pud_ptrs[pgd_idx], IVPU_MMU_PGTABLE_SIZE);
-	}
-	clflush_cache_range(pgtable->pgd_dma_ptr, IVPU_MMU_PGTABLE_SIZE);
-}
-
 static int
 ivpu_mmu_context_map_pages(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx,
 			   u64 vpu_addr, dma_addr_t dma_addr, size_t size, u64 prot)
@@ -352,10 +361,11 @@ ivpu_mmu_context_map_sgt(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx,
 			mutex_unlock(&ctx->lock);
 			return ret;
 		}
-		ivpu_mmu_context_flush_page_tables(ctx, vpu_addr, size);
 		vpu_addr += size;
 	}
 
+	/* Ensure page table modifications are flushed from wc buffers to memory */
+	wmb();
 	mutex_unlock(&ctx->lock);
 
 	ret = ivpu_mmu_invalidate_tlb(vdev, ctx->id);
@@ -381,10 +391,11 @@ ivpu_mmu_context_unmap_sgt(struct ivpu_device *vdev, struct ivpu_mmu_context *ct
 		size_t size = sg_dma_len(sg) + sg->offset;
 
 		ivpu_mmu_context_unmap_pages(ctx, vpu_addr, size);
-		ivpu_mmu_context_flush_page_tables(ctx, vpu_addr, size);
 		vpu_addr += size;
 	}
 
+	/* Ensure page table modifications are flushed from wc buffers to memory */
+	wmb();
 	mutex_unlock(&ctx->lock);
 
 	ret = ivpu_mmu_invalidate_tlb(vdev, ctx->id);
-- 
cgit 


From 0c287c27fbffa2737f155af73646a794e540e1d3 Mon Sep 17 00:00:00 2001
From: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Date: Sat, 28 Oct 2023 17:59:35 +0200
Subject: accel/ivpu: Simplify MMU SYNC command

CMD_SYNC does not need any args as we poll for completion anyway.

Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231028155936.1183342-8-stanislaw.gruszka@linux.intel.com
---
 drivers/accel/ivpu/ivpu_mmu.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/ivpu/ivpu_mmu.c b/drivers/accel/ivpu/ivpu_mmu.c
index b15cf9cc9c43..b46f3743c0e7 100644
--- a/drivers/accel/ivpu/ivpu_mmu.c
+++ b/drivers/accel/ivpu/ivpu_mmu.c
@@ -500,10 +500,7 @@ static int ivpu_mmu_cmdq_sync(struct ivpu_device *vdev)
 	u64 val;
 	int ret;
 
-	val = FIELD_PREP(IVPU_MMU_CMD_OPCODE, CMD_SYNC) |
-	      FIELD_PREP(IVPU_MMU_CMD_SYNC_0_CS, 0x2) |
-	      FIELD_PREP(IVPU_MMU_CMD_SYNC_0_MSH, 0x3) |
-	      FIELD_PREP(IVPU_MMU_CMD_SYNC_0_MSI_ATTR, 0xf);
+	val = FIELD_PREP(IVPU_MMU_CMD_OPCODE, CMD_SYNC);
 
 	ret = ivpu_mmu_cmdq_cmd_write(vdev, "SYNC", val, 0);
 	if (ret)
-- 
cgit 


From 2fc1a50fa4472301a3b262fcfc78744c841d5587 Mon Sep 17 00:00:00 2001
From: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Date: Sat, 28 Oct 2023 17:59:36 +0200
Subject: accel/ivpu: Rename VPU to NPU in product strings

VPU was rebranded as NPU (Neural Processing Unit) so user facing
strings have to be updated but the code remains as is and the module
is still called intel_vpu.ko.

Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231028155936.1183342-9-stanislaw.gruszka@linux.intel.com
---
 drivers/accel/ivpu/Kconfig    | 9 +++++----
 drivers/accel/ivpu/ivpu_drv.h | 2 +-
 2 files changed, 6 insertions(+), 5 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/ivpu/Kconfig b/drivers/accel/ivpu/Kconfig
index 1a4c4ed9d113..82749e0da524 100644
--- a/drivers/accel/ivpu/Kconfig
+++ b/drivers/accel/ivpu/Kconfig
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 
 config DRM_ACCEL_IVPU
-	tristate "Intel VPU for Meteor Lake and newer"
+	tristate "Intel NPU (Neural Processing Unit)"
 	depends on DRM_ACCEL
 	depends on X86_64 && !UML
 	depends on PCI && PCI_MSI
@@ -9,8 +9,9 @@ config DRM_ACCEL_IVPU
 	select SHMEM
 	select GENERIC_ALLOCATOR
 	help
-	  Choose this option if you have a system that has an 14th generation Intel CPU
-	  or newer. VPU stands for Versatile Processing Unit and it's a CPU-integrated
-	  inference accelerator for Computer Vision and Deep Learning applications.
+	  Choose this option if you have a system with an 14th generation
+	  Intel CPU (Meteor Lake) or newer. Intel NPU (formerly called Intel VPU)
+	  is a CPU-integrated inference accelerator for Computer Vision
+	  and Deep Learning applications.
 
 	  If "M" is selected, the module will be called intel_vpu.
diff --git a/drivers/accel/ivpu/ivpu_drv.h b/drivers/accel/ivpu/ivpu_drv.h
index 1b482d1d66d9..79b193ffbc26 100644
--- a/drivers/accel/ivpu/ivpu_drv.h
+++ b/drivers/accel/ivpu/ivpu_drv.h
@@ -19,7 +19,7 @@
 #include "ivpu_mmu_context.h"
 
 #define DRIVER_NAME "intel_vpu"
-#define DRIVER_DESC "Driver for Intel Versatile Processing Unit (VPU)"
+#define DRIVER_DESC "Driver for Intel NPU (Neural Processing Unit)"
 #define DRIVER_DATE "20230117"
 
 #define PCI_DEVICE_ID_MTL   0x7d1d
-- 
cgit 


From 44793c6a5b784f1f25608e3773fd40e011c63391 Mon Sep 17 00:00:00 2001
From: Carl Vanderlip <quic_carlv@quicinc.com>
Date: Fri, 27 Oct 2023 12:08:10 -0600
Subject: accel/qaic: Quiet array bounds check on DMA abort message

Current wrapper is right-sized to the message being transferred;
however, this is smaller than the structure defining message wrappers
since the trailing element is a union of message/transfer headers of
various sizes (8 and 32 bytes on 32-bit system where issue was
reported). Using the smaller header with a small message
(wire_trans_dma_xfer is 24 bytes including header) ends up being smaller
than a wrapper with the larger header. There are no accesses outside of
the defined size, however they are possible if the larger union member
is referenced.

Abort messages are outside of hot-path and changing the wrapper struct
would require a larger rewrite, so having the memory allocated to the
message be 8 bytes too big is acceptable.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202310182253.bcb9JcyJ-lkp@intel.com/
Signed-off-by: Carl Vanderlip <quic_carlv@quicinc.com>
Reviewed-by: Pranjal Ramajor Asha Kanojiya <quic_pkanojiy@quicinc.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231027180810.4873-1-quic_jhugo@quicinc.com
---
 drivers/accel/qaic/qaic_control.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/qaic/qaic_control.c b/drivers/accel/qaic/qaic_control.c
index 388abd40024b..84915824be54 100644
--- a/drivers/accel/qaic/qaic_control.c
+++ b/drivers/accel/qaic/qaic_control.c
@@ -1138,7 +1138,7 @@ static int abort_dma_cont(struct qaic_device *qdev, struct wrapper_list *wrapper
 		if (!list_is_first(&wrapper->list, &wrappers->list))
 			kref_put(&wrapper->ref_count, free_wrapper);
 
-	wrapper = add_wrapper(wrappers, offsetof(struct wrapper_msg, trans) + sizeof(*out_trans));
+	wrapper = add_wrapper(wrappers, sizeof(*wrapper));
 
 	if (!wrapper)
 		return -ENOMEM;
-- 
cgit 


From 3b511278b6ef514b3ae3d99ff62947cddd434479 Mon Sep 17 00:00:00 2001
From: Pranjal Ramajor Asha Kanojiya <quic_pkanojiy@quicinc.com>
Date: Fri, 27 Oct 2023 10:43:30 -0600
Subject: accel/qaic: Support for 0 resize slice execution in BO

Add support to partially execute a slice which is resized to zero.
Executing a zero size slice in a BO should mean that there is no DMA
transfers involved but you should still configure doorbell and semaphores.

For example consider a BO of size 18K and it is sliced into 3 6K slices
and user calls partial execute ioctl with resize as 10K.
slice 0 - size is 6k and offset is 0, so resize of 10K will not cut short
          this slice hence we send the entire slice for execution.
slice 1 - size is 6k and offset is 6k, so resize of 10K will cut short this
          slice and only the first 4k should be DMA along with configuring
          doorbell and semaphores.
slice 2 - size is 6k and offset is 12k, so resize of 10k will cut short
          this slice and no DMA transfer would be involved but we should
          would configure doorbell and semaphores.

This change begs to change the behavior of 0 resize. Currently, 0 resize
partial execute ioctl behaves exactly like execute ioctl i.e. no resize.
After this patch all the slice in BO should behave exactly like slice 2 in
above example.

Refactor copy_partial_exec_reqs() to make it more readable and less
complex.

Signed-off-by: Pranjal Ramajor Asha Kanojiya <quic_pkanojiy@quicinc.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231027164330.11978-1-quic_jhugo@quicinc.com
---
 drivers/accel/qaic/qaic_data.c | 104 +++++++++++++++++------------------------
 1 file changed, 43 insertions(+), 61 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/qaic/qaic_data.c b/drivers/accel/qaic/qaic_data.c
index ebc3cca1b094..8da81768f2ab 100644
--- a/drivers/accel/qaic/qaic_data.c
+++ b/drivers/accel/qaic/qaic_data.c
@@ -51,6 +51,7 @@
 		})
 #define NUM_EVENTS	128
 #define NUM_DELAYS	10
+#define fifo_at(base, offset) ((base) + (offset) * get_dbc_req_elem_size())
 
 static unsigned int wait_exec_default_timeout_ms = 5000; /* 5 sec default */
 module_param(wait_exec_default_timeout_ms, uint, 0600);
@@ -1058,6 +1059,16 @@ unlock_usr_srcu:
 	return ret;
 }
 
+static inline u32 fifo_space_avail(u32 head, u32 tail, u32 q_size)
+{
+	u32 avail = head - tail - 1;
+
+	if (head <= tail)
+		avail += q_size;
+
+	return avail;
+}
+
 static inline int copy_exec_reqs(struct qaic_device *qdev, struct bo_slice *slice, u32 dbc_id,
 				 u32 head, u32 *ptail)
 {
@@ -1066,27 +1077,20 @@ static inline int copy_exec_reqs(struct qaic_device *qdev, struct bo_slice *slic
 	u32 tail = *ptail;
 	u32 avail;
 
-	avail = head - tail;
-	if (head <= tail)
-		avail += dbc->nelem;
-
-	--avail;
-
+	avail = fifo_space_avail(head, tail, dbc->nelem);
 	if (avail < slice->nents)
 		return -EAGAIN;
 
 	if (tail + slice->nents > dbc->nelem) {
 		avail = dbc->nelem - tail;
 		avail = min_t(u32, avail, slice->nents);
-		memcpy(dbc->req_q_base + tail * get_dbc_req_elem_size(), reqs,
-		       sizeof(*reqs) * avail);
+		memcpy(fifo_at(dbc->req_q_base, tail), reqs, sizeof(*reqs) * avail);
 		reqs += avail;
 		avail = slice->nents - avail;
 		if (avail)
 			memcpy(dbc->req_q_base, reqs, sizeof(*reqs) * avail);
 	} else {
-		memcpy(dbc->req_q_base + tail * get_dbc_req_elem_size(), reqs,
-		       sizeof(*reqs) * slice->nents);
+		memcpy(fifo_at(dbc->req_q_base, tail), reqs, sizeof(*reqs) * slice->nents);
 	}
 
 	*ptail = (tail + slice->nents) % dbc->nelem;
@@ -1094,46 +1098,31 @@ static inline int copy_exec_reqs(struct qaic_device *qdev, struct bo_slice *slic
 	return 0;
 }
 
-/*
- * Based on the value of resize we may only need to transmit first_n
- * entries and the last entry, with last_bytes to send from the last entry.
- * Note that first_n could be 0.
- */
 static inline int copy_partial_exec_reqs(struct qaic_device *qdev, struct bo_slice *slice,
-					 u64 resize, u32 dbc_id, u32 head, u32 *ptail)
+					 u64 resize, struct dma_bridge_chan *dbc, u32 head,
+					 u32 *ptail)
 {
-	struct dma_bridge_chan *dbc = &qdev->dbc[dbc_id];
 	struct dbc_req *reqs = slice->reqs;
 	struct dbc_req *last_req;
 	u32 tail = *ptail;
-	u64 total_bytes;
 	u64 last_bytes;
 	u32 first_n;
 	u32 avail;
-	int ret;
-	int i;
-
-	avail = head - tail;
-	if (head <= tail)
-		avail += dbc->nelem;
 
-	--avail;
+	avail = fifo_space_avail(head, tail, dbc->nelem);
 
-	total_bytes = 0;
-	for (i = 0; i < slice->nents; i++) {
-		total_bytes += le32_to_cpu(reqs[i].len);
-		if (total_bytes >= resize)
+	/*
+	 * After this for loop is complete, first_n represents the index
+	 * of the last DMA request of this slice that needs to be
+	 * transferred after resizing and last_bytes represents DMA size
+	 * of that request.
+	 */
+	last_bytes = resize;
+	for (first_n = 0; first_n < slice->nents; first_n++)
+		if (last_bytes > le32_to_cpu(reqs[first_n].len))
+			last_bytes -= le32_to_cpu(reqs[first_n].len);
+		else
 			break;
-	}
-
-	if (total_bytes < resize) {
-		/* User space should have used the full buffer path. */
-		ret = -EINVAL;
-		return ret;
-	}
-
-	first_n = i;
-	last_bytes = i ? resize + le32_to_cpu(reqs[i].len) - total_bytes : resize;
 
 	if (avail < (first_n + 1))
 		return -EAGAIN;
@@ -1142,22 +1131,21 @@ static inline int copy_partial_exec_reqs(struct qaic_device *qdev, struct bo_sli
 		if (tail + first_n > dbc->nelem) {
 			avail = dbc->nelem - tail;
 			avail = min_t(u32, avail, first_n);
-			memcpy(dbc->req_q_base + tail * get_dbc_req_elem_size(), reqs,
-			       sizeof(*reqs) * avail);
+			memcpy(fifo_at(dbc->req_q_base, tail), reqs, sizeof(*reqs) * avail);
 			last_req = reqs + avail;
 			avail = first_n - avail;
 			if (avail)
 				memcpy(dbc->req_q_base, last_req, sizeof(*reqs) * avail);
 		} else {
-			memcpy(dbc->req_q_base + tail * get_dbc_req_elem_size(), reqs,
-			       sizeof(*reqs) * first_n);
+			memcpy(fifo_at(dbc->req_q_base, tail), reqs, sizeof(*reqs) * first_n);
 		}
 	}
 
-	/* Copy over the last entry. Here we need to adjust len to the left over
+	/*
+	 * Copy over the last entry. Here we need to adjust len to the left over
 	 * size, and set src and dst to the entry it is copied to.
 	 */
-	last_req = dbc->req_q_base + (tail + first_n) % dbc->nelem * get_dbc_req_elem_size();
+	last_req = fifo_at(dbc->req_q_base, (tail + first_n) % dbc->nelem);
 	memcpy(last_req, reqs + slice->nents - 1, sizeof(*reqs));
 
 	/*
@@ -1168,6 +1156,9 @@ static inline int copy_partial_exec_reqs(struct qaic_device *qdev, struct bo_sli
 	last_req->len = cpu_to_le32((u32)last_bytes);
 	last_req->src_addr = reqs[first_n].src_addr;
 	last_req->dest_addr = reqs[first_n].dest_addr;
+	if (!last_bytes)
+		/* Disable DMA transfer */
+		last_req->cmd = GENMASK(7, 2) & reqs[first_n].cmd;
 
 	*ptail = (tail + first_n + 1) % dbc->nelem;
 
@@ -1227,26 +1218,17 @@ static int send_bo_list_to_device(struct qaic_device *qdev, struct drm_file *fil
 		bo->req_id = dbc->next_req_id++;
 
 		list_for_each_entry(slice, &bo->slices, slice) {
-			/*
-			 * If this slice does not fall under the given
-			 * resize then skip this slice and continue the loop
-			 */
-			if (is_partial && pexec[i].resize && pexec[i].resize <= slice->offset)
-				continue;
-
 			for (j = 0; j < slice->nents; j++)
 				slice->reqs[j].req_id = cpu_to_le16(bo->req_id);
 
-			/*
-			 * If it is a partial execute ioctl call then check if
-			 * resize has cut this slice short then do a partial copy
-			 * else do complete copy
-			 */
-			if (is_partial && pexec[i].resize &&
-			    pexec[i].resize < slice->offset + slice->size)
+			if (is_partial && (!pexec[i].resize || pexec[i].resize <= slice->offset))
+				/* Configure the slice for no DMA transfer */
+				ret = copy_partial_exec_reqs(qdev, slice, 0, dbc, head, tail);
+			else if (is_partial && pexec[i].resize < slice->offset + slice->size)
+				/* Configure the slice to be partially DMA transferred */
 				ret = copy_partial_exec_reqs(qdev, slice,
-							     pexec[i].resize - slice->offset,
-							     dbc->id, head, tail);
+							     pexec[i].resize - slice->offset, dbc,
+							     head, tail);
 			else
 				ret = copy_exec_reqs(qdev, slice, dbc->id, head, tail);
 			if (ret) {
-- 
cgit 


From c015fb6d01adb616fb54824feb55ce5ab18e8ca1 Mon Sep 17 00:00:00 2001
From: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Date: Mon, 6 Nov 2023 14:08:26 +0100
Subject: accel/ivpu: Fix compilation with CONFIG_PM=n

Use pm_runtime_status_suspended() instead of dev->power.runtime_status
field that is not available without PM.

Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://lore.kernel.org/all/20231106130827.1600948-1-jacek.lawrynowicz@linux.intel.com
---
 drivers/accel/ivpu/ivpu_ipc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/ivpu/ivpu_ipc.c b/drivers/accel/ivpu/ivpu_ipc.c
index 255f2b8b0b5e..618dbc17df80 100644
--- a/drivers/accel/ivpu/ivpu_ipc.c
+++ b/drivers/accel/ivpu/ivpu_ipc.c
@@ -6,6 +6,7 @@
 #include <linux/genalloc.h>
 #include <linux/highmem.h>
 #include <linux/kthread.h>
+#include <linux/pm_runtime.h>
 #include <linux/wait.h>
 
 #include "ivpu_drv.h"
@@ -318,8 +319,7 @@ int ivpu_ipc_send_receive_active(struct ivpu_device *vdev, struct vpu_jsm_msg *r
 	struct vpu_jsm_msg hb_resp;
 	int ret, hb_ret;
 
-	drm_WARN_ON(&vdev->drm,
-		    vdev->drm.dev->power.runtime_status == RPM_SUSPENDED);
+	drm_WARN_ON(&vdev->drm, pm_runtime_status_suspended(vdev->drm.dev));
 
 	ret = ivpu_ipc_send_receive_internal(vdev, req, expected_resp, resp, channel, timeout_ms);
 	if (ret != -ETIMEDOUT)
-- 
cgit 


From b035224134626f506c1af73ca32bbc64dd2925ad Mon Sep 17 00:00:00 2001
From: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Date: Tue, 31 Oct 2023 08:31:53 +0100
Subject: accel/ivpu: Allocate vpu_addr in gem->open() callback

Use gem->open() callback to simplify the code and prepare for gem_shmem
conversion. It is called during handle creation for a gem object,
during prime import and in BO_CREATE ioctl. Hence can be used for vpu_addr
allocation. On the way remove unused bo->user_ptr field.

Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231031073156.1301669-2-stanislaw.gruszka@linux.intel.com
---
 drivers/accel/ivpu/ivpu_gem.c         | 66 ++++++++++++++++-------------------
 drivers/accel/ivpu/ivpu_gem.h         |  1 -
 drivers/accel/ivpu/ivpu_mmu_context.c |  2 ++
 3 files changed, 32 insertions(+), 37 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/ivpu/ivpu_gem.c b/drivers/accel/ivpu/ivpu_gem.c
index c91852f2edc8..d1077cf90b65 100644
--- a/drivers/accel/ivpu/ivpu_gem.c
+++ b/drivers/accel/ivpu/ivpu_gem.c
@@ -281,15 +281,6 @@ ivpu_bo_alloc_vpu_addr(struct ivpu_bo *bo, struct ivpu_mmu_context *ctx,
 	struct ivpu_device *vdev = ivpu_bo_to_vdev(bo);
 	int ret;
 
-	if (!range) {
-		if (bo->flags & DRM_IVPU_BO_SHAVE_MEM)
-			range = &vdev->hw->ranges.shave;
-		else if (bo->flags & DRM_IVPU_BO_DMA_MEM)
-			range = &vdev->hw->ranges.dma;
-		else
-			range = &vdev->hw->ranges.user;
-	}
-
 	mutex_lock(&ctx->lock);
 	ret = ivpu_mmu_context_insert_node_locked(ctx, range, ivpu_bo_size(bo), &bo->mm_node);
 	if (!ret) {
@@ -299,6 +290,9 @@ ivpu_bo_alloc_vpu_addr(struct ivpu_bo *bo, struct ivpu_mmu_context *ctx,
 	}
 	mutex_unlock(&ctx->lock);
 
+	if (ret)
+		ivpu_err(vdev, "Failed to add BO to context %u: %d\n", ctx->id, ret);
+
 	return ret;
 }
 
@@ -337,9 +331,7 @@ void ivpu_bo_remove_all_bos_from_context(struct ivpu_mmu_context *ctx)
 }
 
 static struct ivpu_bo *
-ivpu_bo_alloc(struct ivpu_device *vdev, struct ivpu_mmu_context *mmu_context,
-	      u64 size, u32 flags, const struct ivpu_bo_ops *ops,
-	      const struct ivpu_addr_range *range, u64 user_ptr)
+ivpu_bo_alloc(struct ivpu_device *vdev, u64 size, u32 flags, const struct ivpu_bo_ops *ops)
 {
 	struct ivpu_bo *bo;
 	int ret = 0;
@@ -364,7 +356,6 @@ ivpu_bo_alloc(struct ivpu_device *vdev, struct ivpu_mmu_context *mmu_context,
 	bo->base.funcs = &ivpu_gem_funcs;
 	bo->flags = flags;
 	bo->ops = ops;
-	bo->user_ptr = user_ptr;
 
 	if (ops->type == IVPU_BO_TYPE_SHMEM)
 		ret = drm_gem_object_init(&vdev->drm, &bo->base, size);
@@ -384,14 +375,6 @@ ivpu_bo_alloc(struct ivpu_device *vdev, struct ivpu_mmu_context *mmu_context,
 		}
 	}
 
-	if (mmu_context) {
-		ret = ivpu_bo_alloc_vpu_addr(bo, mmu_context, range);
-		if (ret) {
-			ivpu_err(vdev, "Failed to add BO to context: %d\n", ret);
-			goto err_release;
-		}
-	}
-
 	return bo;
 
 err_release:
@@ -401,6 +384,23 @@ err_free:
 	return ERR_PTR(ret);
 }
 
+static int ivpu_bo_open(struct drm_gem_object *obj, struct drm_file *file)
+{
+	struct ivpu_file_priv *file_priv = file->driver_priv;
+	struct ivpu_device *vdev = file_priv->vdev;
+	struct ivpu_bo *bo = to_ivpu_bo(obj);
+	struct ivpu_addr_range *range;
+
+	if (bo->flags & DRM_IVPU_BO_SHAVE_MEM)
+		range = &vdev->hw->ranges.shave;
+	else if (bo->flags & DRM_IVPU_BO_DMA_MEM)
+		range = &vdev->hw->ranges.dma;
+	else
+		range = &vdev->hw->ranges.user;
+
+	return ivpu_bo_alloc_vpu_addr(bo, &file_priv->ctx, range);
+}
+
 static void ivpu_bo_free(struct drm_gem_object *obj)
 {
 	struct ivpu_bo *bo = to_ivpu_bo(obj);
@@ -516,6 +516,7 @@ static const struct vm_operations_struct ivpu_vm_ops = {
 
 static const struct drm_gem_object_funcs ivpu_gem_funcs = {
 	.free = ivpu_bo_free,
+	.open = ivpu_bo_open,
 	.mmap = ivpu_bo_mmap,
 	.vm_ops = &ivpu_vm_ops,
 	.get_sg_table = ivpu_bo_get_sg_table,
@@ -537,7 +538,7 @@ ivpu_bo_create_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	if (size == 0)
 		return -EINVAL;
 
-	bo = ivpu_bo_alloc(vdev, &file_priv->ctx, size, args->flags, &shmem_ops, NULL, 0);
+	bo = ivpu_bo_alloc(vdev, size, args->flags, &shmem_ops);
 	if (IS_ERR(bo)) {
 		ivpu_err(vdev, "Failed to create BO: %pe (ctx %u size %llu flags 0x%x)",
 			 bo, file_priv->ctx.id, args->size, args->flags);
@@ -578,13 +579,17 @@ ivpu_bo_alloc_internal(struct ivpu_device *vdev, u64 vpu_addr, u64 size, u32 fla
 		range = &vdev->hw->ranges.global;
 	}
 
-	bo = ivpu_bo_alloc(vdev, &vdev->gctx, size, flags, &internal_ops, range, 0);
+	bo = ivpu_bo_alloc(vdev, size, flags, &internal_ops);
 	if (IS_ERR(bo)) {
 		ivpu_err(vdev, "Failed to create BO: %pe (vpu_addr 0x%llx size %llu flags 0x%x)",
 			 bo, vpu_addr, size, flags);
 		return NULL;
 	}
 
+	ret = ivpu_bo_alloc_vpu_addr(bo, &vdev->gctx, range);
+	if (ret)
+		goto err_put;
+
 	ret = ivpu_bo_pin(bo);
 	if (ret)
 		goto err_put;
@@ -631,7 +636,7 @@ struct drm_gem_object *ivpu_gem_prime_import(struct drm_device *dev, struct dma_
 
 	get_dma_buf(buf);
 
-	bo = ivpu_bo_alloc(vdev, NULL, buf->size, DRM_IVPU_BO_MAPPABLE, &prime_ops, NULL, 0);
+	bo = ivpu_bo_alloc(vdev, buf->size, DRM_IVPU_BO_MAPPABLE, &prime_ops);
 	if (IS_ERR(bo)) {
 		ivpu_err(vdev, "Failed to import BO: %pe (size %lu)", bo, buf->size);
 		goto err_detach;
@@ -651,8 +656,6 @@ err_detach:
 
 int ivpu_bo_info_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 {
-	struct ivpu_file_priv *file_priv = file->driver_priv;
-	struct ivpu_device *vdev = to_ivpu_device(dev);
 	struct drm_ivpu_bo_info *args = data;
 	struct drm_gem_object *obj;
 	struct ivpu_bo *bo;
@@ -665,21 +668,12 @@ int ivpu_bo_info_ioctl(struct drm_device *dev, void *data, struct drm_file *file
 	bo = to_ivpu_bo(obj);
 
 	mutex_lock(&bo->lock);
-
-	if (!bo->ctx) {
-		ret = ivpu_bo_alloc_vpu_addr(bo, &file_priv->ctx, NULL);
-		if (ret) {
-			ivpu_err(vdev, "Failed to allocate vpu_addr: %d\n", ret);
-			goto unlock;
-		}
-	}
-
 	args->flags = bo->flags;
 	args->mmap_offset = drm_vma_node_offset_addr(&obj->vma_node);
 	args->vpu_addr = bo->vpu_addr;
 	args->size = obj->size;
-unlock:
 	mutex_unlock(&bo->lock);
+
 	drm_gem_object_put(obj);
 	return ret;
 }
diff --git a/drivers/accel/ivpu/ivpu_gem.h b/drivers/accel/ivpu/ivpu_gem.h
index a0b4d4a32b3b..9bbbcd779265 100644
--- a/drivers/accel/ivpu/ivpu_gem.h
+++ b/drivers/accel/ivpu/ivpu_gem.h
@@ -29,7 +29,6 @@ struct ivpu_bo {
 	u64 vpu_addr;
 	u32 handle;
 	u32 flags;
-	uintptr_t user_ptr;
 	u32 job_status;
 };
 
diff --git a/drivers/accel/ivpu/ivpu_mmu_context.c b/drivers/accel/ivpu/ivpu_mmu_context.c
index 7d8005bc78d2..f6de6a4ea608 100644
--- a/drivers/accel/ivpu/ivpu_mmu_context.c
+++ b/drivers/accel/ivpu/ivpu_mmu_context.c
@@ -410,6 +410,8 @@ ivpu_mmu_context_insert_node_locked(struct ivpu_mmu_context *ctx,
 {
 	lockdep_assert_held(&ctx->lock);
 
+	WARN_ON(!range);
+
 	if (!ivpu_disable_mmu_cont_pages && size >= IVPU_MMU_CONT_PAGES_SIZE) {
 		if (!drm_mm_insert_node_in_range(&ctx->mm, node, size, IVPU_MMU_CONT_PAGES_SIZE, 0,
 						 range->start, range->end, DRM_MM_INSERT_BEST))
-- 
cgit 


From 48aea7f2a2efae6a1bd201061c71a81b3f3b7e55 Mon Sep 17 00:00:00 2001
From: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Date: Tue, 31 Oct 2023 08:31:54 +0100
Subject: accel/ivpu: Fix locking in ivpu_bo_remove_all_bos_from_context()

ivpu_bo_remove_all_bos_from_context() could race with ivpu_bo_free()
when prime buffer was closed after vpu device was closed.

Move the bo_list from context to vdev and use a dedicated lock to
sync it. This list is not modified when BO is added/removed from
a context.

Also rename ivpu_bo_free_vpu_addr() to ivpu_bo_unbind() because this
function does more then just free vpu_addr.

Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231031073156.1301669-3-stanislaw.gruszka@linux.intel.com
---
 drivers/accel/ivpu/ivpu_drv.c         |   7 +-
 drivers/accel/ivpu/ivpu_drv.h         |   3 +
 drivers/accel/ivpu/ivpu_gem.c         | 131 ++++++++++++++++++----------------
 drivers/accel/ivpu/ivpu_gem.h         |   6 +-
 drivers/accel/ivpu/ivpu_mmu.c         |   5 +-
 drivers/accel/ivpu/ivpu_mmu_context.c |  36 ++++++----
 drivers/accel/ivpu/ivpu_mmu_context.h |  11 ++-
 7 files changed, 109 insertions(+), 90 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c
index 60277ff6af69..cc6a4dca2aaa 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -91,8 +91,8 @@ static void file_priv_release(struct kref *ref)
 	ivpu_dbg(vdev, FILE, "file_priv release: ctx %u\n", file_priv->ctx.id);
 
 	ivpu_cmdq_release_all(file_priv);
-	ivpu_bo_remove_all_bos_from_context(&file_priv->ctx);
 	ivpu_jsm_context_release(vdev, file_priv->ctx.id);
+	ivpu_bo_remove_all_bos_from_context(vdev, &file_priv->ctx);
 	ivpu_mmu_user_context_fini(vdev, &file_priv->ctx);
 	drm_WARN_ON(&vdev->drm, xa_erase_irq(&vdev->context_xa, file_priv->ctx.id) != file_priv);
 	mutex_destroy(&file_priv->lock);
@@ -528,6 +528,11 @@ static int ivpu_dev_init(struct ivpu_device *vdev)
 	xa_init_flags(&vdev->context_xa, XA_FLAGS_ALLOC);
 	xa_init_flags(&vdev->submitted_jobs_xa, XA_FLAGS_ALLOC1);
 	lockdep_set_class(&vdev->submitted_jobs_xa.xa_lock, &submitted_jobs_xa_lock_class_key);
+	INIT_LIST_HEAD(&vdev->bo_list);
+
+	ret = drmm_mutex_init(&vdev->drm, &vdev->bo_list_lock);
+	if (ret)
+		goto err_xa_destroy;
 
 	ret = ivpu_pci_init(vdev);
 	if (ret)
diff --git a/drivers/accel/ivpu/ivpu_drv.h b/drivers/accel/ivpu/ivpu_drv.h
index 79b193ffbc26..e0517ec4133d 100644
--- a/drivers/accel/ivpu/ivpu_drv.h
+++ b/drivers/accel/ivpu/ivpu_drv.h
@@ -115,6 +115,9 @@ struct ivpu_device {
 	struct xarray context_xa;
 	struct xa_limit context_xa_limit;
 
+	struct mutex bo_list_lock; /* Protects bo_list */
+	struct list_head bo_list;
+
 	struct xarray submitted_jobs_xa;
 	struct task_struct *job_done_thread;
 
diff --git a/drivers/accel/ivpu/ivpu_gem.c b/drivers/accel/ivpu/ivpu_gem.c
index d1077cf90b65..915c53d7bb97 100644
--- a/drivers/accel/ivpu/ivpu_gem.c
+++ b/drivers/accel/ivpu/ivpu_gem.c
@@ -26,6 +26,17 @@ static const struct drm_gem_object_funcs ivpu_gem_funcs;
 
 static struct lock_class_key prime_bo_lock_class_key;
 
+static inline void ivpu_dbg_bo(struct ivpu_device *vdev, struct ivpu_bo *bo, const char *action)
+{
+	if (bo->ctx)
+		ivpu_dbg(vdev, BO, "%6s: size %zu has_pages %d dma_mapped %d handle %u ctx %d vpu_addr 0x%llx mmu_mapped %d\n",
+			 action, bo->base.size, (bool)bo->pages, (bool)bo->sgt, bo->handle,
+			 bo->ctx->id, bo->vpu_addr, bo->mmu_mapped);
+	else
+		ivpu_dbg(vdev, BO, "%6s: size %zu has_pages %d dma_mapped %d handle %u (not added to context)\n",
+			 action, bo->base.size, (bool)bo->pages, (bool)bo->sgt, bo->handle);
+}
+
 static int __must_check prime_alloc_pages_locked(struct ivpu_bo *bo)
 {
 	/* Pages are managed by the underlying dma-buf */
@@ -245,9 +256,8 @@ int __must_check ivpu_bo_pin(struct ivpu_bo *bo)
 
 	mutex_lock(&bo->lock);
 
-	if (!bo->vpu_addr) {
-		ivpu_err(vdev, "vpu_addr not set for BO ctx_id: %d handle: %d\n",
-			 bo->ctx->id, bo->handle);
+	if (!bo->ctx) {
+		ivpu_err(vdev, "vpu_addr not allocated for BO %d\n", bo->handle);
 		ret = -EINVAL;
 		goto unlock;
 	}
@@ -281,53 +291,68 @@ ivpu_bo_alloc_vpu_addr(struct ivpu_bo *bo, struct ivpu_mmu_context *ctx,
 	struct ivpu_device *vdev = ivpu_bo_to_vdev(bo);
 	int ret;
 
-	mutex_lock(&ctx->lock);
-	ret = ivpu_mmu_context_insert_node_locked(ctx, range, ivpu_bo_size(bo), &bo->mm_node);
+	mutex_lock(&bo->lock);
+
+	ret = ivpu_mmu_context_insert_node(ctx, range, bo->base.size, &bo->mm_node);
 	if (!ret) {
 		bo->ctx = ctx;
 		bo->vpu_addr = bo->mm_node.start;
-		list_add_tail(&bo->ctx_node, &ctx->bo_list);
+	} else {
+		ivpu_err(vdev, "Failed to add BO to context %u: %d\n", ctx->id, ret);
 	}
-	mutex_unlock(&ctx->lock);
+	ivpu_dbg_bo(vdev, bo, "alloc");
 
-	if (ret)
-		ivpu_err(vdev, "Failed to add BO to context %u: %d\n", ctx->id, ret);
+	mutex_unlock(&bo->lock);
 
 	return ret;
 }
 
-static void ivpu_bo_free_vpu_addr(struct ivpu_bo *bo)
+static void ivpu_bo_unbind_locked(struct ivpu_bo *bo)
 {
 	struct ivpu_device *vdev = ivpu_bo_to_vdev(bo);
-	struct ivpu_mmu_context *ctx = bo->ctx;
 
-	ivpu_dbg(vdev, BO, "remove from ctx: ctx %d vpu_addr 0x%llx allocated %d mmu_mapped %d\n",
-		 ctx->id, bo->vpu_addr, (bool)bo->sgt, bo->mmu_mapped);
+	lockdep_assert_held(&bo->lock);
 
-	mutex_lock(&bo->lock);
+	ivpu_dbg_bo(vdev, bo, "unbind");
 
+	/* TODO: dma_unmap */
 	if (bo->mmu_mapped) {
+		drm_WARN_ON(&vdev->drm, !bo->ctx);
+		drm_WARN_ON(&vdev->drm, !bo->vpu_addr);
 		drm_WARN_ON(&vdev->drm, !bo->sgt);
-		ivpu_mmu_context_unmap_sgt(vdev, ctx, bo->vpu_addr, bo->sgt);
+		ivpu_mmu_context_unmap_sgt(vdev, bo->ctx, bo->vpu_addr, bo->sgt);
 		bo->mmu_mapped = false;
 	}
 
-	mutex_lock(&ctx->lock);
-	list_del(&bo->ctx_node);
-	bo->vpu_addr = 0;
-	bo->ctx = NULL;
-	ivpu_mmu_context_remove_node_locked(ctx, &bo->mm_node);
-	mutex_unlock(&ctx->lock);
+	if (bo->ctx) {
+		ivpu_mmu_context_remove_node(bo->ctx, &bo->mm_node);
+		bo->vpu_addr = 0;
+		bo->ctx = NULL;
+	}
+}
 
+static void ivpu_bo_unbind(struct ivpu_bo *bo)
+{
+	mutex_lock(&bo->lock);
+	ivpu_bo_unbind_locked(bo);
 	mutex_unlock(&bo->lock);
 }
 
-void ivpu_bo_remove_all_bos_from_context(struct ivpu_mmu_context *ctx)
+void ivpu_bo_remove_all_bos_from_context(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx)
 {
-	struct ivpu_bo *bo, *tmp;
+	struct ivpu_bo *bo;
+
+	if (drm_WARN_ON(&vdev->drm, !ctx))
+		return;
 
-	list_for_each_entry_safe(bo, tmp, &ctx->bo_list, ctx_node)
-		ivpu_bo_free_vpu_addr(bo);
+	mutex_lock(&vdev->bo_list_lock);
+	list_for_each_entry(bo, &vdev->bo_list, bo_list_node) {
+		mutex_lock(&bo->lock);
+		if (bo->ctx == ctx)
+			ivpu_bo_unbind_locked(bo);
+		mutex_unlock(&bo->lock);
+	}
+	mutex_unlock(&vdev->bo_list_lock);
 }
 
 static struct ivpu_bo *
@@ -375,6 +400,10 @@ ivpu_bo_alloc(struct ivpu_device *vdev, u64 size, u32 flags, const struct ivpu_b
 		}
 	}
 
+	mutex_lock(&vdev->bo_list_lock);
+	list_add_tail(&bo->bo_list_node, &vdev->bo_list);
+	mutex_unlock(&vdev->bo_list_lock);
+
 	return bo;
 
 err_release:
@@ -406,19 +435,16 @@ static void ivpu_bo_free(struct drm_gem_object *obj)
 	struct ivpu_bo *bo = to_ivpu_bo(obj);
 	struct ivpu_device *vdev = ivpu_bo_to_vdev(bo);
 
-	if (bo->ctx)
-		ivpu_dbg(vdev, BO, "free: ctx %d vpu_addr 0x%llx allocated %d mmu_mapped %d\n",
-			 bo->ctx->id, bo->vpu_addr, (bool)bo->sgt, bo->mmu_mapped);
-	else
-		ivpu_dbg(vdev, BO, "free: ctx (released) allocated %d mmu_mapped %d\n",
-			 (bool)bo->sgt, bo->mmu_mapped);
+	mutex_lock(&vdev->bo_list_lock);
+	list_del(&bo->bo_list_node);
+	mutex_unlock(&vdev->bo_list_lock);
 
 	drm_WARN_ON(&vdev->drm, !dma_resv_test_signaled(obj->resv, DMA_RESV_USAGE_READ));
 
-	vunmap(bo->kvaddr);
+	ivpu_dbg_bo(vdev, bo, "free");
 
-	if (bo->ctx)
-		ivpu_bo_free_vpu_addr(bo);
+	ivpu_bo_unbind(bo);
+	vunmap(bo->kvaddr);
 
 	if (bo->sgt)
 		ivpu_bo_unmap_and_free_pages(bo);
@@ -435,10 +461,6 @@ static void ivpu_bo_free(struct drm_gem_object *obj)
 static int ivpu_bo_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma)
 {
 	struct ivpu_bo *bo = to_ivpu_bo(obj);
-	struct ivpu_device *vdev = ivpu_bo_to_vdev(bo);
-
-	ivpu_dbg(vdev, BO, "mmap: ctx %u handle %u vpu_addr 0x%llx size %zu type %s",
-		 bo->ctx->id, bo->handle, bo->vpu_addr, ivpu_bo_size(bo), bo->ops->name);
 
 	if (obj->import_attach) {
 		/* Drop the reference drm_gem_mmap_obj() acquired.*/
@@ -553,9 +575,6 @@ ivpu_bo_create_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 
 	drm_gem_object_put(&bo->base);
 
-	ivpu_dbg(vdev, BO, "alloc shmem: ctx %u vpu_addr 0x%llx size %zu flags 0x%x\n",
-		 file_priv->ctx.id, bo->vpu_addr, ivpu_bo_size(bo), bo->flags);
-
 	return ret;
 }
 
@@ -609,9 +628,6 @@ ivpu_bo_alloc_internal(struct ivpu_device *vdev, u64 vpu_addr, u64 size, u32 fla
 		goto err_put;
 	}
 
-	ivpu_dbg(vdev, BO, "alloc internal: ctx 0 vpu_addr 0x%llx size %zu flags 0x%x\n",
-		 bo->vpu_addr, ivpu_bo_size(bo), flags);
-
 	return bo;
 
 err_put:
@@ -708,41 +724,30 @@ static void ivpu_bo_print_info(struct ivpu_bo *bo, struct drm_printer *p)
 {
 	unsigned long dma_refcount = 0;
 
+	mutex_lock(&bo->lock);
+
 	if (bo->base.dma_buf && bo->base.dma_buf->file)
 		dma_refcount = atomic_long_read(&bo->base.dma_buf->file->f_count);
 
 	drm_printf(p, "%5u %6d %16llx %10lu %10u %12lu %14s\n",
-		   bo->ctx->id, bo->handle, bo->vpu_addr, ivpu_bo_size(bo),
+		   bo->ctx ? bo->ctx->id : -1, bo->handle, bo->vpu_addr, bo->base.size,
 		   kref_read(&bo->base.refcount), dma_refcount, bo->ops->name);
+
+	mutex_unlock(&bo->lock);
 }
 
 void ivpu_bo_list(struct drm_device *dev, struct drm_printer *p)
 {
 	struct ivpu_device *vdev = to_ivpu_device(dev);
-	struct ivpu_file_priv *file_priv;
-	unsigned long ctx_id;
 	struct ivpu_bo *bo;
 
 	drm_printf(p, "%5s %6s %16s %10s %10s %12s %14s\n",
 		   "ctx", "handle", "vpu_addr", "size", "refcount", "dma_refcount", "type");
 
-	mutex_lock(&vdev->gctx.lock);
-	list_for_each_entry(bo, &vdev->gctx.bo_list, ctx_node)
+	mutex_lock(&vdev->bo_list_lock);
+	list_for_each_entry(bo, &vdev->bo_list, bo_list_node)
 		ivpu_bo_print_info(bo, p);
-	mutex_unlock(&vdev->gctx.lock);
-
-	xa_for_each(&vdev->context_xa, ctx_id, file_priv) {
-		file_priv = ivpu_file_priv_get_by_ctx_id(vdev, ctx_id);
-		if (!file_priv)
-			continue;
-
-		mutex_lock(&file_priv->ctx.lock);
-		list_for_each_entry(bo, &file_priv->ctx.bo_list, ctx_node)
-			ivpu_bo_print_info(bo, p);
-		mutex_unlock(&file_priv->ctx.lock);
-
-		ivpu_file_priv_put(&file_priv);
-	}
+	mutex_unlock(&vdev->bo_list_lock);
 }
 
 void ivpu_bo_list_print(struct drm_device *dev)
diff --git a/drivers/accel/ivpu/ivpu_gem.h b/drivers/accel/ivpu/ivpu_gem.h
index 9bbbcd779265..214d8fd14310 100644
--- a/drivers/accel/ivpu/ivpu_gem.h
+++ b/drivers/accel/ivpu/ivpu_gem.h
@@ -17,10 +17,10 @@ struct ivpu_bo {
 	const struct ivpu_bo_ops *ops;
 
 	struct ivpu_mmu_context *ctx;
-	struct list_head ctx_node;
+	struct list_head bo_list_node;
 	struct drm_mm_node mm_node;
 
-	struct mutex lock; /* Protects: pages, sgt, mmu_mapped */
+	struct mutex lock; /* Protects: pages, sgt, ctx, mmu_mapped, vpu_addr */
 	struct sg_table *sgt;
 	struct page **pages;
 	bool mmu_mapped;
@@ -48,7 +48,7 @@ struct ivpu_bo_ops {
 };
 
 int ivpu_bo_pin(struct ivpu_bo *bo);
-void ivpu_bo_remove_all_bos_from_context(struct ivpu_mmu_context *ctx);
+void ivpu_bo_remove_all_bos_from_context(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx);
 void ivpu_bo_list(struct drm_device *dev, struct drm_printer *p);
 void ivpu_bo_list_print(struct drm_device *dev);
 
diff --git a/drivers/accel/ivpu/ivpu_mmu.c b/drivers/accel/ivpu/ivpu_mmu.c
index b46f3743c0e7..2228c44b115f 100644
--- a/drivers/accel/ivpu/ivpu_mmu.c
+++ b/drivers/accel/ivpu/ivpu_mmu.c
@@ -775,9 +775,12 @@ int ivpu_mmu_init(struct ivpu_device *vdev)
 
 	ivpu_dbg(vdev, MMU, "Init..\n");
 
-	drmm_mutex_init(&vdev->drm, &mmu->lock);
 	ivpu_mmu_config_check(vdev);
 
+	ret = drmm_mutex_init(&vdev->drm, &mmu->lock);
+	if (ret)
+		return ret;
+
 	ret = ivpu_mmu_structs_alloc(vdev);
 	if (ret)
 		return ret;
diff --git a/drivers/accel/ivpu/ivpu_mmu_context.c b/drivers/accel/ivpu/ivpu_mmu_context.c
index f6de6a4ea608..122c90fecf66 100644
--- a/drivers/accel/ivpu/ivpu_mmu_context.c
+++ b/drivers/accel/ivpu/ivpu_mmu_context.c
@@ -335,6 +335,9 @@ ivpu_mmu_context_map_sgt(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx,
 	u64 prot;
 	u64 i;
 
+	if (drm_WARN_ON(&vdev->drm, !ctx))
+		return -EINVAL;
+
 	if (!IS_ALIGNED(vpu_addr, IVPU_MMU_PAGE_SIZE))
 		return -EINVAL;
 	/*
@@ -382,8 +385,8 @@ ivpu_mmu_context_unmap_sgt(struct ivpu_device *vdev, struct ivpu_mmu_context *ct
 	int ret;
 	u64 i;
 
-	if (!IS_ALIGNED(vpu_addr, IVPU_MMU_PAGE_SIZE))
-		ivpu_warn(vdev, "Unaligned vpu_addr: 0x%llx\n", vpu_addr);
+	if (drm_WARN_ON(&vdev->drm, !ctx))
+		return;
 
 	mutex_lock(&ctx->lock);
 
@@ -404,30 +407,34 @@ ivpu_mmu_context_unmap_sgt(struct ivpu_device *vdev, struct ivpu_mmu_context *ct
 }
 
 int
-ivpu_mmu_context_insert_node_locked(struct ivpu_mmu_context *ctx,
-				    const struct ivpu_addr_range *range,
-				    u64 size, struct drm_mm_node *node)
+ivpu_mmu_context_insert_node(struct ivpu_mmu_context *ctx, const struct ivpu_addr_range *range,
+			     u64 size, struct drm_mm_node *node)
 {
-	lockdep_assert_held(&ctx->lock);
+	int ret;
 
 	WARN_ON(!range);
 
+	mutex_lock(&ctx->lock);
 	if (!ivpu_disable_mmu_cont_pages && size >= IVPU_MMU_CONT_PAGES_SIZE) {
-		if (!drm_mm_insert_node_in_range(&ctx->mm, node, size, IVPU_MMU_CONT_PAGES_SIZE, 0,
-						 range->start, range->end, DRM_MM_INSERT_BEST))
-			return 0;
+		ret = drm_mm_insert_node_in_range(&ctx->mm, node, size, IVPU_MMU_CONT_PAGES_SIZE, 0,
+						  range->start, range->end, DRM_MM_INSERT_BEST);
+		if (!ret)
+			goto unlock;
 	}
 
-	return drm_mm_insert_node_in_range(&ctx->mm, node, size, IVPU_MMU_PAGE_SIZE, 0,
-					   range->start, range->end, DRM_MM_INSERT_BEST);
+	ret = drm_mm_insert_node_in_range(&ctx->mm, node, size, IVPU_MMU_PAGE_SIZE, 0,
+					  range->start, range->end, DRM_MM_INSERT_BEST);
+unlock:
+	mutex_unlock(&ctx->lock);
+	return ret;
 }
 
 void
-ivpu_mmu_context_remove_node_locked(struct ivpu_mmu_context *ctx, struct drm_mm_node *node)
+ivpu_mmu_context_remove_node(struct ivpu_mmu_context *ctx, struct drm_mm_node *node)
 {
-	lockdep_assert_held(&ctx->lock);
-
+	mutex_lock(&ctx->lock);
 	drm_mm_remove_node(node);
+	mutex_unlock(&ctx->lock);
 }
 
 static int
@@ -437,7 +444,6 @@ ivpu_mmu_context_init(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx, u3
 	int ret;
 
 	mutex_init(&ctx->lock);
-	INIT_LIST_HEAD(&ctx->bo_list);
 
 	ret = ivpu_mmu_pgtable_init(vdev, &ctx->pgtable);
 	if (ret) {
diff --git a/drivers/accel/ivpu/ivpu_mmu_context.h b/drivers/accel/ivpu/ivpu_mmu_context.h
index f15d8c630d8a..535db3a1fc74 100644
--- a/drivers/accel/ivpu/ivpu_mmu_context.h
+++ b/drivers/accel/ivpu/ivpu_mmu_context.h
@@ -23,10 +23,9 @@ struct ivpu_mmu_pgtable {
 };
 
 struct ivpu_mmu_context {
-	struct mutex lock; /* protects: mm, pgtable, bo_list */
+	struct mutex lock; /* Protects: mm, pgtable */
 	struct drm_mm mm;
 	struct ivpu_mmu_pgtable pgtable;
-	struct list_head bo_list;
 	u32 id;
 };
 
@@ -39,11 +38,9 @@ int ivpu_mmu_user_context_init(struct ivpu_device *vdev, struct ivpu_mmu_context
 void ivpu_mmu_user_context_fini(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx);
 void ivpu_mmu_user_context_mark_invalid(struct ivpu_device *vdev, u32 ssid);
 
-int ivpu_mmu_context_insert_node_locked(struct ivpu_mmu_context *ctx,
-					const struct ivpu_addr_range *range,
-					u64 size, struct drm_mm_node *node);
-void ivpu_mmu_context_remove_node_locked(struct ivpu_mmu_context *ctx,
-					 struct drm_mm_node *node);
+int ivpu_mmu_context_insert_node(struct ivpu_mmu_context *ctx, const struct ivpu_addr_range *range,
+				 u64 size, struct drm_mm_node *node);
+void ivpu_mmu_context_remove_node(struct ivpu_mmu_context *ctx, struct drm_mm_node *node);
 
 int ivpu_mmu_context_map_sgt(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx,
 			     u64 vpu_addr, struct sg_table *sgt, bool llc_coherent);
-- 
cgit 


From 48d45fac3940347becd290b96b2fc6d5ad8171f7 Mon Sep 17 00:00:00 2001
From: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Date: Tue, 31 Oct 2023 08:31:55 +0100
Subject: accel/ivpu: Remove support for uncached buffers

Usages of DRM_IVPU_BO_UNCACHED should be replaced by DRM_IVPU_BO_WC.
There is no functional benefit from DRM_IVPU_BO_UNCACHED if these
buffers are never mapped to host VM.

This allows to cut the buffer handling code in the kernel driver
by half.

Usage of DRM_IVPU_BO_UNCACHED buffers was removed from user-space
driver and will not be part of first UMD release.

Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231031073156.1301669-4-stanislaw.gruszka@linux.intel.com
---
 drivers/accel/ivpu/ivpu_fw.c  | 2 +-
 drivers/accel/ivpu/ivpu_gem.c | 3 ---
 2 files changed, 1 insertion(+), 4 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/ivpu/ivpu_fw.c b/drivers/accel/ivpu/ivpu_fw.c
index 3fd74cd4205f..3d0c18d68f6c 100644
--- a/drivers/accel/ivpu/ivpu_fw.c
+++ b/drivers/accel/ivpu/ivpu_fw.c
@@ -286,7 +286,7 @@ static int ivpu_fw_mem_init(struct ivpu_device *vdev)
 
 	if (fw->shave_nn_size) {
 		fw->mem_shave_nn = ivpu_bo_alloc_internal(vdev, vdev->hw->ranges.shave.start,
-							  fw->shave_nn_size, DRM_IVPU_BO_UNCACHED);
+							  fw->shave_nn_size, DRM_IVPU_BO_WC);
 		if (!fw->mem_shave_nn) {
 			ivpu_err(vdev, "Failed to allocate shavenn buffer\n");
 			ret = -ENOMEM;
diff --git a/drivers/accel/ivpu/ivpu_gem.c b/drivers/accel/ivpu/ivpu_gem.c
index 915c53d7bb97..2a91eb1e3627 100644
--- a/drivers/accel/ivpu/ivpu_gem.c
+++ b/drivers/accel/ivpu/ivpu_gem.c
@@ -89,8 +89,6 @@ static int __must_check shmem_alloc_pages_locked(struct ivpu_bo *bo)
 
 	if (bo->flags & DRM_IVPU_BO_WC)
 		set_pages_array_wc(pages, npages);
-	else if (bo->flags & DRM_IVPU_BO_UNCACHED)
-		set_pages_array_uc(pages, npages);
 
 	bo->pages = pages;
 	return 0;
@@ -366,7 +364,6 @@ ivpu_bo_alloc(struct ivpu_device *vdev, u64 size, u32 flags, const struct ivpu_b
 
 	switch (flags & DRM_IVPU_BO_CACHE_MASK) {
 	case DRM_IVPU_BO_CACHED:
-	case DRM_IVPU_BO_UNCACHED:
 	case DRM_IVPU_BO_WC:
 		break;
 	default:
-- 
cgit 


From 8d88e4cdce4f5c56de55174a4d32ea9c06f7fa66 Mon Sep 17 00:00:00 2001
From: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Date: Tue, 31 Oct 2023 08:31:56 +0100
Subject: accel/ivpu: Use GEM shmem helper for all buffers

Use struct drm_gem_shmem_object as a base for struct ivpu_bo.
This cuts by 50% the buffer management code.

Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231031073156.1301669-5-stanislaw.gruszka@linux.intel.com
---
 drivers/accel/ivpu/Kconfig    |   2 +-
 drivers/accel/ivpu/ivpu_drv.c |   6 +-
 drivers/accel/ivpu/ivpu_gem.c | 518 ++++++++++--------------------------------
 drivers/accel/ivpu/ivpu_gem.h |  70 ++----
 drivers/accel/ivpu/ivpu_job.c |   8 +-
 5 files changed, 144 insertions(+), 460 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/ivpu/Kconfig b/drivers/accel/ivpu/Kconfig
index 82749e0da524..682c53245286 100644
--- a/drivers/accel/ivpu/Kconfig
+++ b/drivers/accel/ivpu/Kconfig
@@ -6,7 +6,7 @@ config DRM_ACCEL_IVPU
 	depends on X86_64 && !UML
 	depends on PCI && PCI_MSI
 	select FW_LOADER
-	select SHMEM
+	select DRM_GEM_SHMEM_HELPER
 	select GENERIC_ALLOCATOR
 	help
 	  Choose this option if you have a system with an 14th generation
diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c
index cc6a4dca2aaa..51fa60b6254c 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -360,7 +360,7 @@ int ivpu_boot(struct ivpu_device *vdev)
 	int ret;
 
 	/* Update boot params located at first 4KB of FW memory */
-	ivpu_fw_boot_params_setup(vdev, vdev->fw->mem->kvaddr);
+	ivpu_fw_boot_params_setup(vdev, ivpu_bo_vaddr(vdev->fw->mem));
 
 	ret = ivpu_hw_boot_fw(vdev);
 	if (ret) {
@@ -409,7 +409,9 @@ static const struct drm_driver driver = {
 
 	.open = ivpu_open,
 	.postclose = ivpu_postclose,
-	.gem_prime_import = ivpu_gem_prime_import,
+
+	.gem_create_object = ivpu_gem_create_object,
+	.gem_prime_import_sg_table = drm_gem_shmem_prime_import_sg_table,
 
 	.ioctls = ivpu_drm_ioctls,
 	.num_ioctls = ARRAY_SIZE(ivpu_drm_ioctls),
diff --git a/drivers/accel/ivpu/ivpu_gem.c b/drivers/accel/ivpu/ivpu_gem.c
index 2a91eb1e3627..1dda4f38ea25 100644
--- a/drivers/accel/ivpu/ivpu_gem.c
+++ b/drivers/accel/ivpu/ivpu_gem.c
@@ -20,224 +20,18 @@
 #include "ivpu_mmu.h"
 #include "ivpu_mmu_context.h"
 
-MODULE_IMPORT_NS(DMA_BUF);
-
 static const struct drm_gem_object_funcs ivpu_gem_funcs;
 
-static struct lock_class_key prime_bo_lock_class_key;
-
 static inline void ivpu_dbg_bo(struct ivpu_device *vdev, struct ivpu_bo *bo, const char *action)
 {
 	if (bo->ctx)
 		ivpu_dbg(vdev, BO, "%6s: size %zu has_pages %d dma_mapped %d handle %u ctx %d vpu_addr 0x%llx mmu_mapped %d\n",
-			 action, bo->base.size, (bool)bo->pages, (bool)bo->sgt, bo->handle,
-			 bo->ctx->id, bo->vpu_addr, bo->mmu_mapped);
+			 action, ivpu_bo_size(bo), (bool)bo->base.pages, (bool)bo->base.sgt,
+			 bo->handle, bo->ctx->id, bo->vpu_addr, bo->mmu_mapped);
 	else
 		ivpu_dbg(vdev, BO, "%6s: size %zu has_pages %d dma_mapped %d handle %u (not added to context)\n",
-			 action, bo->base.size, (bool)bo->pages, (bool)bo->sgt, bo->handle);
-}
-
-static int __must_check prime_alloc_pages_locked(struct ivpu_bo *bo)
-{
-	/* Pages are managed by the underlying dma-buf */
-	return 0;
-}
-
-static void prime_free_pages_locked(struct ivpu_bo *bo)
-{
-	/* Pages are managed by the underlying dma-buf */
-}
-
-static int prime_map_pages_locked(struct ivpu_bo *bo)
-{
-	struct ivpu_device *vdev = ivpu_bo_to_vdev(bo);
-	struct sg_table *sgt;
-
-	sgt = dma_buf_map_attachment_unlocked(bo->base.import_attach, DMA_BIDIRECTIONAL);
-	if (IS_ERR(sgt)) {
-		ivpu_err(vdev, "Failed to map attachment: %ld\n", PTR_ERR(sgt));
-		return PTR_ERR(sgt);
-	}
-
-	bo->sgt = sgt;
-	return 0;
-}
-
-static void prime_unmap_pages_locked(struct ivpu_bo *bo)
-{
-	dma_buf_unmap_attachment_unlocked(bo->base.import_attach, bo->sgt, DMA_BIDIRECTIONAL);
-	bo->sgt = NULL;
-}
-
-static const struct ivpu_bo_ops prime_ops = {
-	.type = IVPU_BO_TYPE_PRIME,
-	.name = "prime",
-	.alloc_pages = prime_alloc_pages_locked,
-	.free_pages = prime_free_pages_locked,
-	.map_pages = prime_map_pages_locked,
-	.unmap_pages = prime_unmap_pages_locked,
-};
-
-static int __must_check shmem_alloc_pages_locked(struct ivpu_bo *bo)
-{
-	int npages = ivpu_bo_size(bo) >> PAGE_SHIFT;
-	struct page **pages;
-
-	pages = drm_gem_get_pages(&bo->base);
-	if (IS_ERR(pages))
-		return PTR_ERR(pages);
-
-	if (bo->flags & DRM_IVPU_BO_WC)
-		set_pages_array_wc(pages, npages);
-
-	bo->pages = pages;
-	return 0;
-}
-
-static void shmem_free_pages_locked(struct ivpu_bo *bo)
-{
-	if (ivpu_bo_cache_mode(bo) != DRM_IVPU_BO_CACHED)
-		set_pages_array_wb(bo->pages, ivpu_bo_size(bo) >> PAGE_SHIFT);
-
-	drm_gem_put_pages(&bo->base, bo->pages, true, false);
-	bo->pages = NULL;
-}
-
-static int ivpu_bo_map_pages_locked(struct ivpu_bo *bo)
-{
-	int npages = ivpu_bo_size(bo) >> PAGE_SHIFT;
-	struct ivpu_device *vdev = ivpu_bo_to_vdev(bo);
-	struct sg_table *sgt;
-	int ret;
-
-	sgt = drm_prime_pages_to_sg(&vdev->drm, bo->pages, npages);
-	if (IS_ERR(sgt)) {
-		ivpu_err(vdev, "Failed to allocate sgtable\n");
-		return PTR_ERR(sgt);
-	}
-
-	ret = dma_map_sgtable(vdev->drm.dev, sgt, DMA_BIDIRECTIONAL, 0);
-	if (ret) {
-		ivpu_err(vdev, "Failed to map BO in IOMMU: %d\n", ret);
-		goto err_free_sgt;
-	}
-
-	bo->sgt = sgt;
-	return 0;
-
-err_free_sgt:
-	kfree(sgt);
-	return ret;
-}
-
-static void ivpu_bo_unmap_pages_locked(struct ivpu_bo *bo)
-{
-	struct ivpu_device *vdev = ivpu_bo_to_vdev(bo);
-
-	dma_unmap_sgtable(vdev->drm.dev, bo->sgt, DMA_BIDIRECTIONAL, 0);
-	sg_free_table(bo->sgt);
-	kfree(bo->sgt);
-	bo->sgt = NULL;
-}
-
-static const struct ivpu_bo_ops shmem_ops = {
-	.type = IVPU_BO_TYPE_SHMEM,
-	.name = "shmem",
-	.alloc_pages = shmem_alloc_pages_locked,
-	.free_pages = shmem_free_pages_locked,
-	.map_pages = ivpu_bo_map_pages_locked,
-	.unmap_pages = ivpu_bo_unmap_pages_locked,
-};
-
-static int __must_check internal_alloc_pages_locked(struct ivpu_bo *bo)
-{
-	unsigned int i, npages = ivpu_bo_size(bo) >> PAGE_SHIFT;
-	struct page **pages;
-	int ret;
-
-	pages = kvmalloc_array(npages, sizeof(*bo->pages), GFP_KERNEL);
-	if (!pages)
-		return -ENOMEM;
-
-	for (i = 0; i < npages; i++) {
-		pages[i] = alloc_page(GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO);
-		if (!pages[i]) {
-			ret = -ENOMEM;
-			goto err_free_pages;
-		}
-		cond_resched();
-	}
-
-	bo->pages = pages;
-	return 0;
-
-err_free_pages:
-	while (i--)
-		put_page(pages[i]);
-	kvfree(pages);
-	return ret;
-}
-
-static void internal_free_pages_locked(struct ivpu_bo *bo)
-{
-	unsigned int i, npages = ivpu_bo_size(bo) >> PAGE_SHIFT;
-
-	if (ivpu_bo_cache_mode(bo) != DRM_IVPU_BO_CACHED)
-		set_pages_array_wb(bo->pages, ivpu_bo_size(bo) >> PAGE_SHIFT);
-
-	for (i = 0; i < npages; i++)
-		put_page(bo->pages[i]);
-
-	kvfree(bo->pages);
-	bo->pages = NULL;
-}
-
-static const struct ivpu_bo_ops internal_ops = {
-	.type = IVPU_BO_TYPE_INTERNAL,
-	.name = "internal",
-	.alloc_pages = internal_alloc_pages_locked,
-	.free_pages = internal_free_pages_locked,
-	.map_pages = ivpu_bo_map_pages_locked,
-	.unmap_pages = ivpu_bo_unmap_pages_locked,
-};
-
-static int __must_check ivpu_bo_alloc_and_map_pages_locked(struct ivpu_bo *bo)
-{
-	struct ivpu_device *vdev = ivpu_bo_to_vdev(bo);
-	int ret;
-
-	lockdep_assert_held(&bo->lock);
-	drm_WARN_ON(&vdev->drm, bo->sgt);
-
-	ret = bo->ops->alloc_pages(bo);
-	if (ret) {
-		ivpu_err(vdev, "Failed to allocate pages for BO: %d", ret);
-		return ret;
-	}
-
-	ret = bo->ops->map_pages(bo);
-	if (ret) {
-		ivpu_err(vdev, "Failed to map pages for BO: %d", ret);
-		goto err_free_pages;
-	}
-	return ret;
-
-err_free_pages:
-	bo->ops->free_pages(bo);
-	return ret;
-}
-
-static void ivpu_bo_unmap_and_free_pages(struct ivpu_bo *bo)
-{
-	mutex_lock(&bo->lock);
-
-	WARN_ON(!bo->sgt);
-	bo->ops->unmap_pages(bo);
-	WARN_ON(bo->sgt);
-	bo->ops->free_pages(bo);
-	WARN_ON(bo->pages);
-
-	mutex_unlock(&bo->lock);
+			 action, ivpu_bo_size(bo), (bool)bo->base.pages, (bool)bo->base.sgt,
+			 bo->handle);
 }
 
 /*
@@ -254,20 +48,24 @@ int __must_check ivpu_bo_pin(struct ivpu_bo *bo)
 
 	mutex_lock(&bo->lock);
 
+	ivpu_dbg_bo(vdev, bo, "pin");
+
 	if (!bo->ctx) {
 		ivpu_err(vdev, "vpu_addr not allocated for BO %d\n", bo->handle);
 		ret = -EINVAL;
 		goto unlock;
 	}
 
-	if (!bo->sgt) {
-		ret = ivpu_bo_alloc_and_map_pages_locked(bo);
-		if (ret)
+	if (!bo->mmu_mapped) {
+		struct sg_table *sgt = drm_gem_shmem_get_pages_sgt(&bo->base);
+
+		if (IS_ERR(sgt)) {
+			ret = PTR_ERR(sgt);
+			ivpu_err(vdev, "Failed to map BO in IOMMU: %d\n", ret);
 			goto unlock;
-	}
+		}
 
-	if (!bo->mmu_mapped) {
-		ret = ivpu_mmu_context_map_sgt(vdev, bo->ctx, bo->vpu_addr, bo->sgt,
+		ret = ivpu_mmu_context_map_sgt(vdev, bo->ctx, bo->vpu_addr, sgt,
 					       ivpu_bo_is_snooped(bo));
 		if (ret) {
 			ivpu_err(vdev, "Failed to map BO in MMU: %d\n", ret);
@@ -291,13 +89,14 @@ ivpu_bo_alloc_vpu_addr(struct ivpu_bo *bo, struct ivpu_mmu_context *ctx,
 
 	mutex_lock(&bo->lock);
 
-	ret = ivpu_mmu_context_insert_node(ctx, range, bo->base.size, &bo->mm_node);
+	ret = ivpu_mmu_context_insert_node(ctx, range, ivpu_bo_size(bo), &bo->mm_node);
 	if (!ret) {
 		bo->ctx = ctx;
 		bo->vpu_addr = bo->mm_node.start;
 	} else {
 		ivpu_err(vdev, "Failed to add BO to context %u: %d\n", ctx->id, ret);
 	}
+
 	ivpu_dbg_bo(vdev, bo, "alloc");
 
 	mutex_unlock(&bo->lock);
@@ -314,11 +113,12 @@ static void ivpu_bo_unbind_locked(struct ivpu_bo *bo)
 	ivpu_dbg_bo(vdev, bo, "unbind");
 
 	/* TODO: dma_unmap */
+
 	if (bo->mmu_mapped) {
 		drm_WARN_ON(&vdev->drm, !bo->ctx);
 		drm_WARN_ON(&vdev->drm, !bo->vpu_addr);
-		drm_WARN_ON(&vdev->drm, !bo->sgt);
-		ivpu_mmu_context_unmap_sgt(vdev, bo->ctx, bo->vpu_addr, bo->sgt);
+		drm_WARN_ON(&vdev->drm, !bo->base.sgt);
+		ivpu_mmu_context_unmap_sgt(vdev, bo->ctx, bo->vpu_addr, bo->base.sgt);
 		bo->mmu_mapped = false;
 	}
 
@@ -353,15 +153,32 @@ void ivpu_bo_remove_all_bos_from_context(struct ivpu_device *vdev, struct ivpu_m
 	mutex_unlock(&vdev->bo_list_lock);
 }
 
-static struct ivpu_bo *
-ivpu_bo_alloc(struct ivpu_device *vdev, u64 size, u32 flags, const struct ivpu_bo_ops *ops)
+struct drm_gem_object *ivpu_gem_create_object(struct drm_device *dev, size_t size)
 {
 	struct ivpu_bo *bo;
-	int ret = 0;
 
-	if (drm_WARN_ON(&vdev->drm, size == 0 || !PAGE_ALIGNED(size)))
+	if (size == 0 || !PAGE_ALIGNED(size))
 		return ERR_PTR(-EINVAL);
 
+	bo = kzalloc(sizeof(*bo), GFP_KERNEL);
+	if (!bo)
+		return ERR_PTR(-ENOMEM);
+
+	bo->base.base.funcs = &ivpu_gem_funcs;
+	bo->base.pages_mark_dirty_on_put = true; /* VPU can dirty a BO anytime */
+
+	INIT_LIST_HEAD(&bo->bo_list_node);
+	mutex_init(&bo->lock);
+
+	return &bo->base.base;
+}
+
+static struct ivpu_bo *
+ivpu_bo_create(struct ivpu_device *vdev, u64 size, u32 flags)
+{
+	struct drm_gem_shmem_object *shmem;
+	struct ivpu_bo *bo;
+
 	switch (flags & DRM_IVPU_BO_CACHE_MASK) {
 	case DRM_IVPU_BO_CACHED:
 	case DRM_IVPU_BO_WC:
@@ -370,44 +187,22 @@ ivpu_bo_alloc(struct ivpu_device *vdev, u64 size, u32 flags, const struct ivpu_b
 		return ERR_PTR(-EINVAL);
 	}
 
-	bo = kzalloc(sizeof(*bo), GFP_KERNEL);
-	if (!bo)
-		return ERR_PTR(-ENOMEM);
+	shmem = drm_gem_shmem_create(&vdev->drm, size);
+	if (IS_ERR(shmem))
+		return ERR_CAST(shmem);
 
-	mutex_init(&bo->lock);
-	bo->base.funcs = &ivpu_gem_funcs;
+	bo = to_ivpu_bo(&shmem->base);
+	bo->base.map_wc = flags & DRM_IVPU_BO_WC;
 	bo->flags = flags;
-	bo->ops = ops;
-
-	if (ops->type == IVPU_BO_TYPE_SHMEM)
-		ret = drm_gem_object_init(&vdev->drm, &bo->base, size);
-	else
-		drm_gem_private_object_init(&vdev->drm, &bo->base, size);
-
-	if (ret) {
-		ivpu_err(vdev, "Failed to initialize drm object\n");
-		goto err_free;
-	}
-
-	if (flags & DRM_IVPU_BO_MAPPABLE) {
-		ret = drm_gem_create_mmap_offset(&bo->base);
-		if (ret) {
-			ivpu_err(vdev, "Failed to allocate mmap offset\n");
-			goto err_release;
-		}
-	}
 
 	mutex_lock(&vdev->bo_list_lock);
 	list_add_tail(&bo->bo_list_node, &vdev->bo_list);
 	mutex_unlock(&vdev->bo_list_lock);
 
-	return bo;
+	ivpu_dbg(vdev, BO, "create: vpu_addr 0x%llx size %zu flags 0x%x\n",
+		 bo->vpu_addr, bo->base.base.size, flags);
 
-err_release:
-	drm_gem_object_release(&bo->base);
-err_free:
-	kfree(bo);
-	return ERR_PTR(ret);
+	return bo;
 }
 
 static int ivpu_bo_open(struct drm_gem_object *obj, struct drm_file *file)
@@ -429,8 +224,8 @@ static int ivpu_bo_open(struct drm_gem_object *obj, struct drm_file *file)
 
 static void ivpu_bo_free(struct drm_gem_object *obj)
 {
+	struct ivpu_device *vdev = to_ivpu_device(obj->dev);
 	struct ivpu_bo *bo = to_ivpu_bo(obj);
-	struct ivpu_device *vdev = ivpu_bo_to_vdev(bo);
 
 	mutex_lock(&vdev->bo_list_lock);
 	list_del(&bo->bo_list_node);
@@ -441,108 +236,64 @@ static void ivpu_bo_free(struct drm_gem_object *obj)
 	ivpu_dbg_bo(vdev, bo, "free");
 
 	ivpu_bo_unbind(bo);
-	vunmap(bo->kvaddr);
-
-	if (bo->sgt)
-		ivpu_bo_unmap_and_free_pages(bo);
-
-	if (bo->base.import_attach)
-		drm_prime_gem_destroy(&bo->base, bo->sgt);
-
-	drm_gem_object_release(&bo->base);
-
 	mutex_destroy(&bo->lock);
-	kfree(bo);
-}
-
-static int ivpu_bo_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma)
-{
-	struct ivpu_bo *bo = to_ivpu_bo(obj);
 
-	if (obj->import_attach) {
-		/* Drop the reference drm_gem_mmap_obj() acquired.*/
-		drm_gem_object_put(obj);
-		vma->vm_private_data = NULL;
-		return dma_buf_mmap(obj->dma_buf, vma, 0);
-	}
-
-	vm_flags_set(vma, VM_PFNMAP | VM_DONTEXPAND);
-	vma->vm_page_prot = ivpu_bo_pgprot(bo, vm_get_page_prot(vma->vm_flags));
-
-	return 0;
+	drm_WARN_ON(obj->dev, bo->base.pages_use_count > 1);
+	drm_gem_shmem_free(&bo->base);
 }
 
-static struct sg_table *ivpu_bo_get_sg_table(struct drm_gem_object *obj)
-{
-	struct ivpu_bo *bo = to_ivpu_bo(obj);
-	loff_t npages = obj->size >> PAGE_SHIFT;
-	int ret = 0;
-
-	mutex_lock(&bo->lock);
-
-	if (!bo->sgt)
-		ret = ivpu_bo_alloc_and_map_pages_locked(bo);
-
-	mutex_unlock(&bo->lock);
-
-	if (ret)
-		return ERR_PTR(ret);
-
-	return drm_prime_pages_to_sg(obj->dev, bo->pages, npages);
-}
+static const struct dma_buf_ops ivpu_bo_dmabuf_ops =  {
+	.cache_sgt_mapping = true,
+	.attach = drm_gem_map_attach,
+	.detach = drm_gem_map_detach,
+	.map_dma_buf = drm_gem_map_dma_buf,
+	.unmap_dma_buf = drm_gem_unmap_dma_buf,
+	.release = drm_gem_dmabuf_release,
+	.mmap = drm_gem_dmabuf_mmap,
+	.vmap = drm_gem_dmabuf_vmap,
+	.vunmap = drm_gem_dmabuf_vunmap,
+};
 
-static vm_fault_t ivpu_vm_fault(struct vm_fault *vmf)
+static struct dma_buf *ivpu_bo_export(struct drm_gem_object *obj, int flags)
 {
-	struct vm_area_struct *vma = vmf->vma;
-	struct drm_gem_object *obj = vma->vm_private_data;
-	struct ivpu_bo *bo = to_ivpu_bo(obj);
-	loff_t npages = obj->size >> PAGE_SHIFT;
-	pgoff_t page_offset;
-	struct page *page;
-	vm_fault_t ret;
-	int err;
+	struct drm_device *dev = obj->dev;
+	struct dma_buf_export_info exp_info = {
+		.exp_name = KBUILD_MODNAME,
+		.owner = dev->driver->fops->owner,
+		.ops = &ivpu_bo_dmabuf_ops,
+		.size = obj->size,
+		.flags = flags,
+		.priv = obj,
+		.resv = obj->resv,
+	};
+	void *sgt;
 
-	mutex_lock(&bo->lock);
+	/*
+	 * Make sure that pages are allocated and dma-mapped before exporting the bo.
+	 * DMA-mapping is required if the bo will be imported to the same device.
+	 */
+	sgt = drm_gem_shmem_get_pages_sgt(to_drm_gem_shmem_obj(obj));
+	if (IS_ERR(sgt))
+		return sgt;
 
-	if (!bo->sgt) {
-		err = ivpu_bo_alloc_and_map_pages_locked(bo);
-		if (err) {
-			ret = vmf_error(err);
-			goto unlock;
-		}
-	}
-
-	/* We don't use vmf->pgoff since that has the fake offset */
-	page_offset = (vmf->address - vma->vm_start) >> PAGE_SHIFT;
-	if (page_offset >= npages) {
-		ret = VM_FAULT_SIGBUS;
-	} else {
-		page = bo->pages[page_offset];
-		ret = vmf_insert_pfn(vma, vmf->address, page_to_pfn(page));
-	}
-
-unlock:
-	mutex_unlock(&bo->lock);
-
-	return ret;
+	return drm_gem_dmabuf_export(dev, &exp_info);
 }
 
-static const struct vm_operations_struct ivpu_vm_ops = {
-	.fault = ivpu_vm_fault,
-	.open = drm_gem_vm_open,
-	.close = drm_gem_vm_close,
-};
-
 static const struct drm_gem_object_funcs ivpu_gem_funcs = {
 	.free = ivpu_bo_free,
 	.open = ivpu_bo_open,
-	.mmap = ivpu_bo_mmap,
-	.vm_ops = &ivpu_vm_ops,
-	.get_sg_table = ivpu_bo_get_sg_table,
+	.export = ivpu_bo_export,
+	.print_info = drm_gem_shmem_object_print_info,
+	.pin = drm_gem_shmem_object_pin,
+	.unpin = drm_gem_shmem_object_unpin,
+	.get_sg_table = drm_gem_shmem_object_get_sg_table,
+	.vmap = drm_gem_shmem_object_vmap,
+	.vunmap = drm_gem_shmem_object_vunmap,
+	.mmap = drm_gem_shmem_object_mmap,
+	.vm_ops = &drm_gem_shmem_vm_ops,
 };
 
-int
-ivpu_bo_create_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
+int ivpu_bo_create_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 {
 	struct ivpu_file_priv *file_priv = file->driver_priv;
 	struct ivpu_device *vdev = file_priv->vdev;
@@ -557,20 +308,20 @@ ivpu_bo_create_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	if (size == 0)
 		return -EINVAL;
 
-	bo = ivpu_bo_alloc(vdev, size, args->flags, &shmem_ops);
+	bo = ivpu_bo_create(vdev, size, args->flags);
 	if (IS_ERR(bo)) {
 		ivpu_err(vdev, "Failed to create BO: %pe (ctx %u size %llu flags 0x%x)",
 			 bo, file_priv->ctx.id, args->size, args->flags);
 		return PTR_ERR(bo);
 	}
 
-	ret = drm_gem_handle_create(file, &bo->base, &bo->handle);
+	ret = drm_gem_handle_create(file, &bo->base.base, &bo->handle);
 	if (!ret) {
 		args->vpu_addr = bo->vpu_addr;
 		args->handle = bo->handle;
 	}
 
-	drm_gem_object_put(&bo->base);
+	drm_gem_object_put(&bo->base.base);
 
 	return ret;
 }
@@ -580,8 +331,8 @@ ivpu_bo_alloc_internal(struct ivpu_device *vdev, u64 vpu_addr, u64 size, u32 fla
 {
 	const struct ivpu_addr_range *range;
 	struct ivpu_addr_range fixed_range;
+	struct iosys_map map;
 	struct ivpu_bo *bo;
-	pgprot_t prot;
 	int ret;
 
 	drm_WARN_ON(&vdev->drm, !PAGE_ALIGNED(vpu_addr));
@@ -595,7 +346,7 @@ ivpu_bo_alloc_internal(struct ivpu_device *vdev, u64 vpu_addr, u64 size, u32 fla
 		range = &vdev->hw->ranges.global;
 	}
 
-	bo = ivpu_bo_alloc(vdev, size, flags, &internal_ops);
+	bo = ivpu_bo_create(vdev, size, flags);
 	if (IS_ERR(bo)) {
 		ivpu_err(vdev, "Failed to create BO: %pe (vpu_addr 0x%llx size %llu flags 0x%x)",
 			 bo, vpu_addr, size, flags);
@@ -610,61 +361,23 @@ ivpu_bo_alloc_internal(struct ivpu_device *vdev, u64 vpu_addr, u64 size, u32 fla
 	if (ret)
 		goto err_put;
 
-	if (ivpu_bo_cache_mode(bo) != DRM_IVPU_BO_CACHED)
-		drm_clflush_pages(bo->pages, ivpu_bo_size(bo) >> PAGE_SHIFT);
-
-	if (bo->flags & DRM_IVPU_BO_WC)
-		set_pages_array_wc(bo->pages, ivpu_bo_size(bo) >> PAGE_SHIFT);
-	else if (bo->flags & DRM_IVPU_BO_UNCACHED)
-		set_pages_array_uc(bo->pages, ivpu_bo_size(bo) >> PAGE_SHIFT);
-
-	prot = ivpu_bo_pgprot(bo, PAGE_KERNEL);
-	bo->kvaddr = vmap(bo->pages, ivpu_bo_size(bo) >> PAGE_SHIFT, VM_MAP, prot);
-	if (!bo->kvaddr) {
-		ivpu_err(vdev, "Failed to map BO into kernel virtual memory\n");
+	ret = drm_gem_shmem_vmap(&bo->base, &map);
+	if (ret)
 		goto err_put;
-	}
 
 	return bo;
 
 err_put:
-	drm_gem_object_put(&bo->base);
+	drm_gem_object_put(&bo->base.base);
 	return NULL;
 }
 
 void ivpu_bo_free_internal(struct ivpu_bo *bo)
 {
-	drm_gem_object_put(&bo->base);
-}
-
-struct drm_gem_object *ivpu_gem_prime_import(struct drm_device *dev, struct dma_buf *buf)
-{
-	struct ivpu_device *vdev = to_ivpu_device(dev);
-	struct dma_buf_attachment *attach;
-	struct ivpu_bo *bo;
-
-	attach = dma_buf_attach(buf, dev->dev);
-	if (IS_ERR(attach))
-		return ERR_CAST(attach);
+	struct iosys_map map = IOSYS_MAP_INIT_VADDR(bo->base.vaddr);
 
-	get_dma_buf(buf);
-
-	bo = ivpu_bo_alloc(vdev, buf->size, DRM_IVPU_BO_MAPPABLE, &prime_ops);
-	if (IS_ERR(bo)) {
-		ivpu_err(vdev, "Failed to import BO: %pe (size %lu)", bo, buf->size);
-		goto err_detach;
-	}
-
-	lockdep_set_class(&bo->lock, &prime_bo_lock_class_key);
-
-	bo->base.import_attach = attach;
-
-	return &bo->base;
-
-err_detach:
-	dma_buf_detach(buf, attach);
-	dma_buf_put(buf);
-	return ERR_CAST(bo);
+	drm_gem_shmem_vunmap(&bo->base, &map);
+	drm_gem_object_put(&bo->base.base);
 }
 
 int ivpu_bo_info_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
@@ -723,12 +436,23 @@ static void ivpu_bo_print_info(struct ivpu_bo *bo, struct drm_printer *p)
 
 	mutex_lock(&bo->lock);
 
-	if (bo->base.dma_buf && bo->base.dma_buf->file)
-		dma_refcount = atomic_long_read(&bo->base.dma_buf->file->f_count);
+	if (bo->base.base.dma_buf && bo->base.base.dma_buf->file)
+		dma_refcount = atomic_long_read(&bo->base.base.dma_buf->file->f_count);
+
+	drm_printf(p, "%-3u %-6d 0x%-12llx %-10lu 0x%-8x %-4u %-8lu",
+		   bo->ctx->id, bo->handle, bo->vpu_addr, bo->base.base.size,
+		   bo->flags, kref_read(&bo->base.base.refcount), dma_refcount);
+
+	if (bo->base.base.import_attach)
+		drm_printf(p, " imported");
+
+	if (bo->base.pages)
+		drm_printf(p, " has_pages");
+
+	if (bo->mmu_mapped)
+		drm_printf(p, " mmu_mapped");
 
-	drm_printf(p, "%5u %6d %16llx %10lu %10u %12lu %14s\n",
-		   bo->ctx ? bo->ctx->id : -1, bo->handle, bo->vpu_addr, bo->base.size,
-		   kref_read(&bo->base.refcount), dma_refcount, bo->ops->name);
+	drm_printf(p, "\n");
 
 	mutex_unlock(&bo->lock);
 }
@@ -738,8 +462,8 @@ void ivpu_bo_list(struct drm_device *dev, struct drm_printer *p)
 	struct ivpu_device *vdev = to_ivpu_device(dev);
 	struct ivpu_bo *bo;
 
-	drm_printf(p, "%5s %6s %16s %10s %10s %12s %14s\n",
-		   "ctx", "handle", "vpu_addr", "size", "refcount", "dma_refcount", "type");
+	drm_printf(p, "%-3s %-6s %-14s %-10s %-10s %-4s %-8s %s\n",
+		   "ctx", "handle", "vpu_addr", "size", "flags", "refs", "dma_refs", "attribs");
 
 	mutex_lock(&vdev->bo_list_lock);
 	list_for_each_entry(bo, &vdev->bo_list, bo_list_node)
diff --git a/drivers/accel/ivpu/ivpu_gem.h b/drivers/accel/ivpu/ivpu_gem.h
index 214d8fd14310..d75cad0d3c74 100644
--- a/drivers/accel/ivpu/ivpu_gem.h
+++ b/drivers/accel/ivpu/ivpu_gem.h
@@ -6,83 +6,52 @@
 #define __IVPU_GEM_H__
 
 #include <drm/drm_gem.h>
+#include <drm/drm_gem_shmem_helper.h>
 #include <drm/drm_mm.h>
 
-struct dma_buf;
-struct ivpu_bo_ops;
 struct ivpu_file_priv;
 
 struct ivpu_bo {
-	struct drm_gem_object base;
-	const struct ivpu_bo_ops *ops;
-
+	struct drm_gem_shmem_object base;
 	struct ivpu_mmu_context *ctx;
 	struct list_head bo_list_node;
 	struct drm_mm_node mm_node;
 
-	struct mutex lock; /* Protects: pages, sgt, ctx, mmu_mapped, vpu_addr */
-	struct sg_table *sgt;
-	struct page **pages;
-	bool mmu_mapped;
-
-	void *kvaddr;
+	struct mutex lock; /* Protects: ctx, mmu_mapped, vpu_addr */
 	u64 vpu_addr;
 	u32 handle;
 	u32 flags;
-	u32 job_status;
-};
-
-enum ivpu_bo_type {
-	IVPU_BO_TYPE_SHMEM = 1,
-	IVPU_BO_TYPE_INTERNAL,
-	IVPU_BO_TYPE_PRIME,
-};
-
-struct ivpu_bo_ops {
-	enum ivpu_bo_type type;
-	const char *name;
-	int (*alloc_pages)(struct ivpu_bo *bo);
-	void (*free_pages)(struct ivpu_bo *bo);
-	int (*map_pages)(struct ivpu_bo *bo);
-	void (*unmap_pages)(struct ivpu_bo *bo);
+	u32 job_status; /* Valid only for command buffer */
+	bool mmu_mapped;
 };
 
 int ivpu_bo_pin(struct ivpu_bo *bo);
 void ivpu_bo_remove_all_bos_from_context(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx);
-void ivpu_bo_list(struct drm_device *dev, struct drm_printer *p);
-void ivpu_bo_list_print(struct drm_device *dev);
 
-struct ivpu_bo *
-ivpu_bo_alloc_internal(struct ivpu_device *vdev, u64 vpu_addr, u64 size, u32 flags);
+struct drm_gem_object *ivpu_gem_create_object(struct drm_device *dev, size_t size);
+struct ivpu_bo *ivpu_bo_alloc_internal(struct ivpu_device *vdev, u64 vpu_addr, u64 size, u32 flags);
 void ivpu_bo_free_internal(struct ivpu_bo *bo);
-struct drm_gem_object *ivpu_gem_prime_import(struct drm_device *dev, struct dma_buf *dma_buf);
-void ivpu_bo_unmap_sgt_and_remove_from_context(struct ivpu_bo *bo);
 
 int ivpu_bo_create_ioctl(struct drm_device *dev, void *data, struct drm_file *file);
 int ivpu_bo_info_ioctl(struct drm_device *dev, void *data, struct drm_file *file);
 int ivpu_bo_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file);
 
+void ivpu_bo_list(struct drm_device *dev, struct drm_printer *p);
+void ivpu_bo_list_print(struct drm_device *dev);
+
 static inline struct ivpu_bo *to_ivpu_bo(struct drm_gem_object *obj)
 {
-	return container_of(obj, struct ivpu_bo, base);
+	return container_of(obj, struct ivpu_bo, base.base);
 }
 
 static inline void *ivpu_bo_vaddr(struct ivpu_bo *bo)
 {
-	return bo->kvaddr;
+	return bo->base.vaddr;
 }
 
 static inline size_t ivpu_bo_size(struct ivpu_bo *bo)
 {
-	return bo->base.size;
-}
-
-static inline struct page *ivpu_bo_get_page(struct ivpu_bo *bo, u64 offset)
-{
-	if (offset > ivpu_bo_size(bo) || !bo->pages)
-		return NULL;
-
-	return bo->pages[offset / PAGE_SIZE];
+	return bo->base.base.size;
 }
 
 static inline u32 ivpu_bo_cache_mode(struct ivpu_bo *bo)
@@ -95,20 +64,9 @@ static inline bool ivpu_bo_is_snooped(struct ivpu_bo *bo)
 	return ivpu_bo_cache_mode(bo) == DRM_IVPU_BO_CACHED;
 }
 
-static inline pgprot_t ivpu_bo_pgprot(struct ivpu_bo *bo, pgprot_t prot)
-{
-	if (bo->flags & DRM_IVPU_BO_WC)
-		return pgprot_writecombine(prot);
-
-	if (bo->flags & DRM_IVPU_BO_UNCACHED)
-		return pgprot_noncached(prot);
-
-	return prot;
-}
-
 static inline struct ivpu_device *ivpu_bo_to_vdev(struct ivpu_bo *bo)
 {
-	return to_ivpu_device(bo->base.dev);
+	return to_ivpu_device(bo->base.base.dev);
 }
 
 static inline void *ivpu_to_cpu_addr(struct ivpu_bo *bo, u32 vpu_addr)
diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c
index 15a408fad494..02acd8dba02a 100644
--- a/drivers/accel/ivpu/ivpu_job.c
+++ b/drivers/accel/ivpu/ivpu_job.c
@@ -266,7 +266,7 @@ static void job_release(struct kref *ref)
 
 	for (i = 0; i < job->bo_count; i++)
 		if (job->bos[i])
-			drm_gem_object_put(&job->bos[i]->base);
+			drm_gem_object_put(&job->bos[i]->base.base);
 
 	dma_fence_put(job->done_fence);
 	ivpu_file_priv_put(&job->file_priv);
@@ -450,7 +450,7 @@ ivpu_job_prepare_bos_for_submit(struct drm_file *file, struct ivpu_job *job, u32
 	}
 
 	bo = job->bos[CMD_BUF_IDX];
-	if (!dma_resv_test_signaled(bo->base.resv, DMA_RESV_USAGE_READ)) {
+	if (!dma_resv_test_signaled(bo->base.base.resv, DMA_RESV_USAGE_READ)) {
 		ivpu_warn(vdev, "Buffer is already in use\n");
 		return -EBUSY;
 	}
@@ -470,7 +470,7 @@ ivpu_job_prepare_bos_for_submit(struct drm_file *file, struct ivpu_job *job, u32
 	}
 
 	for (i = 0; i < buf_count; i++) {
-		ret = dma_resv_reserve_fences(job->bos[i]->base.resv, 1);
+		ret = dma_resv_reserve_fences(job->bos[i]->base.base.resv, 1);
 		if (ret) {
 			ivpu_warn(vdev, "Failed to reserve fences: %d\n", ret);
 			goto unlock_reservations;
@@ -479,7 +479,7 @@ ivpu_job_prepare_bos_for_submit(struct drm_file *file, struct ivpu_job *job, u32
 
 	for (i = 0; i < buf_count; i++) {
 		usage = (i == CMD_BUF_IDX) ? DMA_RESV_USAGE_WRITE : DMA_RESV_USAGE_BOOKKEEP;
-		dma_resv_add_fence(job->bos[i]->base.resv, job->done_fence, usage);
+		dma_resv_add_fence(job->bos[i]->base.base.resv, job->done_fence, usage);
 	}
 
 unlock_reservations:
-- 
cgit 


From 043a2d5d71d87553985816065da41cff72f5f2df Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Date: Mon, 13 Nov 2023 18:02:48 +0100
Subject: accel/ivpu: Rename cons->rx_msg_lock

Now the cons->rx_msg_lock also protects 'abort' field so rename the lock.

Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231113170252.758137-2-jacek.lawrynowicz@linux.intel.com
---
 drivers/accel/ivpu/ivpu_ipc.c | 27 +++++++++++++--------------
 drivers/accel/ivpu/ivpu_ipc.h |  2 +-
 2 files changed, 14 insertions(+), 15 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/ivpu/ivpu_ipc.c b/drivers/accel/ivpu/ivpu_ipc.c
index 88453762c9d5..31ae0e71a8a3 100644
--- a/drivers/accel/ivpu/ivpu_ipc.c
+++ b/drivers/accel/ivpu/ivpu_ipc.c
@@ -150,7 +150,7 @@ ivpu_ipc_consumer_add(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
 	cons->tx_vpu_addr = 0;
 	cons->request_id = 0;
 	cons->aborted = false;
-	spin_lock_init(&cons->rx_msg_lock);
+	spin_lock_init(&cons->rx_lock);
 	INIT_LIST_HEAD(&cons->rx_msg_list);
 	init_waitqueue_head(&cons->rx_msg_wq);
 
@@ -168,7 +168,7 @@ void ivpu_ipc_consumer_del(struct ivpu_device *vdev, struct ivpu_ipc_consumer *c
 	list_del(&cons->link);
 	spin_unlock_irq(&ipc->cons_list_lock);
 
-	spin_lock_irq(&cons->rx_msg_lock);
+	spin_lock_irq(&cons->rx_lock);
 	list_for_each_entry_safe(rx_msg, r, &cons->rx_msg_list, link) {
 		list_del(&rx_msg->link);
 		if (!cons->aborted)
@@ -176,7 +176,7 @@ void ivpu_ipc_consumer_del(struct ivpu_device *vdev, struct ivpu_ipc_consumer *c
 		atomic_dec(&ipc->rx_msg_count);
 		kfree(rx_msg);
 	}
-	spin_unlock_irq(&cons->rx_msg_lock);
+	spin_unlock_irq(&cons->rx_lock);
 
 	ivpu_ipc_tx_release(vdev, cons->tx_vpu_addr);
 }
@@ -212,9 +212,9 @@ static int ivpu_ipc_rx_need_wakeup(struct ivpu_ipc_consumer *cons)
 	if (IS_KTHREAD())
 		ret |= (kthread_should_stop() || kthread_should_park());
 
-	spin_lock_irq(&cons->rx_msg_lock);
+	spin_lock_irq(&cons->rx_lock);
 	ret |= !list_empty(&cons->rx_msg_list) || cons->aborted;
-	spin_unlock_irq(&cons->rx_msg_lock);
+	spin_unlock_irq(&cons->rx_lock);
 
 	return ret;
 }
@@ -237,20 +237,19 @@ int ivpu_ipc_receive(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
 	if (wait_ret == 0)
 		return -ETIMEDOUT;
 
-	spin_lock_irq(&cons->rx_msg_lock);
+	spin_lock_irq(&cons->rx_lock);
 	rx_msg = list_first_entry_or_null(&cons->rx_msg_list, struct ivpu_ipc_rx_msg, link);
 	if (!rx_msg) {
-		spin_unlock_irq(&cons->rx_msg_lock);
+		spin_unlock_irq(&cons->rx_lock);
 		return -EAGAIN;
 	}
 	list_del(&rx_msg->link);
 	if (cons->aborted) {
-		spin_unlock_irq(&cons->rx_msg_lock);
+		spin_unlock_irq(&cons->rx_lock);
 		ret = -ECANCELED;
 		goto out;
 	}
-
-	spin_unlock_irq(&cons->rx_msg_lock);
+	spin_unlock_irq(&cons->rx_lock);
 
 	if (ipc_buf)
 		memcpy(ipc_buf, rx_msg->ipc_hdr, sizeof(*ipc_buf));
@@ -383,9 +382,9 @@ ivpu_ipc_dispatch(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
 	rx_msg->ipc_hdr = ipc_hdr;
 	rx_msg->jsm_msg = jsm_msg;
 
-	spin_lock_irqsave(&cons->rx_msg_lock, flags);
+	spin_lock_irqsave(&cons->rx_lock, flags);
 	list_add_tail(&rx_msg->link, &cons->rx_msg_list);
-	spin_unlock_irqrestore(&cons->rx_msg_lock, flags);
+	spin_unlock_irqrestore(&cons->rx_lock, flags);
 
 	wake_up(&cons->rx_msg_wq);
 }
@@ -529,9 +528,9 @@ void ivpu_ipc_disable(struct ivpu_device *vdev)
 
 	spin_lock_irqsave(&ipc->cons_list_lock, flags);
 	list_for_each_entry_safe(cons, c, &ipc->cons_list, link) {
-		spin_lock(&cons->rx_msg_lock);
+		spin_lock(&cons->rx_lock);
 		cons->aborted = true;
-		spin_unlock(&cons->rx_msg_lock);
+		spin_unlock(&cons->rx_lock);
 		wake_up(&cons->rx_msg_wq);
 	}
 	spin_unlock_irqrestore(&ipc->cons_list_lock, flags);
diff --git a/drivers/accel/ivpu/ivpu_ipc.h b/drivers/accel/ivpu/ivpu_ipc.h
index a380787f7222..71b2e648dffd 100644
--- a/drivers/accel/ivpu/ivpu_ipc.h
+++ b/drivers/accel/ivpu/ivpu_ipc.h
@@ -49,7 +49,7 @@ struct ivpu_ipc_consumer {
 	u32 request_id;
 	bool aborted;
 
-	spinlock_t rx_msg_lock; /* Protects rx_msg_list and aborted */
+	spinlock_t rx_lock; /* Protects rx_msg_list and aborted */
 	struct list_head rx_msg_list;
 	wait_queue_head_t rx_msg_wq;
 };
-- 
cgit 


From 12fbf8ac39b08f810b767e2e3dc32258907ce890 Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Date: Mon, 13 Nov 2023 18:02:49 +0100
Subject: accel/ivpu: Do not use irqsave in ivpu_ipc_dispatch

ivpu_ipc_dispatch is always called with irqs disabled. Add lockdep
assertion and remove unneeded _irqsave/_irqrestore.

Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231113170252.758137-3-jacek.lawrynowicz@linux.intel.com
---
 drivers/accel/ivpu/ivpu_ipc.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/ivpu/ivpu_ipc.c b/drivers/accel/ivpu/ivpu_ipc.c
index 31ae0e71a8a3..781c7e40505a 100644
--- a/drivers/accel/ivpu/ivpu_ipc.c
+++ b/drivers/accel/ivpu/ivpu_ipc.c
@@ -367,9 +367,9 @@ ivpu_ipc_dispatch(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
 {
 	struct ivpu_ipc_info *ipc = vdev->ipc;
 	struct ivpu_ipc_rx_msg *rx_msg;
-	unsigned long flags;
 
 	lockdep_assert_held(&ipc->cons_list_lock);
+	lockdep_assert_irqs_disabled();
 
 	rx_msg = kzalloc(sizeof(*rx_msg), GFP_ATOMIC);
 	if (!rx_msg) {
@@ -382,9 +382,9 @@ ivpu_ipc_dispatch(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
 	rx_msg->ipc_hdr = ipc_hdr;
 	rx_msg->jsm_msg = jsm_msg;
 
-	spin_lock_irqsave(&cons->rx_lock, flags);
+	spin_lock(&cons->rx_lock);
 	list_add_tail(&rx_msg->link, &cons->rx_msg_list);
-	spin_unlock_irqrestore(&cons->rx_lock, flags);
+	spin_unlock(&cons->rx_lock);
 
 	wake_up(&cons->rx_msg_wq);
 }
-- 
cgit 


From b3c10b71a61c3a0412b7c390831c88405be3d24f Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Date: Mon, 13 Nov 2023 18:02:50 +0100
Subject: accel/ivpu: Do not use cons->aborted for job_done_thread

This allow to simplify ivpu_ipc_receive() as now we do not have
to process all messages in aborted state - they will be freed in
ivpu_ipc_consumer_del().

Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231113170252.758137-4-jacek.lawrynowicz@linux.intel.com
---
 drivers/accel/ivpu/ivpu_ipc.c | 18 +++++++++---------
 drivers/accel/ivpu/ivpu_job.c |  1 -
 2 files changed, 9 insertions(+), 10 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/ivpu/ivpu_ipc.c b/drivers/accel/ivpu/ivpu_ipc.c
index 781c7e40505a..1dd4413dc88f 100644
--- a/drivers/accel/ivpu/ivpu_ipc.c
+++ b/drivers/accel/ivpu/ivpu_ipc.c
@@ -238,17 +238,16 @@ int ivpu_ipc_receive(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
 		return -ETIMEDOUT;
 
 	spin_lock_irq(&cons->rx_lock);
+	if (cons->aborted) {
+		spin_unlock_irq(&cons->rx_lock);
+		return -ECANCELED;
+	}
 	rx_msg = list_first_entry_or_null(&cons->rx_msg_list, struct ivpu_ipc_rx_msg, link);
 	if (!rx_msg) {
 		spin_unlock_irq(&cons->rx_lock);
 		return -EAGAIN;
 	}
 	list_del(&rx_msg->link);
-	if (cons->aborted) {
-		spin_unlock_irq(&cons->rx_lock);
-		ret = -ECANCELED;
-		goto out;
-	}
 	spin_unlock_irq(&cons->rx_lock);
 
 	if (ipc_buf)
@@ -266,7 +265,6 @@ int ivpu_ipc_receive(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
 	}
 
 	ivpu_ipc_rx_mark_free(vdev, rx_msg->ipc_hdr, rx_msg->jsm_msg);
-out:
 	atomic_dec(&ipc->rx_msg_count);
 	kfree(rx_msg);
 
@@ -528,9 +526,11 @@ void ivpu_ipc_disable(struct ivpu_device *vdev)
 
 	spin_lock_irqsave(&ipc->cons_list_lock, flags);
 	list_for_each_entry_safe(cons, c, &ipc->cons_list, link) {
-		spin_lock(&cons->rx_lock);
-		cons->aborted = true;
-		spin_unlock(&cons->rx_lock);
+		if (cons->channel != VPU_IPC_CHAN_JOB_RET) {
+			spin_lock(&cons->rx_lock);
+			cons->aborted = true;
+			spin_unlock(&cons->rx_lock);
+		}
 		wake_up(&cons->rx_msg_wq);
 	}
 	spin_unlock_irqrestore(&ipc->cons_list_lock, flags);
diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c
index 02acd8dba02a..77b1b8abadd6 100644
--- a/drivers/accel/ivpu/ivpu_job.c
+++ b/drivers/accel/ivpu/ivpu_job.c
@@ -578,7 +578,6 @@ static int ivpu_job_done_thread(void *arg)
 	ivpu_ipc_consumer_add(vdev, &cons, VPU_IPC_CHAN_JOB_RET);
 
 	while (!kthread_should_stop()) {
-		cons.aborted = false;
 		timeout = ivpu_tdr_timeout_ms ? ivpu_tdr_timeout_ms : vdev->timeout.tdr;
 		jobs_submitted = !xa_empty(&vdev->submitted_jobs_xa);
 		ret = ivpu_ipc_receive(vdev, &cons, NULL, &jsm_msg, timeout);
-- 
cgit 


From 58cde80f45a2b1683ea3c24a9a9a4b0e1005336b Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Date: Mon, 13 Nov 2023 18:02:51 +0100
Subject: accel/ivpu: Use dedicated work for job timeout detection

Change to use work for timeout detection. Needed for thread_irq
conversion.

Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231113170252.758137-5-jacek.lawrynowicz@linux.intel.com
---
 drivers/accel/ivpu/ivpu_job.c | 24 +++++++++---------------
 drivers/accel/ivpu/ivpu_pm.c  | 31 +++++++++++++++++++++++++++++++
 drivers/accel/ivpu/ivpu_pm.h  |  3 +++
 3 files changed, 43 insertions(+), 15 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c
index 77b1b8abadd6..796366d67984 100644
--- a/drivers/accel/ivpu/ivpu_job.c
+++ b/drivers/accel/ivpu/ivpu_job.c
@@ -24,10 +24,6 @@
 #define JOB_ID_CONTEXT_MASK  GENMASK(31, 8)
 #define JOB_MAX_BUFFER_COUNT 65535
 
-static unsigned int ivpu_tdr_timeout_ms;
-module_param_named(tdr_timeout_ms, ivpu_tdr_timeout_ms, uint, 0644);
-MODULE_PARM_DESC(tdr_timeout_ms, "Timeout for device hang detection, in milliseconds, 0 - default");
-
 static void ivpu_cmdq_ring_db(struct ivpu_device *vdev, struct ivpu_cmdq *cmdq)
 {
 	ivpu_hw_reg_db_set(vdev, cmdq->db_id);
@@ -342,6 +338,8 @@ static int ivpu_job_done(struct ivpu_device *vdev, u32 job_id, u32 job_status)
 	ivpu_dbg(vdev, JOB, "Job complete:  id %3u ctx %2d engine %d status 0x%x\n",
 		 job->job_id, job->file_priv->ctx.id, job->engine_idx, job_status);
 
+	ivpu_stop_job_timeout_detection(vdev);
+
 	job_put(job);
 	return 0;
 }
@@ -357,6 +355,9 @@ static void ivpu_job_done_message(struct ivpu_device *vdev, void *msg)
 	ret = ivpu_job_done(vdev, payload->job_id, payload->job_status);
 	if (ret)
 		ivpu_err(vdev, "Failed to finish job %d: %d\n", payload->job_id, ret);
+
+	if (!ret && !xa_empty(&vdev->submitted_jobs_xa))
+		ivpu_start_job_timeout_detection(vdev);
 }
 
 void ivpu_jobs_abort_all(struct ivpu_device *vdev)
@@ -400,6 +401,8 @@ static int ivpu_direct_job_submission(struct ivpu_job *job)
 	if (ret)
 		goto err_xa_erase;
 
+	ivpu_start_job_timeout_detection(vdev);
+
 	ivpu_dbg(vdev, JOB, "Job submitted: id %3u addr 0x%llx ctx %2d engine %d next %d\n",
 		 job->job_id, job->cmd_buf_vpu_addr, file_priv->ctx.id,
 		 job->engine_idx, cmdq->jobq->header.tail);
@@ -569,7 +572,6 @@ static int ivpu_job_done_thread(void *arg)
 	struct ivpu_device *vdev = (struct ivpu_device *)arg;
 	struct ivpu_ipc_consumer cons;
 	struct vpu_jsm_msg jsm_msg;
-	bool jobs_submitted;
 	unsigned int timeout;
 	int ret;
 
@@ -578,18 +580,10 @@ static int ivpu_job_done_thread(void *arg)
 	ivpu_ipc_consumer_add(vdev, &cons, VPU_IPC_CHAN_JOB_RET);
 
 	while (!kthread_should_stop()) {
-		timeout = ivpu_tdr_timeout_ms ? ivpu_tdr_timeout_ms : vdev->timeout.tdr;
-		jobs_submitted = !xa_empty(&vdev->submitted_jobs_xa);
 		ret = ivpu_ipc_receive(vdev, &cons, NULL, &jsm_msg, timeout);
-		if (!ret) {
+		if (!ret)
 			ivpu_job_done_message(vdev, &jsm_msg);
-		} else if (ret == -ETIMEDOUT) {
-			if (jobs_submitted && !xa_empty(&vdev->submitted_jobs_xa)) {
-				ivpu_err(vdev, "TDR detected, timeout %d ms", timeout);
-				ivpu_hw_diagnose_failure(vdev);
-				ivpu_pm_schedule_recovery(vdev);
-			}
-		}
+
 		if (kthread_should_park()) {
 			ivpu_dbg(vdev, JOB, "Parked %s\n", __func__);
 			kthread_parkme();
diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c
index d915f3c2991f..0af8864cb3b5 100644
--- a/drivers/accel/ivpu/ivpu_pm.c
+++ b/drivers/accel/ivpu/ivpu_pm.c
@@ -23,6 +23,10 @@ static bool ivpu_disable_recovery;
 module_param_named_unsafe(disable_recovery, ivpu_disable_recovery, bool, 0644);
 MODULE_PARM_DESC(disable_recovery, "Disables recovery when VPU hang is detected");
 
+static unsigned long ivpu_tdr_timeout_ms;
+module_param_named(tdr_timeout_ms, ivpu_tdr_timeout_ms, ulong, 0644);
+MODULE_PARM_DESC(tdr_timeout_ms, "Timeout for device hang detection, in milliseconds, 0 - default");
+
 #define PM_RESCHEDULE_LIMIT     5
 
 static void ivpu_pm_prepare_cold_boot(struct ivpu_device *vdev)
@@ -141,6 +145,31 @@ void ivpu_pm_schedule_recovery(struct ivpu_device *vdev)
 	}
 }
 
+static void ivpu_job_timeout_work(struct work_struct *work)
+{
+	struct ivpu_pm_info *pm = container_of(work, struct ivpu_pm_info, job_timeout_work.work);
+	struct ivpu_device *vdev = pm->vdev;
+	unsigned long timeout_ms = ivpu_tdr_timeout_ms ? ivpu_tdr_timeout_ms : vdev->timeout.tdr;
+
+	ivpu_err(vdev, "TDR detected, timeout %lu ms", timeout_ms);
+	ivpu_hw_diagnose_failure(vdev);
+
+	ivpu_pm_schedule_recovery(vdev);
+}
+
+void ivpu_start_job_timeout_detection(struct ivpu_device *vdev)
+{
+	unsigned long timeout_ms = ivpu_tdr_timeout_ms ? ivpu_tdr_timeout_ms : vdev->timeout.tdr;
+
+	/* No-op if already queued */
+	queue_delayed_work(system_wq, &vdev->pm->job_timeout_work, msecs_to_jiffies(timeout_ms));
+}
+
+void ivpu_stop_job_timeout_detection(struct ivpu_device *vdev)
+{
+	cancel_delayed_work_sync(&vdev->pm->job_timeout_work);
+}
+
 int ivpu_pm_suspend_cb(struct device *dev)
 {
 	struct drm_device *drm = dev_get_drvdata(dev);
@@ -317,6 +346,7 @@ void ivpu_pm_init(struct ivpu_device *vdev)
 
 	atomic_set(&pm->in_reset, 0);
 	INIT_WORK(&pm->recovery_work, ivpu_pm_recovery_work);
+	INIT_DELAYED_WORK(&pm->job_timeout_work, ivpu_job_timeout_work);
 
 	if (ivpu_disable_recovery)
 		delay = -1;
@@ -331,6 +361,7 @@ void ivpu_pm_init(struct ivpu_device *vdev)
 
 void ivpu_pm_cancel_recovery(struct ivpu_device *vdev)
 {
+	drm_WARN_ON(&vdev->drm, delayed_work_pending(&vdev->pm->job_timeout_work));
 	cancel_work_sync(&vdev->pm->recovery_work);
 }
 
diff --git a/drivers/accel/ivpu/ivpu_pm.h b/drivers/accel/ivpu/ivpu_pm.h
index 044db150be07..97c6e0b0aa42 100644
--- a/drivers/accel/ivpu/ivpu_pm.h
+++ b/drivers/accel/ivpu/ivpu_pm.h
@@ -12,6 +12,7 @@ struct ivpu_device;
 
 struct ivpu_pm_info {
 	struct ivpu_device *vdev;
+	struct delayed_work job_timeout_work;
 	struct work_struct recovery_work;
 	atomic_t in_reset;
 	atomic_t reset_counter;
@@ -37,5 +38,7 @@ int __must_check ivpu_rpm_get_if_active(struct ivpu_device *vdev);
 void ivpu_rpm_put(struct ivpu_device *vdev);
 
 void ivpu_pm_schedule_recovery(struct ivpu_device *vdev);
+void ivpu_start_job_timeout_detection(struct ivpu_device *vdev);
+void ivpu_stop_job_timeout_detection(struct ivpu_device *vdev);
 
 #endif /* __IVPU_PM_H__ */
-- 
cgit 


From 3b434a3445fff3149128db0169da864d67057325 Mon Sep 17 00:00:00 2001
From: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Date: Mon, 13 Nov 2023 18:02:52 +0100
Subject: accel/ivpu: Use threaded IRQ to handle JOB done messages

Remove job_done thread and replace it with generic callback based
mechanism.

Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231113170252.758137-6-jacek.lawrynowicz@linux.intel.com
---
 drivers/accel/ivpu/ivpu_drv.c     |  30 +++---
 drivers/accel/ivpu/ivpu_drv.h     |   3 +-
 drivers/accel/ivpu/ivpu_hw_37xx.c |  29 +++---
 drivers/accel/ivpu/ivpu_hw_40xx.c |  30 +++---
 drivers/accel/ivpu/ivpu_ipc.c     | 196 +++++++++++++++++++++-----------------
 drivers/accel/ivpu/ivpu_ipc.h     |  22 ++++-
 drivers/accel/ivpu/ivpu_job.c     |  84 ++++------------
 drivers/accel/ivpu/ivpu_job.h     |   6 +-
 8 files changed, 199 insertions(+), 201 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c
index bc15b06e1744..64927682161b 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -318,13 +318,11 @@ static int ivpu_wait_for_ready(struct ivpu_device *vdev)
 	if (ivpu_test_mode & IVPU_TEST_MODE_FW_TEST)
 		return 0;
 
-	ivpu_ipc_consumer_add(vdev, &cons, IVPU_IPC_CHAN_BOOT_MSG);
+	ivpu_ipc_consumer_add(vdev, &cons, IVPU_IPC_CHAN_BOOT_MSG, NULL);
 
 	timeout = jiffies + msecs_to_jiffies(vdev->timeout.boot);
 	while (1) {
-		ret = ivpu_ipc_irq_handler(vdev);
-		if (ret)
-			break;
+		ivpu_ipc_irq_handler(vdev, NULL);
 		ret = ivpu_ipc_receive(vdev, &cons, &ipc_hdr, NULL, 0);
 		if (ret != -ETIMEDOUT || time_after_eq(jiffies, timeout))
 			break;
@@ -378,7 +376,6 @@ int ivpu_boot(struct ivpu_device *vdev)
 	enable_irq(vdev->irq);
 	ivpu_hw_irq_enable(vdev);
 	ivpu_ipc_enable(vdev);
-	ivpu_job_done_thread_enable(vdev);
 	return 0;
 }
 
@@ -388,7 +385,6 @@ void ivpu_prepare_for_reset(struct ivpu_device *vdev)
 	disable_irq(vdev->irq);
 	ivpu_ipc_disable(vdev);
 	ivpu_mmu_disable(vdev);
-	ivpu_job_done_thread_disable(vdev);
 }
 
 int ivpu_shutdown(struct ivpu_device *vdev)
@@ -429,6 +425,13 @@ static const struct drm_driver driver = {
 	.minor = DRM_IVPU_DRIVER_MINOR,
 };
 
+static irqreturn_t ivpu_irq_thread_handler(int irq, void *arg)
+{
+	struct ivpu_device *vdev = arg;
+
+	return ivpu_ipc_irq_thread_handler(vdev);
+}
+
 static int ivpu_irq_init(struct ivpu_device *vdev)
 {
 	struct pci_dev *pdev = to_pci_dev(vdev->drm.dev);
@@ -442,8 +445,8 @@ static int ivpu_irq_init(struct ivpu_device *vdev)
 
 	vdev->irq = pci_irq_vector(pdev, 0);
 
-	ret = devm_request_irq(vdev->drm.dev, vdev->irq, vdev->hw->ops->irq_handler,
-			       IRQF_NO_AUTOEN, DRIVER_NAME, vdev);
+	ret = devm_request_threaded_irq(vdev->drm.dev, vdev->irq, vdev->hw->ops->irq_handler,
+					ivpu_irq_thread_handler, IRQF_NO_AUTOEN, DRIVER_NAME, vdev);
 	if (ret)
 		ivpu_err(vdev, "Failed to request an IRQ %d\n", ret);
 
@@ -581,20 +584,15 @@ static int ivpu_dev_init(struct ivpu_device *vdev)
 
 	ivpu_pm_init(vdev);
 
-	ret = ivpu_job_done_thread_init(vdev);
-	if (ret)
-		goto err_ipc_fini;
-
 	ret = ivpu_boot(vdev);
 	if (ret)
-		goto err_job_done_thread_fini;
+		goto err_ipc_fini;
 
+	ivpu_job_done_consumer_init(vdev);
 	ivpu_pm_enable(vdev);
 
 	return 0;
 
-err_job_done_thread_fini:
-	ivpu_job_done_thread_fini(vdev);
 err_ipc_fini:
 	ivpu_ipc_fini(vdev);
 err_fw_fini:
@@ -619,7 +617,7 @@ static void ivpu_dev_fini(struct ivpu_device *vdev)
 	ivpu_shutdown(vdev);
 	if (IVPU_WA(d3hot_after_power_off))
 		pci_set_power_state(to_pci_dev(vdev->drm.dev), PCI_D3hot);
-	ivpu_job_done_thread_fini(vdev);
+	ivpu_job_done_consumer_fini(vdev);
 	ivpu_pm_cancel_recovery(vdev);
 
 	ivpu_ipc_fini(vdev);
diff --git a/drivers/accel/ivpu/ivpu_drv.h b/drivers/accel/ivpu/ivpu_drv.h
index f1e7072449f1..ebc4b84f27b2 100644
--- a/drivers/accel/ivpu/ivpu_drv.h
+++ b/drivers/accel/ivpu/ivpu_drv.h
@@ -17,6 +17,7 @@
 #include <uapi/drm/ivpu_accel.h>
 
 #include "ivpu_mmu_context.h"
+#include "ivpu_ipc.h"
 
 #define DRIVER_NAME "intel_vpu"
 #define DRIVER_DESC "Driver for Intel NPU (Neural Processing Unit)"
@@ -120,7 +121,7 @@ struct ivpu_device {
 	struct list_head bo_list;
 
 	struct xarray submitted_jobs_xa;
-	struct task_struct *job_done_thread;
+	struct ivpu_ipc_consumer job_done_consumer;
 
 	atomic64_t unique_id_counter;
 
diff --git a/drivers/accel/ivpu/ivpu_hw_37xx.c b/drivers/accel/ivpu/ivpu_hw_37xx.c
index a172cfb1c31f..4ab1f14cf360 100644
--- a/drivers/accel/ivpu/ivpu_hw_37xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_37xx.c
@@ -891,17 +891,20 @@ static void ivpu_hw_37xx_irq_noc_firewall_handler(struct ivpu_device *vdev)
 }
 
 /* Handler for IRQs from VPU core (irqV) */
-static u32 ivpu_hw_37xx_irqv_handler(struct ivpu_device *vdev, int irq)
+static bool ivpu_hw_37xx_irqv_handler(struct ivpu_device *vdev, int irq, bool *wake_thread)
 {
 	u32 status = REGV_RD32(VPU_37XX_HOST_SS_ICB_STATUS_0) & ICB_0_IRQ_MASK;
 
+	if (!status)
+		return false;
+
 	REGV_WR32(VPU_37XX_HOST_SS_ICB_CLEAR_0, status);
 
 	if (REG_TEST_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, MMU_IRQ_0_INT, status))
 		ivpu_mmu_irq_evtq_handler(vdev);
 
 	if (REG_TEST_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, HOST_IPC_FIFO_INT, status))
-		ivpu_ipc_irq_handler(vdev);
+		ivpu_ipc_irq_handler(vdev, wake_thread);
 
 	if (REG_TEST_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, MMU_IRQ_1_INT, status))
 		ivpu_dbg(vdev, IRQ, "MMU sync complete\n");
@@ -918,17 +921,17 @@ static u32 ivpu_hw_37xx_irqv_handler(struct ivpu_device *vdev, int irq)
 	if (REG_TEST_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, NOC_FIREWALL_INT, status))
 		ivpu_hw_37xx_irq_noc_firewall_handler(vdev);
 
-	return status;
+	return true;
 }
 
 /* Handler for IRQs from Buttress core (irqB) */
-static u32 ivpu_hw_37xx_irqb_handler(struct ivpu_device *vdev, int irq)
+static bool ivpu_hw_37xx_irqb_handler(struct ivpu_device *vdev, int irq)
 {
 	u32 status = REGB_RD32(VPU_37XX_BUTTRESS_INTERRUPT_STAT) & BUTTRESS_IRQ_MASK;
 	bool schedule_recovery = false;
 
-	if (status == 0)
-		return 0;
+	if (!status)
+		return false;
 
 	if (REG_TEST_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, FREQ_CHANGE, status))
 		ivpu_dbg(vdev, IRQ, "FREQ_CHANGE irq: %08x",
@@ -964,23 +967,27 @@ static u32 ivpu_hw_37xx_irqb_handler(struct ivpu_device *vdev, int irq)
 	if (schedule_recovery)
 		ivpu_pm_schedule_recovery(vdev);
 
-	return status;
+	return true;
 }
 
 static irqreturn_t ivpu_hw_37xx_irq_handler(int irq, void *ptr)
 {
 	struct ivpu_device *vdev = ptr;
-	u32 ret_irqv, ret_irqb;
+	bool irqv_handled, irqb_handled, wake_thread = false;
 
 	REGB_WR32(VPU_37XX_BUTTRESS_GLOBAL_INT_MASK, 0x1);
 
-	ret_irqv = ivpu_hw_37xx_irqv_handler(vdev, irq);
-	ret_irqb = ivpu_hw_37xx_irqb_handler(vdev, irq);
+	irqv_handled = ivpu_hw_37xx_irqv_handler(vdev, irq, &wake_thread);
+	irqb_handled = ivpu_hw_37xx_irqb_handler(vdev, irq);
 
 	/* Re-enable global interrupts to re-trigger MSI for pending interrupts */
 	REGB_WR32(VPU_37XX_BUTTRESS_GLOBAL_INT_MASK, 0x0);
 
-	return IRQ_RETVAL(ret_irqb | ret_irqv);
+	if (wake_thread)
+		return IRQ_WAKE_THREAD;
+	if (irqv_handled || irqb_handled)
+		return IRQ_HANDLED;
+	return IRQ_NONE;
 }
 
 static void ivpu_hw_37xx_diagnose_failure(struct ivpu_device *vdev)
diff --git a/drivers/accel/ivpu/ivpu_hw_40xx.c b/drivers/accel/ivpu/ivpu_hw_40xx.c
index f7e1f5c0667b..eba2fdef2ace 100644
--- a/drivers/accel/ivpu/ivpu_hw_40xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_40xx.c
@@ -1047,13 +1047,12 @@ static void ivpu_hw_40xx_irq_noc_firewall_handler(struct ivpu_device *vdev)
 }
 
 /* Handler for IRQs from VPU core (irqV) */
-static irqreturn_t ivpu_hw_40xx_irqv_handler(struct ivpu_device *vdev, int irq)
+static bool ivpu_hw_40xx_irqv_handler(struct ivpu_device *vdev, int irq, bool *wake_thread)
 {
 	u32 status = REGV_RD32(VPU_40XX_HOST_SS_ICB_STATUS_0) & ICB_0_IRQ_MASK;
-	irqreturn_t ret = IRQ_NONE;
 
 	if (!status)
-		return IRQ_NONE;
+		return false;
 
 	REGV_WR32(VPU_40XX_HOST_SS_ICB_CLEAR_0, status);
 
@@ -1061,7 +1060,7 @@ static irqreturn_t ivpu_hw_40xx_irqv_handler(struct ivpu_device *vdev, int irq)
 		ivpu_mmu_irq_evtq_handler(vdev);
 
 	if (REG_TEST_FLD(VPU_40XX_HOST_SS_ICB_STATUS_0, HOST_IPC_FIFO_INT, status))
-		ret |= ivpu_ipc_irq_handler(vdev);
+		ivpu_ipc_irq_handler(vdev, wake_thread);
 
 	if (REG_TEST_FLD(VPU_40XX_HOST_SS_ICB_STATUS_0, MMU_IRQ_1_INT, status))
 		ivpu_dbg(vdev, IRQ, "MMU sync complete\n");
@@ -1078,17 +1077,17 @@ static irqreturn_t ivpu_hw_40xx_irqv_handler(struct ivpu_device *vdev, int irq)
 	if (REG_TEST_FLD(VPU_40XX_HOST_SS_ICB_STATUS_0, NOC_FIREWALL_INT, status))
 		ivpu_hw_40xx_irq_noc_firewall_handler(vdev);
 
-	return ret;
+	return true;
 }
 
 /* Handler for IRQs from Buttress core (irqB) */
-static irqreturn_t ivpu_hw_40xx_irqb_handler(struct ivpu_device *vdev, int irq)
+static bool ivpu_hw_40xx_irqb_handler(struct ivpu_device *vdev, int irq)
 {
 	bool schedule_recovery = false;
 	u32 status = REGB_RD32(VPU_40XX_BUTTRESS_INTERRUPT_STAT) & BUTTRESS_IRQ_MASK;
 
-	if (status == 0)
-		return IRQ_NONE;
+	if (!status)
+		return false;
 
 	if (REG_TEST_FLD(VPU_40XX_BUTTRESS_INTERRUPT_STAT, FREQ_CHANGE, status))
 		ivpu_dbg(vdev, IRQ, "FREQ_CHANGE");
@@ -1140,26 +1139,27 @@ static irqreturn_t ivpu_hw_40xx_irqb_handler(struct ivpu_device *vdev, int irq)
 	if (schedule_recovery)
 		ivpu_pm_schedule_recovery(vdev);
 
-	return IRQ_HANDLED;
+	return true;
 }
 
 static irqreturn_t ivpu_hw_40xx_irq_handler(int irq, void *ptr)
 {
+	bool irqv_handled, irqb_handled, wake_thread = false;
 	struct ivpu_device *vdev = ptr;
-	irqreturn_t ret = IRQ_NONE;
 
 	REGB_WR32(VPU_40XX_BUTTRESS_GLOBAL_INT_MASK, 0x1);
 
-	ret |= ivpu_hw_40xx_irqv_handler(vdev, irq);
-	ret |= ivpu_hw_40xx_irqb_handler(vdev, irq);
+	irqv_handled = ivpu_hw_40xx_irqv_handler(vdev, irq, &wake_thread);
+	irqb_handled = ivpu_hw_40xx_irqb_handler(vdev, irq);
 
 	/* Re-enable global interrupts to re-trigger MSI for pending interrupts */
 	REGB_WR32(VPU_40XX_BUTTRESS_GLOBAL_INT_MASK, 0x0);
 
-	if (ret & IRQ_WAKE_THREAD)
+	if (wake_thread)
 		return IRQ_WAKE_THREAD;
-
-	return ret;
+	if (irqv_handled || irqb_handled)
+		return IRQ_HANDLED;
+	return IRQ_NONE;
 }
 
 static void ivpu_hw_40xx_diagnose_failure(struct ivpu_device *vdev)
diff --git a/drivers/accel/ivpu/ivpu_ipc.c b/drivers/accel/ivpu/ivpu_ipc.c
index 1dd4413dc88f..e86621f16f85 100644
--- a/drivers/accel/ivpu/ivpu_ipc.c
+++ b/drivers/accel/ivpu/ivpu_ipc.c
@@ -5,7 +5,6 @@
 
 #include <linux/genalloc.h>
 #include <linux/highmem.h>
-#include <linux/kthread.h>
 #include <linux/pm_runtime.h>
 #include <linux/wait.h>
 
@@ -18,19 +17,12 @@
 #include "ivpu_pm.h"
 
 #define IPC_MAX_RX_MSG	128
-#define IS_KTHREAD()	(get_current()->flags & PF_KTHREAD)
 
 struct ivpu_ipc_tx_buf {
 	struct ivpu_ipc_hdr ipc;
 	struct vpu_jsm_msg jsm;
 };
 
-struct ivpu_ipc_rx_msg {
-	struct list_head link;
-	struct ivpu_ipc_hdr *ipc_hdr;
-	struct vpu_jsm_msg *jsm_msg;
-};
-
 static void ivpu_ipc_msg_dump(struct ivpu_device *vdev, char *c,
 			      struct ivpu_ipc_hdr *ipc_hdr, u32 vpu_addr)
 {
@@ -140,8 +132,49 @@ static void ivpu_ipc_tx(struct ivpu_device *vdev, u32 vpu_addr)
 	ivpu_hw_reg_ipc_tx_set(vdev, vpu_addr);
 }
 
-void
-ivpu_ipc_consumer_add(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons, u32 channel)
+static void
+ivpu_ipc_rx_msg_add(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
+		    struct ivpu_ipc_hdr *ipc_hdr, struct vpu_jsm_msg *jsm_msg)
+{
+	struct ivpu_ipc_info *ipc = vdev->ipc;
+	struct ivpu_ipc_rx_msg *rx_msg;
+
+	lockdep_assert_held(&ipc->cons_lock);
+	lockdep_assert_irqs_disabled();
+
+	rx_msg = kzalloc(sizeof(*rx_msg), GFP_ATOMIC);
+	if (!rx_msg) {
+		ivpu_ipc_rx_mark_free(vdev, ipc_hdr, jsm_msg);
+		return;
+	}
+
+	atomic_inc(&ipc->rx_msg_count);
+
+	rx_msg->ipc_hdr = ipc_hdr;
+	rx_msg->jsm_msg = jsm_msg;
+	rx_msg->callback = cons->rx_callback;
+
+	if (rx_msg->callback) {
+		list_add_tail(&rx_msg->link, &ipc->cb_msg_list);
+	} else {
+		spin_lock(&cons->rx_lock);
+		list_add_tail(&rx_msg->link, &cons->rx_msg_list);
+		spin_unlock(&cons->rx_lock);
+		wake_up(&cons->rx_msg_wq);
+	}
+}
+
+static void
+ivpu_ipc_rx_msg_del(struct ivpu_device *vdev, struct ivpu_ipc_rx_msg *rx_msg)
+{
+	list_del(&rx_msg->link);
+	ivpu_ipc_rx_mark_free(vdev, rx_msg->ipc_hdr, rx_msg->jsm_msg);
+	atomic_dec(&vdev->ipc->rx_msg_count);
+	kfree(rx_msg);
+}
+
+void ivpu_ipc_consumer_add(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
+			   u32 channel, ivpu_ipc_rx_callback_t rx_callback)
 {
 	struct ivpu_ipc_info *ipc = vdev->ipc;
 
@@ -150,13 +183,14 @@ ivpu_ipc_consumer_add(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
 	cons->tx_vpu_addr = 0;
 	cons->request_id = 0;
 	cons->aborted = false;
+	cons->rx_callback = rx_callback;
 	spin_lock_init(&cons->rx_lock);
 	INIT_LIST_HEAD(&cons->rx_msg_list);
 	init_waitqueue_head(&cons->rx_msg_wq);
 
-	spin_lock_irq(&ipc->cons_list_lock);
+	spin_lock_irq(&ipc->cons_lock);
 	list_add_tail(&cons->link, &ipc->cons_list);
-	spin_unlock_irq(&ipc->cons_list_lock);
+	spin_unlock_irq(&ipc->cons_lock);
 }
 
 void ivpu_ipc_consumer_del(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons)
@@ -164,18 +198,13 @@ void ivpu_ipc_consumer_del(struct ivpu_device *vdev, struct ivpu_ipc_consumer *c
 	struct ivpu_ipc_info *ipc = vdev->ipc;
 	struct ivpu_ipc_rx_msg *rx_msg, *r;
 
-	spin_lock_irq(&ipc->cons_list_lock);
+	spin_lock_irq(&ipc->cons_lock);
 	list_del(&cons->link);
-	spin_unlock_irq(&ipc->cons_list_lock);
+	spin_unlock_irq(&ipc->cons_lock);
 
 	spin_lock_irq(&cons->rx_lock);
-	list_for_each_entry_safe(rx_msg, r, &cons->rx_msg_list, link) {
-		list_del(&rx_msg->link);
-		if (!cons->aborted)
-			ivpu_ipc_rx_mark_free(vdev, rx_msg->ipc_hdr, rx_msg->jsm_msg);
-		atomic_dec(&ipc->rx_msg_count);
-		kfree(rx_msg);
-	}
+	list_for_each_entry_safe(rx_msg, r, &cons->rx_msg_list, link)
+		ivpu_ipc_rx_msg_del(vdev, rx_msg);
 	spin_unlock_irq(&cons->rx_lock);
 
 	ivpu_ipc_tx_release(vdev, cons->tx_vpu_addr);
@@ -205,15 +234,12 @@ unlock:
 	return ret;
 }
 
-static int ivpu_ipc_rx_need_wakeup(struct ivpu_ipc_consumer *cons)
+static bool ivpu_ipc_rx_need_wakeup(struct ivpu_ipc_consumer *cons)
 {
-	int ret = 0;
-
-	if (IS_KTHREAD())
-		ret |= (kthread_should_stop() || kthread_should_park());
+	bool ret;
 
 	spin_lock_irq(&cons->rx_lock);
-	ret |= !list_empty(&cons->rx_msg_list) || cons->aborted;
+	ret = !list_empty(&cons->rx_msg_list) || cons->aborted;
 	spin_unlock_irq(&cons->rx_lock);
 
 	return ret;
@@ -221,19 +247,18 @@ static int ivpu_ipc_rx_need_wakeup(struct ivpu_ipc_consumer *cons)
 
 int ivpu_ipc_receive(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
 		     struct ivpu_ipc_hdr *ipc_buf,
-		     struct vpu_jsm_msg *ipc_payload, unsigned long timeout_ms)
+		     struct vpu_jsm_msg *jsm_msg, unsigned long timeout_ms)
 {
-	struct ivpu_ipc_info *ipc = vdev->ipc;
 	struct ivpu_ipc_rx_msg *rx_msg;
 	int wait_ret, ret = 0;
 
+	if (drm_WARN_ONCE(&vdev->drm, cons->rx_callback, "Consumer works only in async mode\n"))
+		return -EINVAL;
+
 	wait_ret = wait_event_timeout(cons->rx_msg_wq,
 				      ivpu_ipc_rx_need_wakeup(cons),
 				      msecs_to_jiffies(timeout_ms));
 
-	if (IS_KTHREAD() && kthread_should_stop())
-		return -EINTR;
-
 	if (wait_ret == 0)
 		return -ETIMEDOUT;
 
@@ -247,27 +272,23 @@ int ivpu_ipc_receive(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
 		spin_unlock_irq(&cons->rx_lock);
 		return -EAGAIN;
 	}
-	list_del(&rx_msg->link);
-	spin_unlock_irq(&cons->rx_lock);
 
 	if (ipc_buf)
 		memcpy(ipc_buf, rx_msg->ipc_hdr, sizeof(*ipc_buf));
 	if (rx_msg->jsm_msg) {
-		u32 size = min_t(int, rx_msg->ipc_hdr->data_size, sizeof(*ipc_payload));
+		u32 size = min_t(int, rx_msg->ipc_hdr->data_size, sizeof(*jsm_msg));
 
 		if (rx_msg->jsm_msg->result != VPU_JSM_STATUS_SUCCESS) {
 			ivpu_dbg(vdev, IPC, "IPC resp result error: %d\n", rx_msg->jsm_msg->result);
 			ret = -EBADMSG;
 		}
 
-		if (ipc_payload)
-			memcpy(ipc_payload, rx_msg->jsm_msg, size);
+		if (jsm_msg)
+			memcpy(jsm_msg, rx_msg->jsm_msg, size);
 	}
 
-	ivpu_ipc_rx_mark_free(vdev, rx_msg->ipc_hdr, rx_msg->jsm_msg);
-	atomic_dec(&ipc->rx_msg_count);
-	kfree(rx_msg);
-
+	ivpu_ipc_rx_msg_del(vdev, rx_msg);
+	spin_unlock_irq(&cons->rx_lock);
 	return ret;
 }
 
@@ -280,7 +301,7 @@ ivpu_ipc_send_receive_internal(struct ivpu_device *vdev, struct vpu_jsm_msg *req
 	struct ivpu_ipc_consumer cons;
 	int ret;
 
-	ivpu_ipc_consumer_add(vdev, &cons, channel);
+	ivpu_ipc_consumer_add(vdev, &cons, channel, NULL);
 
 	ret = ivpu_ipc_send(vdev, &cons, req);
 	if (ret) {
@@ -359,35 +380,7 @@ ivpu_ipc_match_consumer(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons
 	return false;
 }
 
-static void
-ivpu_ipc_dispatch(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
-		  struct ivpu_ipc_hdr *ipc_hdr, struct vpu_jsm_msg *jsm_msg)
-{
-	struct ivpu_ipc_info *ipc = vdev->ipc;
-	struct ivpu_ipc_rx_msg *rx_msg;
-
-	lockdep_assert_held(&ipc->cons_list_lock);
-	lockdep_assert_irqs_disabled();
-
-	rx_msg = kzalloc(sizeof(*rx_msg), GFP_ATOMIC);
-	if (!rx_msg) {
-		ivpu_ipc_rx_mark_free(vdev, ipc_hdr, jsm_msg);
-		return;
-	}
-
-	atomic_inc(&ipc->rx_msg_count);
-
-	rx_msg->ipc_hdr = ipc_hdr;
-	rx_msg->jsm_msg = jsm_msg;
-
-	spin_lock(&cons->rx_lock);
-	list_add_tail(&rx_msg->link, &cons->rx_msg_list);
-	spin_unlock(&cons->rx_lock);
-
-	wake_up(&cons->rx_msg_wq);
-}
-
-int ivpu_ipc_irq_handler(struct ivpu_device *vdev)
+void ivpu_ipc_irq_handler(struct ivpu_device *vdev, bool *wake_thread)
 {
 	struct ivpu_ipc_info *ipc = vdev->ipc;
 	struct ivpu_ipc_consumer *cons;
@@ -405,7 +398,7 @@ int ivpu_ipc_irq_handler(struct ivpu_device *vdev)
 		vpu_addr = ivpu_hw_reg_ipc_rx_addr_get(vdev);
 		if (vpu_addr == REG_IO_ERROR) {
 			ivpu_err_ratelimited(vdev, "Failed to read IPC rx addr register\n");
-			return -EIO;
+			return;
 		}
 
 		ipc_hdr = ivpu_to_cpu_addr(ipc->mem_rx, vpu_addr);
@@ -435,15 +428,15 @@ int ivpu_ipc_irq_handler(struct ivpu_device *vdev)
 		}
 
 		dispatched = false;
-		spin_lock_irqsave(&ipc->cons_list_lock, flags);
+		spin_lock_irqsave(&ipc->cons_lock, flags);
 		list_for_each_entry(cons, &ipc->cons_list, link) {
 			if (ivpu_ipc_match_consumer(vdev, cons, ipc_hdr, jsm_msg)) {
-				ivpu_ipc_dispatch(vdev, cons, ipc_hdr, jsm_msg);
+				ivpu_ipc_rx_msg_add(vdev, cons, ipc_hdr, jsm_msg);
 				dispatched = true;
 				break;
 			}
 		}
-		spin_unlock_irqrestore(&ipc->cons_list_lock, flags);
+		spin_unlock_irqrestore(&ipc->cons_lock, flags);
 
 		if (!dispatched) {
 			ivpu_dbg(vdev, IPC, "IPC RX msg 0x%x dropped (no consumer)\n", vpu_addr);
@@ -451,7 +444,28 @@ int ivpu_ipc_irq_handler(struct ivpu_device *vdev)
 		}
 	}
 
-	return 0;
+	if (wake_thread)
+		*wake_thread = !list_empty(&ipc->cb_msg_list);
+}
+
+irqreturn_t ivpu_ipc_irq_thread_handler(struct ivpu_device *vdev)
+{
+	struct ivpu_ipc_info *ipc = vdev->ipc;
+	struct ivpu_ipc_rx_msg *rx_msg, *r;
+	struct list_head cb_msg_list;
+
+	INIT_LIST_HEAD(&cb_msg_list);
+
+	spin_lock_irq(&ipc->cons_lock);
+	list_splice_tail_init(&ipc->cb_msg_list, &cb_msg_list);
+	spin_unlock_irq(&ipc->cons_lock);
+
+	list_for_each_entry_safe(rx_msg, r, &cb_msg_list, link) {
+		rx_msg->callback(vdev, rx_msg->ipc_hdr, rx_msg->jsm_msg);
+		ivpu_ipc_rx_msg_del(vdev, rx_msg);
+	}
+
+	return IRQ_HANDLED;
 }
 
 int ivpu_ipc_init(struct ivpu_device *vdev)
@@ -486,10 +500,10 @@ int ivpu_ipc_init(struct ivpu_device *vdev)
 		goto err_free_rx;
 	}
 
+	spin_lock_init(&ipc->cons_lock);
 	INIT_LIST_HEAD(&ipc->cons_list);
-	spin_lock_init(&ipc->cons_list_lock);
+	INIT_LIST_HEAD(&ipc->cb_msg_list);
 	drmm_mutex_init(&vdev->drm, &ipc->lock);
-
 	ivpu_ipc_reset(vdev);
 	return 0;
 
@@ -502,6 +516,13 @@ err_free_tx:
 
 void ivpu_ipc_fini(struct ivpu_device *vdev)
 {
+	struct ivpu_ipc_info *ipc = vdev->ipc;
+
+	drm_WARN_ON(&vdev->drm, ipc->on);
+	drm_WARN_ON(&vdev->drm, !list_empty(&ipc->cons_list));
+	drm_WARN_ON(&vdev->drm, !list_empty(&ipc->cb_msg_list));
+	drm_WARN_ON(&vdev->drm, atomic_read(&ipc->rx_msg_count) > 0);
+
 	ivpu_ipc_mem_fini(vdev);
 }
 
@@ -518,22 +539,27 @@ void ivpu_ipc_disable(struct ivpu_device *vdev)
 {
 	struct ivpu_ipc_info *ipc = vdev->ipc;
 	struct ivpu_ipc_consumer *cons, *c;
-	unsigned long flags;
+	struct ivpu_ipc_rx_msg *rx_msg, *r;
+
+	drm_WARN_ON(&vdev->drm, !list_empty(&ipc->cb_msg_list));
 
 	mutex_lock(&ipc->lock);
 	ipc->on = false;
 	mutex_unlock(&ipc->lock);
 
-	spin_lock_irqsave(&ipc->cons_list_lock, flags);
+	spin_lock_irq(&ipc->cons_lock);
 	list_for_each_entry_safe(cons, c, &ipc->cons_list, link) {
-		if (cons->channel != VPU_IPC_CHAN_JOB_RET) {
-			spin_lock(&cons->rx_lock);
+		spin_lock(&cons->rx_lock);
+		if (!cons->rx_callback)
 			cons->aborted = true;
-			spin_unlock(&cons->rx_lock);
-		}
+		list_for_each_entry_safe(rx_msg, r, &cons->rx_msg_list, link)
+			ivpu_ipc_rx_msg_del(vdev, rx_msg);
+		spin_unlock(&cons->rx_lock);
 		wake_up(&cons->rx_msg_wq);
 	}
-	spin_unlock_irqrestore(&ipc->cons_list_lock, flags);
+	spin_unlock_irq(&ipc->cons_lock);
+
+	drm_WARN_ON(&vdev->drm, atomic_read(&ipc->rx_msg_count) > 0);
 }
 
 void ivpu_ipc_reset(struct ivpu_device *vdev)
diff --git a/drivers/accel/ivpu/ivpu_ipc.h b/drivers/accel/ivpu/ivpu_ipc.h
index 71b2e648dffd..40ca3cc4e61f 100644
--- a/drivers/accel/ivpu/ivpu_ipc.h
+++ b/drivers/accel/ivpu/ivpu_ipc.h
@@ -42,12 +42,24 @@ struct ivpu_ipc_hdr {
 	u8 status;
 } __packed __aligned(IVPU_IPC_ALIGNMENT);
 
+typedef void (*ivpu_ipc_rx_callback_t)(struct ivpu_device *vdev,
+				       struct ivpu_ipc_hdr *ipc_hdr,
+				       struct vpu_jsm_msg *jsm_msg);
+
+struct ivpu_ipc_rx_msg {
+	struct list_head link;
+	struct ivpu_ipc_hdr *ipc_hdr;
+	struct vpu_jsm_msg *jsm_msg;
+	ivpu_ipc_rx_callback_t callback;
+};
+
 struct ivpu_ipc_consumer {
 	struct list_head link;
 	u32 channel;
 	u32 tx_vpu_addr;
 	u32 request_id;
 	bool aborted;
+	ivpu_ipc_rx_callback_t rx_callback;
 
 	spinlock_t rx_lock; /* Protects rx_msg_list and aborted */
 	struct list_head rx_msg_list;
@@ -61,8 +73,9 @@ struct ivpu_ipc_info {
 
 	atomic_t rx_msg_count;
 
-	spinlock_t cons_list_lock; /* Protects cons_list */
+	spinlock_t cons_lock; /* Protects cons_list and cb_msg_list */
 	struct list_head cons_list;
+	struct list_head cb_msg_list;
 
 	atomic_t request_id;
 	struct mutex lock; /* Lock on status */
@@ -76,14 +89,15 @@ void ivpu_ipc_enable(struct ivpu_device *vdev);
 void ivpu_ipc_disable(struct ivpu_device *vdev);
 void ivpu_ipc_reset(struct ivpu_device *vdev);
 
-int ivpu_ipc_irq_handler(struct ivpu_device *vdev);
+void ivpu_ipc_irq_handler(struct ivpu_device *vdev, bool *wake_thread);
+irqreturn_t ivpu_ipc_irq_thread_handler(struct ivpu_device *vdev);
 
 void ivpu_ipc_consumer_add(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
-			   u32 channel);
+			   u32 channel, ivpu_ipc_rx_callback_t callback);
 void ivpu_ipc_consumer_del(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons);
 
 int ivpu_ipc_receive(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
-		     struct ivpu_ipc_hdr *ipc_buf, struct vpu_jsm_msg *ipc_payload,
+		     struct ivpu_ipc_hdr *ipc_buf, struct vpu_jsm_msg *jsm_msg,
 		     unsigned long timeout_ms);
 
 int ivpu_ipc_send_receive_active(struct ivpu_device *vdev, struct vpu_jsm_msg *req,
diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c
index 796366d67984..7206cf9cdb4a 100644
--- a/drivers/accel/ivpu/ivpu_job.c
+++ b/drivers/accel/ivpu/ivpu_job.c
@@ -7,7 +7,6 @@
 
 #include <linux/bitfield.h>
 #include <linux/highmem.h>
-#include <linux/kthread.h>
 #include <linux/pci.h>
 #include <linux/module.h>
 #include <uapi/drm/ivpu_accel.h>
@@ -344,22 +343,6 @@ static int ivpu_job_done(struct ivpu_device *vdev, u32 job_id, u32 job_status)
 	return 0;
 }
 
-static void ivpu_job_done_message(struct ivpu_device *vdev, void *msg)
-{
-	struct vpu_ipc_msg_payload_job_done *payload;
-	struct vpu_jsm_msg *job_ret_msg = msg;
-	int ret;
-
-	payload = (struct vpu_ipc_msg_payload_job_done *)&job_ret_msg->payload;
-
-	ret = ivpu_job_done(vdev, payload->job_id, payload->job_status);
-	if (ret)
-		ivpu_err(vdev, "Failed to finish job %d: %d\n", payload->job_id, ret);
-
-	if (!ret && !xa_empty(&vdev->submitted_jobs_xa))
-		ivpu_start_job_timeout_detection(vdev);
-}
-
 void ivpu_jobs_abort_all(struct ivpu_device *vdev)
 {
 	struct ivpu_job *job;
@@ -567,65 +550,36 @@ free_handles:
 	return ret;
 }
 
-static int ivpu_job_done_thread(void *arg)
+static void
+ivpu_job_done_callback(struct ivpu_device *vdev, struct ivpu_ipc_hdr *ipc_hdr,
+		       struct vpu_jsm_msg *jsm_msg)
 {
-	struct ivpu_device *vdev = (struct ivpu_device *)arg;
-	struct ivpu_ipc_consumer cons;
-	struct vpu_jsm_msg jsm_msg;
-	unsigned int timeout;
+	struct vpu_ipc_msg_payload_job_done *payload;
 	int ret;
 
-	ivpu_dbg(vdev, JOB, "Started %s\n", __func__);
-
-	ivpu_ipc_consumer_add(vdev, &cons, VPU_IPC_CHAN_JOB_RET);
-
-	while (!kthread_should_stop()) {
-		ret = ivpu_ipc_receive(vdev, &cons, NULL, &jsm_msg, timeout);
-		if (!ret)
-			ivpu_job_done_message(vdev, &jsm_msg);
-
-		if (kthread_should_park()) {
-			ivpu_dbg(vdev, JOB, "Parked %s\n", __func__);
-			kthread_parkme();
-			ivpu_dbg(vdev, JOB, "Unparked %s\n", __func__);
-		}
+	if (!jsm_msg) {
+		ivpu_err(vdev, "IPC message has no JSM payload\n");
+		return;
 	}
 
-	ivpu_ipc_consumer_del(vdev, &cons);
-
-	ivpu_jobs_abort_all(vdev);
-
-	ivpu_dbg(vdev, JOB, "Stopped %s\n", __func__);
-	return 0;
-}
-
-int ivpu_job_done_thread_init(struct ivpu_device *vdev)
-{
-	struct task_struct *thread;
-
-	thread = kthread_run(&ivpu_job_done_thread, (void *)vdev, "ivpu_job_done_thread");
-	if (IS_ERR(thread)) {
-		ivpu_err(vdev, "Failed to start job completion thread\n");
-		return -EIO;
+	if (jsm_msg->result != VPU_JSM_STATUS_SUCCESS) {
+		ivpu_err(vdev, "Invalid JSM message result: %d\n", jsm_msg->result);
+		return;
 	}
 
-	vdev->job_done_thread = thread;
-
-	return 0;
-}
-
-void ivpu_job_done_thread_fini(struct ivpu_device *vdev)
-{
-	kthread_unpark(vdev->job_done_thread);
-	kthread_stop(vdev->job_done_thread);
+	payload = (struct vpu_ipc_msg_payload_job_done *)&jsm_msg->payload;
+	ret = ivpu_job_done(vdev, payload->job_id, payload->job_status);
+	if (!ret && !xa_empty(&vdev->submitted_jobs_xa))
+		ivpu_start_job_timeout_detection(vdev);
 }
 
-void ivpu_job_done_thread_disable(struct ivpu_device *vdev)
+void ivpu_job_done_consumer_init(struct ivpu_device *vdev)
 {
-	kthread_park(vdev->job_done_thread);
+	ivpu_ipc_consumer_add(vdev, &vdev->job_done_consumer,
+			      VPU_IPC_CHAN_JOB_RET, ivpu_job_done_callback);
 }
 
-void ivpu_job_done_thread_enable(struct ivpu_device *vdev)
+void ivpu_job_done_consumer_fini(struct ivpu_device *vdev)
 {
-	kthread_unpark(vdev->job_done_thread);
+	ivpu_ipc_consumer_del(vdev, &vdev->job_done_consumer);
 }
diff --git a/drivers/accel/ivpu/ivpu_job.h b/drivers/accel/ivpu/ivpu_job.h
index 4b604c90041e..45a2f2ec82e5 100644
--- a/drivers/accel/ivpu/ivpu_job.h
+++ b/drivers/accel/ivpu/ivpu_job.h
@@ -59,10 +59,8 @@ int ivpu_submit_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 void ivpu_cmdq_release_all(struct ivpu_file_priv *file_priv);
 void ivpu_cmdq_reset_all_contexts(struct ivpu_device *vdev);
 
-int ivpu_job_done_thread_init(struct ivpu_device *vdev);
-void ivpu_job_done_thread_fini(struct ivpu_device *vdev);
-void ivpu_job_done_thread_disable(struct ivpu_device *vdev);
-void ivpu_job_done_thread_enable(struct ivpu_device *vdev);
+void ivpu_job_done_consumer_init(struct ivpu_device *vdev);
+void ivpu_job_done_consumer_fini(struct ivpu_device *vdev);
 
 void ivpu_jobs_abort_all(struct ivpu_device *vdev);
 
-- 
cgit 


From 47fbee5f27ed9ef43340db03ba2b58a673a6e72b Mon Sep 17 00:00:00 2001
From: Jeffrey Hugo <quic_jhugo@quicinc.com>
Date: Fri, 3 Nov 2023 09:33:02 -0600
Subject: accel/qaic: Update MAX_ORDER use to be inclusive

MAX_ORDER was redefined so that valid allocations to the page allocator
are in the range of 0..MAX_ORDER, inclusive in the commit
23baf831a32c ("mm, treewide: redefine MAX_ORDER sanely").

We are treating MAX_ORDER as an exclusive value, and thus could be
requesting larger allocations.  Update our use to match the redefinition
of MAX_ORDER.

Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Reviewed-by: Pranjal Ramajor Asha Kanojiya <quic_pkanojiy@quicinc.com>
Reviewed-by: Carl Vanderlip <quic_carlv@quicinc.com>
Reviewed-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231103153302.20642-1-quic_jhugo@quicinc.com
---
 drivers/accel/qaic/qaic_data.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/qaic/qaic_data.c b/drivers/accel/qaic/qaic_data.c
index 8da81768f2ab..8998c28e566e 100644
--- a/drivers/accel/qaic/qaic_data.c
+++ b/drivers/accel/qaic/qaic_data.c
@@ -452,7 +452,7 @@ static int create_sgt(struct qaic_device *qdev, struct sg_table **sgt_out, u64 s
 		 * later
 		 */
 		buf_extra = (PAGE_SIZE - size % PAGE_SIZE) % PAGE_SIZE;
-		max_order = min(MAX_ORDER - 1, get_order(size));
+		max_order = min(MAX_ORDER, get_order(size));
 	} else {
 		/* allocate a single page for book keeping */
 		nr_pages = 1;
-- 
cgit 


From 44df9a2a13211955ae98f8650e4dc04065e8ec0b Mon Sep 17 00:00:00 2001
From: Carl Vanderlip <quic_carlv@quicinc.com>
Date: Fri, 17 Nov 2023 10:43:36 -0700
Subject: accel/qaic: Increase number of in_reset states

'in_reset' holds the state of the device. As part of bringup, the device
needs to be queried to check if it's in a valid state. Add a new state
that indicates that the device is coming up, but not ready for users
yet. Rename to 'dev_state' to better describe the variable.

Signed-off-by: Carl Vanderlip <quic_carlv@quicinc.com>
Reviewed-by: Pranjal Ramajor Asha Kanojiya <quic_pkanojiy@quicinc.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Reviewed-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231117174337.20174-2-quic_jhugo@quicinc.com
---
 drivers/accel/qaic/qaic.h         | 13 +++++++++++--
 drivers/accel/qaic/qaic_control.c |  5 +++--
 drivers/accel/qaic/qaic_data.c    | 16 ++++++++--------
 drivers/accel/qaic/qaic_drv.c     | 12 ++++++------
 4 files changed, 28 insertions(+), 18 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/qaic/qaic.h b/drivers/accel/qaic/qaic.h
index bc40d52dc010..cb04f7f9cdb3 100644
--- a/drivers/accel/qaic/qaic.h
+++ b/drivers/accel/qaic/qaic.h
@@ -31,6 +31,15 @@
 #define to_drm(qddev) (&(qddev)->drm)
 #define to_accel_kdev(qddev) (to_drm(qddev)->accel->kdev) /* Return Linux device of accel node */
 
+enum __packed dev_states {
+	/* Device is offline or will be very soon */
+	QAIC_OFFLINE,
+	/* Device is booting, not clear if it's in a usable state */
+	QAIC_BOOT,
+	/* Device is fully operational */
+	QAIC_ONLINE,
+};
+
 extern bool datapath_polling;
 
 struct qaic_user {
@@ -121,8 +130,8 @@ struct qaic_device {
 	struct workqueue_struct	*cntl_wq;
 	/* Synchronizes all the users of device during cleanup */
 	struct srcu_struct	dev_lock;
-	/* true: Device under reset; false: Device not under reset */
-	bool			in_reset;
+	/* Track the state of the device during resets */
+	enum dev_states		dev_state;
 	/* true: single MSI is used to operate device */
 	bool			single_msi;
 	/*
diff --git a/drivers/accel/qaic/qaic_control.c b/drivers/accel/qaic/qaic_control.c
index 84915824be54..9e8a8cbadf6b 100644
--- a/drivers/accel/qaic/qaic_control.c
+++ b/drivers/accel/qaic/qaic_control.c
@@ -1022,7 +1022,8 @@ static void *msg_xfer(struct qaic_device *qdev, struct wrapper_list *wrappers, u
 	int xfer_count = 0;
 	int retry_count;
 
-	if (qdev->in_reset) {
+	/* Allow QAIC_BOOT state since we need to check control protocol version */
+	if (qdev->dev_state == QAIC_OFFLINE) {
 		mutex_unlock(&qdev->cntl_mutex);
 		return ERR_PTR(-ENODEV);
 	}
@@ -1306,7 +1307,7 @@ int qaic_manage_ioctl(struct drm_device *dev, void *data, struct drm_file *file_
 	qdev = usr->qddev->qdev;
 
 	qdev_rcu_id = srcu_read_lock(&qdev->dev_lock);
-	if (qdev->in_reset) {
+	if (qdev->dev_state != QAIC_ONLINE) {
 		srcu_read_unlock(&qdev->dev_lock, qdev_rcu_id);
 		srcu_read_unlock(&usr->qddev_lock, usr_rcu_id);
 		return -ENODEV;
diff --git a/drivers/accel/qaic/qaic_data.c b/drivers/accel/qaic/qaic_data.c
index 8998c28e566e..cf2898eda7ae 100644
--- a/drivers/accel/qaic/qaic_data.c
+++ b/drivers/accel/qaic/qaic_data.c
@@ -690,7 +690,7 @@ int qaic_create_bo_ioctl(struct drm_device *dev, void *data, struct drm_file *fi
 
 	qdev = usr->qddev->qdev;
 	qdev_rcu_id = srcu_read_lock(&qdev->dev_lock);
-	if (qdev->in_reset) {
+	if (qdev->dev_state != QAIC_ONLINE) {
 		ret = -ENODEV;
 		goto unlock_dev_srcu;
 	}
@@ -749,7 +749,7 @@ int qaic_mmap_bo_ioctl(struct drm_device *dev, void *data, struct drm_file *file
 
 	qdev = usr->qddev->qdev;
 	qdev_rcu_id = srcu_read_lock(&qdev->dev_lock);
-	if (qdev->in_reset) {
+	if (qdev->dev_state != QAIC_ONLINE) {
 		ret = -ENODEV;
 		goto unlock_dev_srcu;
 	}
@@ -970,7 +970,7 @@ int qaic_attach_slice_bo_ioctl(struct drm_device *dev, void *data, struct drm_fi
 
 	qdev = usr->qddev->qdev;
 	qdev_rcu_id = srcu_read_lock(&qdev->dev_lock);
-	if (qdev->in_reset) {
+	if (qdev->dev_state != QAIC_ONLINE) {
 		ret = -ENODEV;
 		goto unlock_dev_srcu;
 	}
@@ -1341,7 +1341,7 @@ static int __qaic_execute_bo_ioctl(struct drm_device *dev, void *data, struct dr
 
 	qdev = usr->qddev->qdev;
 	qdev_rcu_id = srcu_read_lock(&qdev->dev_lock);
-	if (qdev->in_reset) {
+	if (qdev->dev_state != QAIC_ONLINE) {
 		ret = -ENODEV;
 		goto unlock_dev_srcu;
 	}
@@ -1497,7 +1497,7 @@ void irq_polling_work(struct work_struct *work)
 	rcu_id = srcu_read_lock(&dbc->ch_lock);
 
 	while (1) {
-		if (dbc->qdev->in_reset) {
+		if (dbc->qdev->dev_state != QAIC_ONLINE) {
 			srcu_read_unlock(&dbc->ch_lock, rcu_id);
 			return;
 		}
@@ -1687,7 +1687,7 @@ int qaic_wait_bo_ioctl(struct drm_device *dev, void *data, struct drm_file *file
 
 	qdev = usr->qddev->qdev;
 	qdev_rcu_id = srcu_read_lock(&qdev->dev_lock);
-	if (qdev->in_reset) {
+	if (qdev->dev_state != QAIC_ONLINE) {
 		ret = -ENODEV;
 		goto unlock_dev_srcu;
 	}
@@ -1756,7 +1756,7 @@ int qaic_perf_stats_bo_ioctl(struct drm_device *dev, void *data, struct drm_file
 
 	qdev = usr->qddev->qdev;
 	qdev_rcu_id = srcu_read_lock(&qdev->dev_lock);
-	if (qdev->in_reset) {
+	if (qdev->dev_state != QAIC_ONLINE) {
 		ret = -ENODEV;
 		goto unlock_dev_srcu;
 	}
@@ -1847,7 +1847,7 @@ int qaic_detach_slice_bo_ioctl(struct drm_device *dev, void *data, struct drm_fi
 
 	qdev = usr->qddev->qdev;
 	qdev_rcu_id = srcu_read_lock(&qdev->dev_lock);
-	if (qdev->in_reset) {
+	if (qdev->dev_state != QAIC_ONLINE) {
 		ret = -ENODEV;
 		goto unlock_dev_srcu;
 	}
diff --git a/drivers/accel/qaic/qaic_drv.c b/drivers/accel/qaic/qaic_drv.c
index b12226385003..24b8680b2dbd 100644
--- a/drivers/accel/qaic/qaic_drv.c
+++ b/drivers/accel/qaic/qaic_drv.c
@@ -64,7 +64,7 @@ static int qaic_open(struct drm_device *dev, struct drm_file *file)
 	int ret;
 
 	rcu_id = srcu_read_lock(&qdev->dev_lock);
-	if (qdev->in_reset) {
+	if (qdev->dev_state != QAIC_ONLINE) {
 		ret = -ENODEV;
 		goto dev_unlock;
 	}
@@ -121,7 +121,7 @@ static void qaic_postclose(struct drm_device *dev, struct drm_file *file)
 	if (qddev) {
 		qdev = qddev->qdev;
 		qdev_rcu_id = srcu_read_lock(&qdev->dev_lock);
-		if (!qdev->in_reset) {
+		if (qdev->dev_state == QAIC_ONLINE) {
 			qaic_release_usr(qdev, usr);
 			for (i = 0; i < qdev->num_dbc; ++i)
 				if (qdev->dbc[i].usr && qdev->dbc[i].usr->handle == usr->handle)
@@ -254,7 +254,7 @@ static int qaic_mhi_probe(struct mhi_device *mhi_dev, const struct mhi_device_id
 
 	qdev = pci_get_drvdata(to_pci_dev(mhi_dev->mhi_cntrl->cntrl_dev));
 
-	qdev->in_reset = false;
+	qdev->dev_state = QAIC_ONLINE;
 
 	dev_set_drvdata(&mhi_dev->dev, qdev);
 	qdev->cntl_ch = mhi_dev;
@@ -291,7 +291,7 @@ static void qaic_notify_reset(struct qaic_device *qdev)
 {
 	int i;
 
-	qdev->in_reset = true;
+	qdev->dev_state = QAIC_OFFLINE;
 	/* wake up any waiters to avoid waiting for timeouts at sync */
 	wake_all_cntl(qdev);
 	for (i = 0; i < qdev->num_dbc; ++i)
@@ -313,7 +313,7 @@ void qaic_dev_reset_clean_local_state(struct qaic_device *qdev, bool exit_reset)
 		release_dbc(qdev, i);
 
 	if (exit_reset)
-		qdev->in_reset = false;
+		qdev->dev_state = QAIC_ONLINE;
 }
 
 static void cleanup_qdev(struct qaic_device *qdev)
@@ -550,7 +550,7 @@ static void qaic_pci_reset_done(struct pci_dev *pdev)
 {
 	struct qaic_device *qdev = pci_get_drvdata(pdev);
 
-	qdev->in_reset = false;
+	qdev->dev_state = QAIC_ONLINE;
 	qaic_mhi_reset_done(qdev->mhi_cntrl);
 }
 
-- 
cgit 


From 5f0a0ebca2b98eeda10715433c7d9418ef2e6d01 Mon Sep 17 00:00:00 2001
From: Carl Vanderlip <quic_carlv@quicinc.com>
Date: Fri, 17 Nov 2023 10:43:37 -0700
Subject: accel/qaic: Expand DRM device lifecycle

Currently the QAIC DRM device registers itself when the MHI QAIC_CONTROL
channel becomes available. This is when the device is able to process
workloads. However, the DRM driver also provides the debugfs interface
bootlog for the device. If the device fails to boot to the QSM (which
brings up the MHI QAIC_CONTROL channel), the bootlog won't be available for
debugging why it failed to boot.

Change when the DRM device registers itself from when QAIC_CONTROL is
available to when the card is first probed on the PCI bus. Additionally,
make the DRM driver persist through reset/error cases so the driver
doesn't have to be reloaded to access the card again. Send
KOBJ_ONLINE/OFFLINE uevents so userspace can know when DRM device is
ready to handle requests.

Signed-off-by: Carl Vanderlip <quic_carlv@quicinc.com>
Reviewed-by: Pranjal Ramajor Asha Kanojiya <quic_pkanojiy@quicinc.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Reviewed-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231117174337.20174-3-quic_jhugo@quicinc.com
---
 drivers/accel/qaic/mhi_controller.c |  2 +-
 drivers/accel/qaic/qaic.h           |  2 +-
 drivers/accel/qaic/qaic_drv.c       | 44 ++++++++++++++-----------------------
 3 files changed, 19 insertions(+), 29 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/qaic/mhi_controller.c b/drivers/accel/qaic/mhi_controller.c
index 5d3cc30009cc..832464f2833a 100644
--- a/drivers/accel/qaic/mhi_controller.c
+++ b/drivers/accel/qaic/mhi_controller.c
@@ -469,7 +469,7 @@ static void mhi_status_cb(struct mhi_controller *mhi_cntrl, enum mhi_callback re
 		pci_err(qdev->pdev, "Fatal error received from device. Attempting to recover\n");
 	/* this event occurs in non-atomic context */
 	if (reason == MHI_CB_SYS_ERROR)
-		qaic_dev_reset_clean_local_state(qdev, true);
+		qaic_dev_reset_clean_local_state(qdev);
 }
 
 static int mhi_reset_and_async_power_up(struct mhi_controller *mhi_cntrl)
diff --git a/drivers/accel/qaic/qaic.h b/drivers/accel/qaic/qaic.h
index cb04f7f9cdb3..582836f9538f 100644
--- a/drivers/accel/qaic/qaic.h
+++ b/drivers/accel/qaic/qaic.h
@@ -283,7 +283,7 @@ void wakeup_dbc(struct qaic_device *qdev, u32 dbc_id);
 void release_dbc(struct qaic_device *qdev, u32 dbc_id);
 
 void wake_all_cntl(struct qaic_device *qdev);
-void qaic_dev_reset_clean_local_state(struct qaic_device *qdev, bool exit_reset);
+void qaic_dev_reset_clean_local_state(struct qaic_device *qdev);
 
 struct drm_gem_object *qaic_gem_prime_import(struct drm_device *dev, struct dma_buf *dma_buf);
 
diff --git a/drivers/accel/qaic/qaic_drv.c b/drivers/accel/qaic/qaic_drv.c
index 24b8680b2dbd..2a313eb69b12 100644
--- a/drivers/accel/qaic/qaic_drv.c
+++ b/drivers/accel/qaic/qaic_drv.c
@@ -8,6 +8,7 @@
 #include <linux/idr.h>
 #include <linux/interrupt.h>
 #include <linux/list.h>
+#include <linux/kobject.h>
 #include <linux/kref.h>
 #include <linux/mhi.h>
 #include <linux/module.h>
@@ -43,9 +44,6 @@ MODULE_PARM_DESC(datapath_polling, "Operate the datapath in polling mode");
 static bool link_up;
 static DEFINE_IDA(qaic_usrs);
 
-static int qaic_create_drm_device(struct qaic_device *qdev, s32 partition_id);
-static void qaic_destroy_drm_device(struct qaic_device *qdev, s32 partition_id);
-
 static void free_usr(struct kref *kref)
 {
 	struct qaic_user *usr = container_of(kref, struct qaic_user, ref_count);
@@ -183,13 +181,6 @@ static int qaic_create_drm_device(struct qaic_device *qdev, s32 partition_id)
 
 	qddev->partition_id = partition_id;
 
-	/*
-	 * drm_dev_unregister() sets the driver data to NULL and
-	 * drm_dev_register() does not update the driver data. During a SOC
-	 * reset drm dev is unregistered and registered again leaving the
-	 * driver data to NULL.
-	 */
-	dev_set_drvdata(to_accel_kdev(qddev), drm->accel);
 	ret = drm_dev_register(drm, 0);
 	if (ret)
 		pci_dbg(qdev->pdev, "drm_dev_register failed %d\n", ret);
@@ -203,7 +194,6 @@ static void qaic_destroy_drm_device(struct qaic_device *qdev, s32 partition_id)
 	struct drm_device *drm = to_drm(qddev);
 	struct qaic_user *usr;
 
-	drm_dev_get(drm);
 	drm_dev_unregister(drm);
 	qddev->partition_id = 0;
 	/*
@@ -232,7 +222,6 @@ static void qaic_destroy_drm_device(struct qaic_device *qdev, s32 partition_id)
 		mutex_lock(&qddev->users_mutex);
 	}
 	mutex_unlock(&qddev->users_mutex);
-	drm_dev_put(drm);
 }
 
 static int qaic_mhi_probe(struct mhi_device *mhi_dev, const struct mhi_device_id *id)
@@ -254,8 +243,6 @@ static int qaic_mhi_probe(struct mhi_device *mhi_dev, const struct mhi_device_id
 
 	qdev = pci_get_drvdata(to_pci_dev(mhi_dev->mhi_cntrl->cntrl_dev));
 
-	qdev->dev_state = QAIC_ONLINE;
-
 	dev_set_drvdata(&mhi_dev->dev, qdev);
 	qdev->cntl_ch = mhi_dev;
 
@@ -265,6 +252,7 @@ static int qaic_mhi_probe(struct mhi_device *mhi_dev, const struct mhi_device_id
 		return ret;
 	}
 
+	qdev->dev_state = QAIC_BOOT;
 	ret = get_cntl_version(qdev, NULL, &major, &minor);
 	if (ret || major != CNTL_MAJOR || minor > CNTL_MINOR) {
 		pci_err(qdev->pdev, "%s: Control protocol version (%d.%d) not supported. Supported version is (%d.%d). Ret: %d\n",
@@ -272,8 +260,8 @@ static int qaic_mhi_probe(struct mhi_device *mhi_dev, const struct mhi_device_id
 		ret = -EINVAL;
 		goto close_control;
 	}
-
-	ret = qaic_create_drm_device(qdev, QAIC_NO_PARTITION);
+	qdev->dev_state = QAIC_ONLINE;
+	kobject_uevent(&(to_accel_kdev(qdev->qddev))->kobj, KOBJ_ONLINE);
 
 	return ret;
 
@@ -291,6 +279,7 @@ static void qaic_notify_reset(struct qaic_device *qdev)
 {
 	int i;
 
+	kobject_uevent(&(to_accel_kdev(qdev->qddev))->kobj, KOBJ_OFFLINE);
 	qdev->dev_state = QAIC_OFFLINE;
 	/* wake up any waiters to avoid waiting for timeouts at sync */
 	wake_all_cntl(qdev);
@@ -299,21 +288,15 @@ static void qaic_notify_reset(struct qaic_device *qdev)
 	synchronize_srcu(&qdev->dev_lock);
 }
 
-void qaic_dev_reset_clean_local_state(struct qaic_device *qdev, bool exit_reset)
+void qaic_dev_reset_clean_local_state(struct qaic_device *qdev)
 {
 	int i;
 
 	qaic_notify_reset(qdev);
 
-	/* remove drmdevs to prevent new users from coming in */
-	qaic_destroy_drm_device(qdev, QAIC_NO_PARTITION);
-
 	/* start tearing things down */
 	for (i = 0; i < qdev->num_dbc; ++i)
 		release_dbc(qdev, i);
-
-	if (exit_reset)
-		qdev->dev_state = QAIC_ONLINE;
 }
 
 static void cleanup_qdev(struct qaic_device *qdev)
@@ -338,6 +321,7 @@ static struct qaic_device *create_qdev(struct pci_dev *pdev, const struct pci_de
 	if (!qdev)
 		return NULL;
 
+	qdev->dev_state = QAIC_OFFLINE;
 	if (id->device == PCI_DEV_AIC100) {
 		qdev->num_dbc = 16;
 		qdev->dbc = devm_kcalloc(&pdev->dev, qdev->num_dbc, sizeof(*qdev->dbc), GFP_KERNEL);
@@ -499,15 +483,21 @@ static int qaic_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto cleanup_qdev;
 	}
 
+	ret = qaic_create_drm_device(qdev, QAIC_NO_PARTITION);
+	if (ret)
+		goto cleanup_qdev;
+
 	qdev->mhi_cntrl = qaic_mhi_register_controller(pdev, qdev->bar_0, mhi_irq,
 						       qdev->single_msi);
 	if (IS_ERR(qdev->mhi_cntrl)) {
 		ret = PTR_ERR(qdev->mhi_cntrl);
-		goto cleanup_qdev;
+		goto cleanup_drm_dev;
 	}
 
 	return 0;
 
+cleanup_drm_dev:
+	qaic_destroy_drm_device(qdev, QAIC_NO_PARTITION);
 cleanup_qdev:
 	cleanup_qdev(qdev);
 	return ret;
@@ -520,7 +510,8 @@ static void qaic_pci_remove(struct pci_dev *pdev)
 	if (!qdev)
 		return;
 
-	qaic_dev_reset_clean_local_state(qdev, false);
+	qaic_dev_reset_clean_local_state(qdev);
+	qaic_destroy_drm_device(qdev, QAIC_NO_PARTITION);
 	qaic_mhi_free_controller(qdev->mhi_cntrl, link_up);
 	cleanup_qdev(qdev);
 }
@@ -543,14 +534,13 @@ static void qaic_pci_reset_prepare(struct pci_dev *pdev)
 
 	qaic_notify_reset(qdev);
 	qaic_mhi_start_reset(qdev->mhi_cntrl);
-	qaic_dev_reset_clean_local_state(qdev, false);
+	qaic_dev_reset_clean_local_state(qdev);
 }
 
 static void qaic_pci_reset_done(struct pci_dev *pdev)
 {
 	struct qaic_device *qdev = pci_get_drvdata(pdev);
 
-	qdev->dev_state = QAIC_ONLINE;
 	qaic_mhi_reset_done(qdev->mhi_cntrl);
 }
 
-- 
cgit 


From 64c39a93ef6c45447bc093e34e02afeb4c063579 Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Wed, 22 Nov 2023 13:09:34 +0100
Subject: accel: Include <drm/drm_auth.h>

One of the source files includes <drm/drm_auth.h> via <drm/drm_legacy.h>,
which will be removed. Include drm_auth.h directly.

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Cc: Oded Gabbay <ogabbay@kernel.org>
Reviewed-by: David Airlie <airlied@gmail.com>
Reviewed-by: Daniel Vetter <daniel@ffwll.ch>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231122122449.11588-6-tzimmermann@suse.de
---
 drivers/accel/drm_accel.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'drivers/accel')

diff --git a/drivers/accel/drm_accel.c b/drivers/accel/drm_accel.c
index 294b572a9c33..24cac4c0274b 100644
--- a/drivers/accel/drm_accel.c
+++ b/drivers/accel/drm_accel.c
@@ -11,6 +11,7 @@
 #include <linux/idr.h>
 
 #include <drm/drm_accel.h>
+#include <drm/drm_auth.h>
 #include <drm/drm_debugfs.h>
 #include <drm/drm_drv.h>
 #include <drm/drm_file.h>
-- 
cgit 


From f64fa332602c311a76495fd0139bd4abb9aa7bbf Mon Sep 17 00:00:00 2001
From: farah kassabri <fkassabri@habana.ai>
Date: Mon, 9 Oct 2023 15:07:38 +0300
Subject: accel/habanalabs: add pcie reset prepare/done hooks

When working on a bare-metal system, if FLR will happen the firmware
will handle it and driver will have no knowledge of it, and this will
cause two issues:

1.The driver will be in operational state while it should be in reset.
  This will cause the heartbeat mechanism to keep sending messages to FW
  while pci device is in reset. Eventually heartbeat will fail and
  the device will end up in non-operational state.

2. After FW handles the FLR, and due to the reset it'll go back to
   preboot stage, and driver need to perform hard reset in order to
   load the boot fit binary.

This patch will add reset_prepare hook that will set the device to
be in disabled state, so it'll be not operational, and also
reset_done hook which will be called after the actual FLR handling,
then it will perform hard reset.

Signed-off-by: farah kassabri <fkassabri@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
 drivers/accel/habanalabs/common/habanalabs_drv.c | 34 ++++++++++++++++++++++++
 1 file changed, 34 insertions(+)

(limited to 'drivers/accel')

diff --git a/drivers/accel/habanalabs/common/habanalabs_drv.c b/drivers/accel/habanalabs/common/habanalabs_drv.c
index 306a5bc9bf89..35ae0ff347f5 100644
--- a/drivers/accel/habanalabs/common/habanalabs_drv.c
+++ b/drivers/accel/habanalabs/common/habanalabs_drv.c
@@ -670,6 +670,38 @@ static pci_ers_result_t hl_pci_err_slot_reset(struct pci_dev *pdev)
 	return PCI_ERS_RESULT_RECOVERED;
 }
 
+static void hl_pci_reset_prepare(struct pci_dev *pdev)
+{
+	struct hl_device *hdev;
+
+	hdev = pci_get_drvdata(pdev);
+	if (!hdev)
+		return;
+
+	hdev->disabled = true;
+}
+
+static void hl_pci_reset_done(struct pci_dev *pdev)
+{
+	struct hl_device *hdev;
+	u32 flags;
+
+	hdev = pci_get_drvdata(pdev);
+	if (!hdev)
+		return;
+
+	/*
+	 * Schedule a thread to trigger hard reset.
+	 * The reason for this handler, is for rare cases where the driver is up
+	 * and FLR occurs. This is valid only when working with no VM, so FW handles FLR
+	 * and resets the device. FW will go back preboot stage, so driver needs to perform
+	 * hard reset in order to load FW fit again.
+	 */
+	flags = HL_DRV_RESET_HARD | HL_DRV_RESET_BYPASS_REQ_TO_FW;
+
+	hl_device_reset(hdev, flags);
+}
+
 static const struct dev_pm_ops hl_pm_ops = {
 	.suspend = hl_pmops_suspend,
 	.resume = hl_pmops_resume,
@@ -679,6 +711,8 @@ static const struct pci_error_handlers hl_pci_err_handler = {
 	.error_detected = hl_pci_err_detected,
 	.slot_reset = hl_pci_err_slot_reset,
 	.resume = hl_pci_err_resume,
+	.reset_prepare = hl_pci_reset_prepare,
+	.reset_done = hl_pci_reset_done,
 };
 
 static struct pci_driver hl_pci_driver = {
-- 
cgit 


From fbc2a09e09201eb64b94c0c7e4d2b4ec5337f844 Mon Sep 17 00:00:00 2001
From: Farah Kassabri <fkassabri@habana.ai>
Date: Wed, 18 Oct 2023 16:22:13 +0300
Subject: accel/habanalabs: update device boot error check

Use a predefined mask which set the device critical boot errors.
Driver will fail and stop its loading, only upon detecting at least
one of those errors defined in this mask.

Signed-off-by: Farah Kassabri <fkassabri@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
 drivers/accel/habanalabs/common/firmware_if.c | 115 +++++++-------------------
 1 file changed, 32 insertions(+), 83 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/habanalabs/common/firmware_if.c b/drivers/accel/habanalabs/common/firmware_if.c
index 47e8384134aa..9e9dfe013659 100644
--- a/drivers/accel/habanalabs/common/firmware_if.c
+++ b/drivers/accel/habanalabs/common/firmware_if.c
@@ -646,39 +646,27 @@ int hl_fw_send_heartbeat(struct hl_device *hdev)
 	return rc;
 }
 
-static bool fw_report_boot_dev0(struct hl_device *hdev, u32 err_val,
-								u32 sts_val)
+static bool fw_report_boot_dev0(struct hl_device *hdev, u32 err_val, u32 sts_val)
 {
 	bool err_exists = false;
 
 	if (!(err_val & CPU_BOOT_ERR0_ENABLED))
 		return false;
 
-	if (err_val & CPU_BOOT_ERR0_DRAM_INIT_FAIL) {
-		dev_err(hdev->dev,
-			"Device boot error - DRAM initialization failed\n");
-		err_exists = true;
-	}
+	if (err_val & CPU_BOOT_ERR0_DRAM_INIT_FAIL)
+		dev_err(hdev->dev, "Device boot error - DRAM initialization failed\n");
 
-	if (err_val & CPU_BOOT_ERR0_FIT_CORRUPTED) {
+	if (err_val & CPU_BOOT_ERR0_FIT_CORRUPTED)
 		dev_err(hdev->dev, "Device boot error - FIT image corrupted\n");
-		err_exists = true;
-	}
 
-	if (err_val & CPU_BOOT_ERR0_TS_INIT_FAIL) {
-		dev_err(hdev->dev,
-			"Device boot error - Thermal Sensor initialization failed\n");
-		err_exists = true;
-	}
+	if (err_val & CPU_BOOT_ERR0_TS_INIT_FAIL)
+		dev_err(hdev->dev, "Device boot error - Thermal Sensor initialization failed\n");
 
 	if (err_val & CPU_BOOT_ERR0_BMC_WAIT_SKIPPED) {
 		if (hdev->bmc_enable) {
-			dev_err(hdev->dev,
-				"Device boot error - Skipped waiting for BMC\n");
-			err_exists = true;
+			dev_err(hdev->dev, "Device boot error - Skipped waiting for BMC\n");
 		} else {
-			dev_info(hdev->dev,
-				"Device boot message - Skipped waiting for BMC\n");
+			dev_info(hdev->dev, "Device boot message - Skipped waiting for BMC\n");
 			/* This is an info so we don't want it to disable the
 			 * device
 			 */
@@ -686,48 +674,29 @@ static bool fw_report_boot_dev0(struct hl_device *hdev, u32 err_val,
 		}
 	}
 
-	if (err_val & CPU_BOOT_ERR0_NIC_DATA_NOT_RDY) {
-		dev_err(hdev->dev,
-			"Device boot error - Serdes data from BMC not available\n");
-		err_exists = true;
-	}
+	if (err_val & CPU_BOOT_ERR0_NIC_DATA_NOT_RDY)
+		dev_err(hdev->dev, "Device boot error - Serdes data from BMC not available\n");
 
-	if (err_val & CPU_BOOT_ERR0_NIC_FW_FAIL) {
-		dev_err(hdev->dev,
-			"Device boot error - NIC F/W initialization failed\n");
-		err_exists = true;
-	}
+	if (err_val & CPU_BOOT_ERR0_NIC_FW_FAIL)
+		dev_err(hdev->dev, "Device boot error - NIC F/W initialization failed\n");
 
-	if (err_val & CPU_BOOT_ERR0_SECURITY_NOT_RDY) {
-		dev_err(hdev->dev,
-			"Device boot warning - security not ready\n");
-		err_exists = true;
-	}
+	if (err_val & CPU_BOOT_ERR0_SECURITY_NOT_RDY)
+		dev_err(hdev->dev, "Device boot warning - security not ready\n");
 
-	if (err_val & CPU_BOOT_ERR0_SECURITY_FAIL) {
+	if (err_val & CPU_BOOT_ERR0_SECURITY_FAIL)
 		dev_err(hdev->dev, "Device boot error - security failure\n");
-		err_exists = true;
-	}
 
-	if (err_val & CPU_BOOT_ERR0_EFUSE_FAIL) {
+	if (err_val & CPU_BOOT_ERR0_EFUSE_FAIL)
 		dev_err(hdev->dev, "Device boot error - eFuse failure\n");
-		err_exists = true;
-	}
 
-	if (err_val & CPU_BOOT_ERR0_SEC_IMG_VER_FAIL) {
+	if (err_val & CPU_BOOT_ERR0_SEC_IMG_VER_FAIL)
 		dev_err(hdev->dev, "Device boot error - Failed to load preboot secondary image\n");
-		err_exists = true;
-	}
 
-	if (err_val & CPU_BOOT_ERR0_PLL_FAIL) {
+	if (err_val & CPU_BOOT_ERR0_PLL_FAIL)
 		dev_err(hdev->dev, "Device boot error - PLL failure\n");
-		err_exists = true;
-	}
 
-	if (err_val & CPU_BOOT_ERR0_TMP_THRESH_INIT_FAIL) {
+	if (err_val & CPU_BOOT_ERR0_TMP_THRESH_INIT_FAIL)
 		dev_err(hdev->dev, "Device boot error - Failed to set threshold for temperature sensor\n");
-		err_exists = true;
-	}
 
 	if (err_val & CPU_BOOT_ERR0_DEVICE_UNUSABLE_FAIL) {
 		/* Ignore this bit, don't prevent driver loading */
@@ -735,52 +704,32 @@ static bool fw_report_boot_dev0(struct hl_device *hdev, u32 err_val,
 		err_val &= ~CPU_BOOT_ERR0_DEVICE_UNUSABLE_FAIL;
 	}
 
-	if (err_val & CPU_BOOT_ERR0_BINNING_FAIL) {
+	if (err_val & CPU_BOOT_ERR0_BINNING_FAIL)
 		dev_err(hdev->dev, "Device boot error - binning failure\n");
-		err_exists = true;
-	}
 
 	if (sts_val & CPU_BOOT_DEV_STS0_ENABLED)
 		dev_dbg(hdev->dev, "Device status0 %#x\n", sts_val);
 
+	if (err_val & CPU_BOOT_ERR0_DRAM_SKIPPED)
+		dev_err(hdev->dev, "Device boot warning - Skipped DRAM initialization\n");
+
+	if (err_val & CPU_BOOT_ERR_ENG_ARC_MEM_SCRUB_FAIL)
+		dev_err(hdev->dev, "Device boot error - ARC memory scrub failed\n");
+
+	/* All warnings should go here in order not to reach the unknown error validation */
 	if (err_val & CPU_BOOT_ERR0_EEPROM_FAIL) {
 		dev_err(hdev->dev, "Device boot error - EEPROM failure detected\n");
 		err_exists = true;
 	}
 
-	/* All warnings should go here in order not to reach the unknown error validation */
-	if (err_val & CPU_BOOT_ERR0_DRAM_SKIPPED) {
-		dev_warn(hdev->dev,
-			"Device boot warning - Skipped DRAM initialization\n");
-		/* This is a warning so we don't want it to disable the
-		 * device
-		 */
-		err_val &= ~CPU_BOOT_ERR0_DRAM_SKIPPED;
-	}
+	if (err_val & CPU_BOOT_ERR0_PRI_IMG_VER_FAIL)
+		dev_warn(hdev->dev, "Device boot warning - Failed to load preboot primary image\n");
 
-	if (err_val & CPU_BOOT_ERR0_PRI_IMG_VER_FAIL) {
-		dev_warn(hdev->dev,
-			"Device boot warning - Failed to load preboot primary image\n");
-		/* This is a warning so we don't want it to disable the
-		 * device as we have a secondary preboot image
-		 */
-		err_val &= ~CPU_BOOT_ERR0_PRI_IMG_VER_FAIL;
-	}
+	if (err_val & CPU_BOOT_ERR0_TPM_FAIL)
+		dev_warn(hdev->dev, "Device boot warning - TPM failure\n");
 
-	if (err_val & CPU_BOOT_ERR0_TPM_FAIL) {
-		dev_warn(hdev->dev,
-			"Device boot warning - TPM failure\n");
-		/* This is a warning so we don't want it to disable the
-		 * device
-		 */
-		err_val &= ~CPU_BOOT_ERR0_TPM_FAIL;
-	}
-
-	if (!err_exists && (err_val & ~CPU_BOOT_ERR0_ENABLED)) {
-		dev_err(hdev->dev,
-			"Device boot error - unknown ERR0 error 0x%08x\n", err_val);
+	if (err_val & CPU_BOOT_ERR_FATAL_MASK)
 		err_exists = true;
-	}
 
 	/* return error only if it's in the predefined mask */
 	if (err_exists && ((err_val & ~CPU_BOOT_ERR0_ENABLED) &
-- 
cgit 


From c6485482330d9f9a745d4bfec4dca722bd2bd75f Mon Sep 17 00:00:00 2001
From: Tomer Tayar <ttayar@habana.ai>
Date: Sun, 15 Oct 2023 14:04:53 +0300
Subject: accel/habanalabs/gaudi2: assume hard-reset by FW upon PCIe AXI drain

When a PCIe AXI drain event happens, it is possible that the driver
cannot access the device through PCIe, and therefore cannot send a
hard-reset request to FW.
Starting from FW version 1.13, FW will initiate a hard-reset in such
a case without waiting for a reset request from the driver.

Signed-off-by: Tomer Tayar <ttayar@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
 drivers/accel/habanalabs/common/habanalabs.h | 8 ++++++++
 drivers/accel/habanalabs/gaudi2/gaudi2.c     | 2 ++
 2 files changed, 10 insertions(+)

(limited to 'drivers/accel')

diff --git a/drivers/accel/habanalabs/common/habanalabs.h b/drivers/accel/habanalabs/common/habanalabs.h
index 1655c101c705..5c69a482b8de 100644
--- a/drivers/accel/habanalabs/common/habanalabs.h
+++ b/drivers/accel/habanalabs/common/habanalabs.h
@@ -3594,6 +3594,14 @@ static inline bool hl_is_fw_sw_ver_below(struct hl_device *hdev, u32 fw_sw_major
 	return false;
 }
 
+static inline bool hl_is_fw_sw_ver_equal_or_greater(struct hl_device *hdev, u32 fw_sw_major,
+							u32 fw_sw_minor)
+{
+	return (hdev->fw_sw_major_ver > fw_sw_major ||
+			(hdev->fw_sw_major_ver == fw_sw_major &&
+					hdev->fw_sw_minor_ver >= fw_sw_minor));
+}
+
 /*
  * Kernel module functions that can be accessed by entire module
  */
diff --git a/drivers/accel/habanalabs/gaudi2/gaudi2.c b/drivers/accel/habanalabs/gaudi2/gaudi2.c
index 819660c684cf..b739078c2d87 100644
--- a/drivers/accel/habanalabs/gaudi2/gaudi2.c
+++ b/drivers/accel/habanalabs/gaudi2/gaudi2.c
@@ -10007,6 +10007,8 @@ static void gaudi2_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_ent
 		error_count = gaudi2_handle_pcie_drain(hdev, &eq_entry->pcie_drain_ind_data);
 		reset_flags |= HL_DRV_RESET_FW_FATAL_ERR;
 		event_mask |= HL_NOTIFIER_EVENT_GENERAL_HW_ERR;
+		if (hl_is_fw_sw_ver_equal_or_greater(hdev, 1, 13))
+			is_critical = true;
 		break;
 
 	case GAUDI2_EVENT_PSOC59_RPM_ERROR_OR_DRAIN:
-- 
cgit 


From e8bc0c1b1b730eb8759f5305ebd2d6876952e539 Mon Sep 17 00:00:00 2001
From: Farah Kassabri <fkassabri@habana.ai>
Date: Sun, 29 Oct 2023 16:16:16 +0200
Subject: accel/habanalabs: add log when eq event is not received

Add error log when no eq event is received from FW,
to cover a scenario when FW is stuck for some reason.
In such case driver will not receive neither the eq error interrupt
or the eq heartbeat event, and will just initiate a reset without
indication in the dmesg about the reason.

Signed-off-by: Farah Kassabri <fkassabri@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
 drivers/accel/habanalabs/common/device.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/habanalabs/common/device.c b/drivers/accel/habanalabs/common/device.c
index 9711e8fc979d..d95a981b2906 100644
--- a/drivers/accel/habanalabs/common/device.c
+++ b/drivers/accel/habanalabs/common/device.c
@@ -1049,10 +1049,12 @@ static void hl_device_eq_heartbeat(struct hl_device *hdev)
 	if (!prop->cpucp_info.eq_health_check_supported)
 		return;
 
-	if (hdev->eq_heartbeat_received)
+	if (hdev->eq_heartbeat_received) {
 		hdev->eq_heartbeat_received = false;
-	else
+	} else {
+		dev_err(hdev->dev, "EQ heartbeat event was not received!\n");
 		hl_device_cond_reset(hdev, HL_DRV_RESET_HARD, event_mask);
+	}
 }
 
 static void hl_device_heartbeat(struct work_struct *work)
-- 
cgit 


From 42422993cf28d456778ee9168d73758ec037cd51 Mon Sep 17 00:00:00 2001
From: Oded Gabbay <ogabbay@kernel.org>
Date: Mon, 30 Oct 2023 12:23:57 +0200
Subject: accel/habanalabs: add support for Gaudi2C device

Gaudi2 with PCI revision ID with the value of '3' represents Gaudi2C
device and should be detected and initialized as Gaudi2.

Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
 drivers/accel/habanalabs/common/device.c                 | 3 +++
 drivers/accel/habanalabs/common/habanalabs.h             | 2 ++
 drivers/accel/habanalabs/common/habanalabs_drv.c         | 3 +++
 drivers/accel/habanalabs/common/mmu/mmu.c                | 1 +
 drivers/accel/habanalabs/common/sysfs.c                  | 3 +++
 drivers/accel/habanalabs/include/hw_ip/pci/pci_general.h | 1 +
 6 files changed, 13 insertions(+)

(limited to 'drivers/accel')

diff --git a/drivers/accel/habanalabs/common/device.c b/drivers/accel/habanalabs/common/device.c
index d95a981b2906..d9447aeb3937 100644
--- a/drivers/accel/habanalabs/common/device.c
+++ b/drivers/accel/habanalabs/common/device.c
@@ -853,6 +853,9 @@ static int device_early_init(struct hl_device *hdev)
 		gaudi2_set_asic_funcs(hdev);
 		strscpy(hdev->asic_name, "GAUDI2B", sizeof(hdev->asic_name));
 		break;
+	case ASIC_GAUDI2C:
+		gaudi2_set_asic_funcs(hdev);
+		strscpy(hdev->asic_name, "GAUDI2C", sizeof(hdev->asic_name));
 		break;
 	default:
 		dev_err(hdev->dev, "Unrecognized ASIC type %d\n",
diff --git a/drivers/accel/habanalabs/common/habanalabs.h b/drivers/accel/habanalabs/common/habanalabs.h
index 5c69a482b8de..7b0209e5bad6 100644
--- a/drivers/accel/habanalabs/common/habanalabs.h
+++ b/drivers/accel/habanalabs/common/habanalabs.h
@@ -1262,6 +1262,7 @@ struct hl_dec {
  * @ASIC_GAUDI_SEC: Gaudi secured device (HL-2000).
  * @ASIC_GAUDI2: Gaudi2 device.
  * @ASIC_GAUDI2B: Gaudi2B device.
+ * @ASIC_GAUDI2C: Gaudi2C device.
  */
 enum hl_asic_type {
 	ASIC_INVALID,
@@ -1270,6 +1271,7 @@ enum hl_asic_type {
 	ASIC_GAUDI_SEC,
 	ASIC_GAUDI2,
 	ASIC_GAUDI2B,
+	ASIC_GAUDI2C,
 };
 
 struct hl_cs_parser;
diff --git a/drivers/accel/habanalabs/common/habanalabs_drv.c b/drivers/accel/habanalabs/common/habanalabs_drv.c
index 35ae0ff347f5..e542fd40e16c 100644
--- a/drivers/accel/habanalabs/common/habanalabs_drv.c
+++ b/drivers/accel/habanalabs/common/habanalabs_drv.c
@@ -141,6 +141,9 @@ static enum hl_asic_type get_asic_type(struct hl_device *hdev)
 		case REV_ID_B:
 			asic_type = ASIC_GAUDI2B;
 			break;
+		case REV_ID_C:
+			asic_type = ASIC_GAUDI2C;
+			break;
 		default:
 			break;
 		}
diff --git a/drivers/accel/habanalabs/common/mmu/mmu.c b/drivers/accel/habanalabs/common/mmu/mmu.c
index b2145716c605..b654302a68fc 100644
--- a/drivers/accel/habanalabs/common/mmu/mmu.c
+++ b/drivers/accel/habanalabs/common/mmu/mmu.c
@@ -596,6 +596,7 @@ int hl_mmu_if_set_funcs(struct hl_device *hdev)
 		break;
 	case ASIC_GAUDI2:
 	case ASIC_GAUDI2B:
+	case ASIC_GAUDI2C:
 		/* MMUs in Gaudi2 are always host resident */
 		hl_mmu_v2_hr_set_funcs(hdev, &hdev->mmu_func[MMU_HR_PGT]);
 		break;
diff --git a/drivers/accel/habanalabs/common/sysfs.c b/drivers/accel/habanalabs/common/sysfs.c
index 01f89f029355..278606373055 100644
--- a/drivers/accel/habanalabs/common/sysfs.c
+++ b/drivers/accel/habanalabs/common/sysfs.c
@@ -251,6 +251,9 @@ static ssize_t device_type_show(struct device *dev,
 	case ASIC_GAUDI2B:
 		str = "GAUDI2B";
 		break;
+	case ASIC_GAUDI2C:
+		str = "GAUDI2C";
+		break;
 	default:
 		dev_err(hdev->dev, "Unrecognized ASIC type %d\n",
 				hdev->asic_type);
diff --git a/drivers/accel/habanalabs/include/hw_ip/pci/pci_general.h b/drivers/accel/habanalabs/include/hw_ip/pci/pci_general.h
index f5d497dc9bdc..4f951cada077 100644
--- a/drivers/accel/habanalabs/include/hw_ip/pci/pci_general.h
+++ b/drivers/accel/habanalabs/include/hw_ip/pci/pci_general.h
@@ -25,6 +25,7 @@ enum hl_revision_id {
 	REV_ID_INVALID				= 0x00,
 	REV_ID_A				= 0x01,
 	REV_ID_B				= 0x02,
+	REV_ID_C				= 0x03
 };
 
 #endif /* INCLUDE_PCI_GENERAL_H_ */
-- 
cgit 


From d1958dce5ab6a3e089c60cf474e8c9b7e96e70ad Mon Sep 17 00:00:00 2001
From: Farah Kassabri <fkassabri@habana.ai>
Date: Tue, 31 Oct 2023 12:20:36 +0200
Subject: accel/habanalabs: fix EQ heartbeat mechanism

Stop rescheduling another heartbeat check when EQ heartbeat check fails
as it generates confusing logs in dmesg that the heartbeat fails.

Signed-off-by: Farah Kassabri <fkassabri@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
 drivers/accel/habanalabs/common/device.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/habanalabs/common/device.c b/drivers/accel/habanalabs/common/device.c
index d9447aeb3937..6bf5f1d0d005 100644
--- a/drivers/accel/habanalabs/common/device.c
+++ b/drivers/accel/habanalabs/common/device.c
@@ -1044,20 +1044,21 @@ static bool is_pci_link_healthy(struct hl_device *hdev)
 	return (vendor_id == PCI_VENDOR_ID_HABANALABS);
 }
 
-static void hl_device_eq_heartbeat(struct hl_device *hdev)
+static int hl_device_eq_heartbeat_check(struct hl_device *hdev)
 {
-	u64 event_mask = HL_NOTIFIER_EVENT_DEVICE_RESET | HL_NOTIFIER_EVENT_DEVICE_UNAVAILABLE;
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
 
 	if (!prop->cpucp_info.eq_health_check_supported)
-		return;
+		return 0;
 
 	if (hdev->eq_heartbeat_received) {
 		hdev->eq_heartbeat_received = false;
 	} else {
 		dev_err(hdev->dev, "EQ heartbeat event was not received!\n");
-		hl_device_cond_reset(hdev, HL_DRV_RESET_HARD, event_mask);
+		return -EIO;
 	}
+
+	return 0;
 }
 
 static void hl_device_heartbeat(struct work_struct *work)
@@ -1074,10 +1075,9 @@ static void hl_device_heartbeat(struct work_struct *work)
 	/*
 	 * For EQ health check need to check if driver received the heartbeat eq event
 	 * in order to validate the eq is working.
+	 * Only if both the EQ is healthy and we managed to send the next heartbeat reschedule.
 	 */
-	hl_device_eq_heartbeat(hdev);
-
-	if (!hdev->asic_funcs->send_heartbeat(hdev))
+	if ((!hl_device_eq_heartbeat_check(hdev)) && (!hdev->asic_funcs->send_heartbeat(hdev)))
 		goto reschedule;
 
 	if (hl_device_operational(hdev, NULL))
-- 
cgit 


From 0ec346779644039c4c05cfa7f071b1a24e54d8d9 Mon Sep 17 00:00:00 2001
From: Dafna Hirschfeld <dhirschfeld@habana.ai>
Date: Tue, 31 Oct 2023 13:51:10 +0200
Subject: accel/habanalabs/gaudi2: fix undef opcode reporting

currently the undefined opcode event bit in set only for lower cp and
only if 'write_enable' is true. It should be set anyway and for all
streams in order to report that event to userspace.

Signed-off-by: Dafna Hirschfeld <dhirschfeld@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
 drivers/accel/habanalabs/gaudi2/gaudi2.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/habanalabs/gaudi2/gaudi2.c b/drivers/accel/habanalabs/gaudi2/gaudi2.c
index b739078c2d87..5075f92d15cc 100644
--- a/drivers/accel/habanalabs/gaudi2/gaudi2.c
+++ b/drivers/accel/habanalabs/gaudi2/gaudi2.c
@@ -7929,21 +7929,19 @@ static int gaudi2_handle_qman_err_generic(struct hl_device *hdev, u16 event_type
 				error_count++;
 			}
 
-		if (i == QMAN_STREAMS && error_count) {
-			/* check for undefined opcode */
-			if (glbl_sts_val & PDMA0_QM_GLBL_ERR_STS_CP_UNDEF_CMD_ERR_MASK &&
-					hdev->captured_err_info.undef_opcode.write_enable) {
+		/* check for undefined opcode */
+		if (glbl_sts_val & PDMA0_QM_GLBL_ERR_STS_CP_UNDEF_CMD_ERR_MASK) {
+			*event_mask |= HL_NOTIFIER_EVENT_UNDEFINED_OPCODE;
+			if (hdev->captured_err_info.undef_opcode.write_enable) {
 				memset(&hdev->captured_err_info.undef_opcode, 0,
 						sizeof(hdev->captured_err_info.undef_opcode));
-
-				hdev->captured_err_info.undef_opcode.write_enable = false;
 				hdev->captured_err_info.undef_opcode.timestamp = ktime_get();
 				hdev->captured_err_info.undef_opcode.engine_id =
 							gaudi2_queue_id_to_engine_id[qid_base];
-				*event_mask |= HL_NOTIFIER_EVENT_UNDEFINED_OPCODE;
 			}
 
-			handle_lower_qman_data_on_err(hdev, qman_base, *event_mask);
+			if (i == QMAN_STREAMS)
+				handle_lower_qman_data_on_err(hdev, qman_base, *event_mask);
 		}
 	}
 
-- 
cgit 


From 571cdb6e3b9a9c077b39047091f0ccc721b92b83 Mon Sep 17 00:00:00 2001
From: Ofir Bitton <obitton@habana.ai>
Date: Thu, 9 Nov 2023 10:53:10 +0200
Subject: accel/habanalabs: remove 'get temperature' debug print

The print was added long back for a specific debug and can
now be removed.

Signed-off-by: Ofir Bitton <obitton@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
 drivers/accel/habanalabs/common/hwmon.c | 4 ----
 1 file changed, 4 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/habanalabs/common/hwmon.c b/drivers/accel/habanalabs/common/hwmon.c
index 8598056216e7..1ee2ee07e9ed 100644
--- a/drivers/accel/habanalabs/common/hwmon.c
+++ b/drivers/accel/habanalabs/common/hwmon.c
@@ -578,10 +578,6 @@ int hl_get_temperature(struct hl_device *hdev,
 				CPUCP_PKT_CTL_OPCODE_SHIFT);
 	pkt.sensor_index = __cpu_to_le16(sensor_index);
 	pkt.type = __cpu_to_le16(attr);
-
-	dev_dbg(hdev->dev, "get temp, ctl 0x%x, sensor %d, type %d\n",
-		pkt.ctl, pkt.sensor_index, pkt.type);
-
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
 						0, &result);
 
-- 
cgit 


From 4b0b1fbc7757169b6d304545a321c7a88f13f8f0 Mon Sep 17 00:00:00 2001
From: Tomer Tayar <ttayar@habana.ai>
Date: Thu, 20 Jul 2023 16:50:39 +0300
Subject: accel/habanalabs: set hard reset flag if graceful reset is skipped

hl_device_cond_reset() might be called with the hard reset flag unset,
because a compute reset upon device release as part of a graceful reset
is valid.
If the conditions for graceful reset are not met, hl_device_reset() will
be called for an immediate reset. In this case a compute reset is not
valid, so it will be replaced with a hard reset together with a debug
message about it.
This message might be confusing, as it implies that a compute reset was
requested when it shouldn't. To prevent this confusion, set the hard
reset flag in hl_device_cond_reset() if going to an immediate reset.

Signed-off-by: Tomer Tayar <ttayar@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
 drivers/accel/habanalabs/common/device.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/habanalabs/common/device.c b/drivers/accel/habanalabs/common/device.c
index 6bf5f1d0d005..a365791a9f5c 100644
--- a/drivers/accel/habanalabs/common/device.c
+++ b/drivers/accel/habanalabs/common/device.c
@@ -2040,7 +2040,7 @@ device_reset:
 	if (ctx)
 		hl_ctx_put(ctx);
 
-	return hl_device_reset(hdev, flags);
+	return hl_device_reset(hdev, flags | HL_DRV_RESET_HARD);
 }
 
 static void hl_notifier_event_send(struct hl_notifier_event *notifier_event, u64 event_mask)
-- 
cgit 


From ae303d885d4a0fcea65330de9327d28edfebd206 Mon Sep 17 00:00:00 2001
From: Tomer Tayar <ttayar@habana.ai>
Date: Mon, 6 Nov 2023 18:41:35 +0200
Subject: accel/habanalabs/gaudi2: get the correct QM CQ info upon an error

Upon a QM error, the address/size from both the CQ and the ARC_CQ are
printed, although the instruction that led to the error was received
from only one of them.

Moreover, in case of a QM undefined opcode, only one of these
address/size sets will be captured based on the value of ARC_CQ_PTR.
However, this value can be non-zero even if currently the CQ is used, in
case the CQ/ARC_CQ are alternately used.

Under the assumption of having a stop-on-error configuration, modify to
use CP_STS.CUR_CQ field to get the relevant CQ for the QM error.

Signed-off-by: Tomer Tayar <ttayar@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
 drivers/accel/habanalabs/gaudi2/gaudi2.c           | 44 +++++++++++-----------
 .../include/gaudi2/asic_reg/gaudi2_regs.h          |  1 +
 2 files changed, 23 insertions(+), 22 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/habanalabs/gaudi2/gaudi2.c b/drivers/accel/habanalabs/gaudi2/gaudi2.c
index 5075f92d15cc..77c480725a84 100644
--- a/drivers/accel/habanalabs/gaudi2/gaudi2.c
+++ b/drivers/accel/habanalabs/gaudi2/gaudi2.c
@@ -7860,36 +7860,36 @@ static bool gaudi2_handle_ecc_event(struct hl_device *hdev, u16 event_type,
 
 static void handle_lower_qman_data_on_err(struct hl_device *hdev, u64 qman_base, u64 event_mask)
 {
-	u32 lo, hi, cq_ptr_size, arc_cq_ptr_size;
-	u64 cq_ptr, arc_cq_ptr, cp_current_inst;
-
-	lo = RREG32(qman_base + QM_CQ_PTR_LO_4_OFFSET);
-	hi = RREG32(qman_base + QM_CQ_PTR_HI_4_OFFSET);
-	cq_ptr = ((u64) hi) << 32 | lo;
-	cq_ptr_size = RREG32(qman_base + QM_CQ_TSIZE_4_OFFSET);
-
-	lo = RREG32(qman_base + QM_ARC_CQ_PTR_LO_OFFSET);
-	hi = RREG32(qman_base + QM_ARC_CQ_PTR_HI_OFFSET);
-	arc_cq_ptr = ((u64) hi) << 32 | lo;
-	arc_cq_ptr_size = RREG32(qman_base + QM_ARC_CQ_TSIZE_OFFSET);
+	u32 lo, hi, cq_ptr_size, cp_sts;
+	u64 cq_ptr, cp_current_inst;
+	bool is_arc_cq;
+
+	cp_sts = RREG32(qman_base + QM_CP_STS_4_OFFSET);
+	is_arc_cq = FIELD_GET(PDMA0_QM_CP_STS_CUR_CQ_MASK, cp_sts); /* 0 - legacy CQ, 1 - ARC_CQ */
+
+	if (is_arc_cq) {
+		lo = RREG32(qman_base + QM_ARC_CQ_PTR_LO_OFFSET);
+		hi = RREG32(qman_base + QM_ARC_CQ_PTR_HI_OFFSET);
+		cq_ptr = ((u64) hi) << 32 | lo;
+		cq_ptr_size = RREG32(qman_base + QM_ARC_CQ_TSIZE_OFFSET);
+	} else {
+		lo = RREG32(qman_base + QM_CQ_PTR_LO_4_OFFSET);
+		hi = RREG32(qman_base + QM_CQ_PTR_HI_4_OFFSET);
+		cq_ptr = ((u64) hi) << 32 | lo;
+		cq_ptr_size = RREG32(qman_base + QM_CQ_TSIZE_4_OFFSET);
+	}
 
 	lo = RREG32(qman_base + QM_CP_CURRENT_INST_LO_4_OFFSET);
 	hi = RREG32(qman_base + QM_CP_CURRENT_INST_HI_4_OFFSET);
 	cp_current_inst = ((u64) hi) << 32 | lo;
 
 	dev_info(hdev->dev,
-		"LowerQM. CQ: {ptr %#llx, size %u}, ARC_CQ: {ptr %#llx, size %u}, CP: {instruction %#llx}\n",
-		cq_ptr, cq_ptr_size, arc_cq_ptr, arc_cq_ptr_size, cp_current_inst);
+		"LowerQM. %sCQ: {ptr %#llx, size %u}, CP: {instruction %#llx}\n",
+		is_arc_cq ? "ARC_" : "", cq_ptr, cq_ptr_size, cp_current_inst);
 
 	if (event_mask & HL_NOTIFIER_EVENT_UNDEFINED_OPCODE) {
-		if (arc_cq_ptr) {
-			hdev->captured_err_info.undef_opcode.cq_addr = arc_cq_ptr;
-			hdev->captured_err_info.undef_opcode.cq_size = arc_cq_ptr_size;
-		} else {
-			hdev->captured_err_info.undef_opcode.cq_addr = cq_ptr;
-			hdev->captured_err_info.undef_opcode.cq_size = cq_ptr_size;
-		}
-
+		hdev->captured_err_info.undef_opcode.cq_addr = cq_ptr;
+		hdev->captured_err_info.undef_opcode.cq_size = cq_ptr_size;
 		hdev->captured_err_info.undef_opcode.stream_id = QMAN_STREAMS;
 	}
 }
diff --git a/drivers/accel/habanalabs/include/gaudi2/asic_reg/gaudi2_regs.h b/drivers/accel/habanalabs/include/gaudi2/asic_reg/gaudi2_regs.h
index a08378d0802b..8018214a7b59 100644
--- a/drivers/accel/habanalabs/include/gaudi2/asic_reg/gaudi2_regs.h
+++ b/drivers/accel/habanalabs/include/gaudi2/asic_reg/gaudi2_regs.h
@@ -250,6 +250,7 @@
 #define QM_ARC_CQ_PTR_HI_OFFSET		(mmPDMA0_QM_ARC_CQ_PTR_HI - mmPDMA0_QM_BASE)
 #define QM_ARC_CQ_TSIZE_OFFSET		(mmPDMA0_QM_ARC_CQ_TSIZE - mmPDMA0_QM_BASE)
 
+#define QM_CP_STS_4_OFFSET		(mmPDMA0_QM_CP_STS_4 - mmPDMA0_QM_BASE)
 #define QM_CP_CURRENT_INST_LO_4_OFFSET	(mmPDMA0_QM_CP_CURRENT_INST_LO_4 - mmPDMA0_QM_BASE)
 #define QM_CP_CURRENT_INST_HI_4_OFFSET	(mmPDMA0_QM_CP_CURRENT_INST_HI_4 - mmPDMA0_QM_BASE)
 
-- 
cgit 


From c9f9d0e3d0db300315d3bde7f122439633e6f007 Mon Sep 17 00:00:00 2001
From: Dani Liberman <dliberman@habana.ai>
Date: Sun, 12 Nov 2023 13:38:42 +0200
Subject: accel/habanalabs: print error code when mapping fails

Failure to map is considered a non-trivial error and we need to notify
the user about it.

Signed-off-by: Dani Liberman <dliberman@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
 drivers/accel/habanalabs/common/memory.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/habanalabs/common/memory.c b/drivers/accel/habanalabs/common/memory.c
index 0b8689fe0b64..3348ad12c237 100644
--- a/drivers/accel/habanalabs/common/memory.c
+++ b/drivers/accel/habanalabs/common/memory.c
@@ -955,8 +955,8 @@ static int map_phys_pg_pack(struct hl_ctx *ctx, u64 vaddr,
 				(i + 1) == phys_pg_pack->npages);
 		if (rc) {
 			dev_err(hdev->dev,
-				"map failed for handle %u, npages: %llu, mapped: %llu",
-				phys_pg_pack->handle, phys_pg_pack->npages,
+				"map failed (%d) for handle %u, npages: %llu, mapped: %llu\n",
+				rc, phys_pg_pack->handle, phys_pg_pack->npages,
 				mapped_pg_cnt);
 			goto err;
 		}
@@ -1186,7 +1186,8 @@ static int map_device_va(struct hl_ctx *ctx, struct hl_mem_in *args, u64 *device
 
 	rc = map_phys_pg_pack(ctx, ret_vaddr, phys_pg_pack);
 	if (rc) {
-		dev_err(hdev->dev, "mapping page pack failed for handle %u\n", handle);
+		dev_err(hdev->dev, "mapping page pack failed (%d) for handle %u\n",
+			rc, handle);
 		mutex_unlock(&hdev->mmu_lock);
 		goto map_err;
 	}
-- 
cgit 


From 47a552863d6c9ea26abe9ad35d2c35e4d6896551 Mon Sep 17 00:00:00 2001
From: Dani Liberman <dliberman@habana.ai>
Date: Mon, 13 Nov 2023 21:11:13 +0200
Subject: accel/habanalabs: expose module id through sysfs

Module ID exposes the physical location of the device in the server,
from the pov of the devices in regard to how they are connected by
internal fabric.

This information is already exposed in our INFO ioctl, but there are
utilities and scripts running in data-center which are already
accessing sysfs for topology information and it is easier for them
to continue getting that information from sysfs instead of opening
a file descriptor.

Signed-off-by: Dani Liberman <dliberman@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
 drivers/accel/habanalabs/common/sysfs.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

(limited to 'drivers/accel')

diff --git a/drivers/accel/habanalabs/common/sysfs.c b/drivers/accel/habanalabs/common/sysfs.c
index 278606373055..8d2164691d81 100644
--- a/drivers/accel/habanalabs/common/sysfs.c
+++ b/drivers/accel/habanalabs/common/sysfs.c
@@ -386,6 +386,14 @@ static ssize_t security_enabled_show(struct device *dev,
 	return sprintf(buf, "%d\n", hdev->asic_prop.fw_security_enabled);
 }
 
+static ssize_t module_id_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct hl_device *hdev = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%u\n", le32_to_cpu(hdev->asic_prop.cpucp_info.card_location));
+}
+
 static DEVICE_ATTR_RO(armcp_kernel_ver);
 static DEVICE_ATTR_RO(armcp_ver);
 static DEVICE_ATTR_RO(cpld_ver);
@@ -405,6 +413,7 @@ static DEVICE_ATTR_RO(thermal_ver);
 static DEVICE_ATTR_RO(uboot_ver);
 static DEVICE_ATTR_RO(fw_os_ver);
 static DEVICE_ATTR_RO(security_enabled);
+static DEVICE_ATTR_RO(module_id);
 
 static struct bin_attribute bin_attr_eeprom = {
 	.attr = {.name = "eeprom", .mode = (0444)},
@@ -430,6 +439,7 @@ static struct attribute *hl_dev_attrs[] = {
 	&dev_attr_uboot_ver.attr,
 	&dev_attr_fw_os_ver.attr,
 	&dev_attr_security_enabled.attr,
+	&dev_attr_module_id.attr,
 	NULL,
 };
 
-- 
cgit 


From 5bc155cfea605cd64aa372b44a67473b49c4726c Mon Sep 17 00:00:00 2001
From: Tomer Tayar <ttayar@habana.ai>
Date: Fri, 17 Nov 2023 12:49:19 +0200
Subject: accel/habanalabs/gaudi2: use correct registers to dump QM CQ info

The QM CQ PTR_LO/PTR_HI/TSIZE registers are for pushing a CQ entry, and
although they are updated by HW even when descriptors are fetched by PQ
and CB addresses are fed into CQ, the correct registers to use when
dumping the CQ info are the ones with the _STS suffix.

Signed-off-by: Tomer Tayar <ttayar@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
 drivers/accel/habanalabs/gaudi2/gaudi2.c                     | 12 ++++++------
 .../accel/habanalabs/include/gaudi2/asic_reg/gaudi2_regs.h   | 12 ++++++------
 2 files changed, 12 insertions(+), 12 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/habanalabs/gaudi2/gaudi2.c b/drivers/accel/habanalabs/gaudi2/gaudi2.c
index 77c480725a84..bf537c2082cd 100644
--- a/drivers/accel/habanalabs/gaudi2/gaudi2.c
+++ b/drivers/accel/habanalabs/gaudi2/gaudi2.c
@@ -7868,15 +7868,15 @@ static void handle_lower_qman_data_on_err(struct hl_device *hdev, u64 qman_base,
 	is_arc_cq = FIELD_GET(PDMA0_QM_CP_STS_CUR_CQ_MASK, cp_sts); /* 0 - legacy CQ, 1 - ARC_CQ */
 
 	if (is_arc_cq) {
-		lo = RREG32(qman_base + QM_ARC_CQ_PTR_LO_OFFSET);
-		hi = RREG32(qman_base + QM_ARC_CQ_PTR_HI_OFFSET);
+		lo = RREG32(qman_base + QM_ARC_CQ_PTR_LO_STS_OFFSET);
+		hi = RREG32(qman_base + QM_ARC_CQ_PTR_HI_STS_OFFSET);
 		cq_ptr = ((u64) hi) << 32 | lo;
-		cq_ptr_size = RREG32(qman_base + QM_ARC_CQ_TSIZE_OFFSET);
+		cq_ptr_size = RREG32(qman_base + QM_ARC_CQ_TSIZE_STS_OFFSET);
 	} else {
-		lo = RREG32(qman_base + QM_CQ_PTR_LO_4_OFFSET);
-		hi = RREG32(qman_base + QM_CQ_PTR_HI_4_OFFSET);
+		lo = RREG32(qman_base + QM_CQ_PTR_LO_STS_4_OFFSET);
+		hi = RREG32(qman_base + QM_CQ_PTR_HI_STS_4_OFFSET);
 		cq_ptr = ((u64) hi) << 32 | lo;
-		cq_ptr_size = RREG32(qman_base + QM_CQ_TSIZE_4_OFFSET);
+		cq_ptr_size = RREG32(qman_base + QM_CQ_TSIZE_STS_4_OFFSET);
 	}
 
 	lo = RREG32(qman_base + QM_CP_CURRENT_INST_LO_4_OFFSET);
diff --git a/drivers/accel/habanalabs/include/gaudi2/asic_reg/gaudi2_regs.h b/drivers/accel/habanalabs/include/gaudi2/asic_reg/gaudi2_regs.h
index 8018214a7b59..d21fcd3880b4 100644
--- a/drivers/accel/habanalabs/include/gaudi2/asic_reg/gaudi2_regs.h
+++ b/drivers/accel/habanalabs/include/gaudi2/asic_reg/gaudi2_regs.h
@@ -242,13 +242,13 @@
 #define QM_FENCE2_OFFSET		(mmPDMA0_QM_CP_FENCE2_RDATA_0 - mmPDMA0_QM_BASE)
 #define QM_SEI_STATUS_OFFSET		(mmPDMA0_QM_SEI_STATUS - mmPDMA0_QM_BASE)
 
-#define QM_CQ_PTR_LO_4_OFFSET		(mmPDMA0_QM_CQ_PTR_LO_4 - mmPDMA0_QM_BASE)
-#define QM_CQ_PTR_HI_4_OFFSET		(mmPDMA0_QM_CQ_PTR_HI_4 - mmPDMA0_QM_BASE)
-#define QM_CQ_TSIZE_4_OFFSET		(mmPDMA0_QM_CQ_TSIZE_4 - mmPDMA0_QM_BASE)
+#define QM_CQ_TSIZE_STS_4_OFFSET	(mmPDMA0_QM_CQ_TSIZE_STS_4 - mmPDMA0_QM_BASE)
+#define QM_CQ_PTR_LO_STS_4_OFFSET	(mmPDMA0_QM_CQ_PTR_LO_STS_4 - mmPDMA0_QM_BASE)
+#define QM_CQ_PTR_HI_STS_4_OFFSET	(mmPDMA0_QM_CQ_PTR_HI_STS_4 - mmPDMA0_QM_BASE)
 
-#define QM_ARC_CQ_PTR_LO_OFFSET		(mmPDMA0_QM_ARC_CQ_PTR_LO - mmPDMA0_QM_BASE)
-#define QM_ARC_CQ_PTR_HI_OFFSET		(mmPDMA0_QM_ARC_CQ_PTR_HI - mmPDMA0_QM_BASE)
-#define QM_ARC_CQ_TSIZE_OFFSET		(mmPDMA0_QM_ARC_CQ_TSIZE - mmPDMA0_QM_BASE)
+#define QM_ARC_CQ_TSIZE_STS_OFFSET	(mmPDMA0_QM_ARC_CQ_TSIZE_STS - mmPDMA0_QM_BASE)
+#define QM_ARC_CQ_PTR_LO_STS_OFFSET	(mmPDMA0_QM_ARC_CQ_PTR_LO_STS - mmPDMA0_QM_BASE)
+#define QM_ARC_CQ_PTR_HI_STS_OFFSET	(mmPDMA0_QM_ARC_CQ_PTR_HI_STS - mmPDMA0_QM_BASE)
 
 #define QM_CP_STS_4_OFFSET		(mmPDMA0_QM_CP_STS_4 - mmPDMA0_QM_BASE)
 #define QM_CP_CURRENT_INST_LO_4_OFFSET	(mmPDMA0_QM_CP_CURRENT_INST_LO_4 - mmPDMA0_QM_BASE)
-- 
cgit 


From 7259eb7b534735b9c1153654c0bb4c5f059c0dd3 Mon Sep 17 00:00:00 2001
From: Moti Haimovski <mhaimovski@habana.ai>
Date: Sun, 12 Nov 2023 18:07:10 +0200
Subject: accel/habanalabs/gaudi2: add signed dev info uAPI

User will provide a nonce via the INFO ioctl, and will retrieve
the signed device info generated using given nonce.

Signed-off-by: Moti Haimovski <mhaimovski@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
 drivers/accel/habanalabs/common/firmware_if.c      |  8 ++++
 drivers/accel/habanalabs/common/habanalabs.h       |  2 +
 drivers/accel/habanalabs/common/habanalabs_ioctl.c | 53 ++++++++++++++++++++++
 3 files changed, 63 insertions(+)

(limited to 'drivers/accel')

diff --git a/drivers/accel/habanalabs/common/firmware_if.c b/drivers/accel/habanalabs/common/firmware_if.c
index 9e9dfe013659..3558a6a8e192 100644
--- a/drivers/accel/habanalabs/common/firmware_if.c
+++ b/drivers/accel/habanalabs/common/firmware_if.c
@@ -3244,6 +3244,14 @@ int hl_fw_get_sec_attest_info(struct hl_device *hdev, struct cpucp_sec_attest_in
 					HL_CPUCP_SEC_ATTEST_INFO_TINEOUT_USEC);
 }
 
+int hl_fw_get_dev_info_signed(struct hl_device *hdev,
+			      struct cpucp_dev_info_signed *dev_info_signed, u32 nonce)
+{
+	return hl_fw_get_sec_attest_data(hdev, CPUCP_PACKET_INFO_SIGNED_GET, dev_info_signed,
+					 sizeof(struct cpucp_dev_info_signed), nonce,
+					 HL_CPUCP_SEC_ATTEST_INFO_TINEOUT_USEC);
+}
+
 int hl_fw_send_generic_request(struct hl_device *hdev, enum hl_passthrough_type sub_opcode,
 						dma_addr_t buff, u32 *size)
 {
diff --git a/drivers/accel/habanalabs/common/habanalabs.h b/drivers/accel/habanalabs/common/habanalabs.h
index 7b0209e5bad6..dd3fe3ddc00a 100644
--- a/drivers/accel/habanalabs/common/habanalabs.h
+++ b/drivers/accel/habanalabs/common/habanalabs.h
@@ -3964,6 +3964,8 @@ long hl_fw_get_max_power(struct hl_device *hdev);
 void hl_fw_set_max_power(struct hl_device *hdev);
 int hl_fw_get_sec_attest_info(struct hl_device *hdev, struct cpucp_sec_attest_info *sec_attest_info,
 				u32 nonce);
+int hl_fw_get_dev_info_signed(struct hl_device *hdev,
+			      struct cpucp_dev_info_signed *dev_info_signed, u32 nonce);
 int hl_set_voltage(struct hl_device *hdev, int sensor_index, u32 attr, long value);
 int hl_set_current(struct hl_device *hdev, int sensor_index, u32 attr, long value);
 int hl_set_power(struct hl_device *hdev, int sensor_index, u32 attr, long value);
diff --git a/drivers/accel/habanalabs/common/habanalabs_ioctl.c b/drivers/accel/habanalabs/common/habanalabs_ioctl.c
index 8ef36effb95b..a92713e0e580 100644
--- a/drivers/accel/habanalabs/common/habanalabs_ioctl.c
+++ b/drivers/accel/habanalabs/common/habanalabs_ioctl.c
@@ -19,6 +19,9 @@
 
 #include <asm/msr.h>
 
+/* make sure there is space for all the signed info */
+static_assert(sizeof(struct cpucp_info) <= SEC_DEV_INFO_BUF_SZ);
+
 static u32 hl_debug_struct_size[HL_DEBUG_OP_TIMESTAMP + 1] = {
 	[HL_DEBUG_OP_ETR] = sizeof(struct hl_debug_params_etr),
 	[HL_DEBUG_OP_ETF] = sizeof(struct hl_debug_params_etf),
@@ -719,6 +722,53 @@ free_sec_attest_info:
 	return rc;
 }
 
+static int dev_info_signed(struct hl_fpriv *hpriv, struct hl_info_args *args)
+{
+	void __user *out = (void __user *) (uintptr_t) args->return_pointer;
+	struct cpucp_dev_info_signed *dev_info_signed;
+	struct hl_info_signed *info;
+	u32 max_size = args->return_size;
+	int rc;
+
+	if ((!max_size) || (!out))
+		return -EINVAL;
+
+	dev_info_signed = kzalloc(sizeof(*dev_info_signed), GFP_KERNEL);
+	if (!dev_info_signed)
+		return -ENOMEM;
+
+	info = kzalloc(sizeof(*info), GFP_KERNEL);
+	if (!info) {
+		rc = -ENOMEM;
+		goto free_dev_info_signed;
+	}
+
+	rc = hl_fw_get_dev_info_signed(hpriv->hdev,
+					dev_info_signed, args->sec_attest_nonce);
+	if (rc)
+		goto free_info;
+
+	info->nonce = le32_to_cpu(dev_info_signed->nonce);
+	info->info_sig_len = dev_info_signed->info_sig_len;
+	info->pub_data_len = le16_to_cpu(dev_info_signed->pub_data_len);
+	info->certificate_len = le16_to_cpu(dev_info_signed->certificate_len);
+	info->dev_info_len = sizeof(struct cpucp_info);
+	memcpy(&info->info_sig, &dev_info_signed->info_sig, sizeof(info->info_sig));
+	memcpy(&info->public_data, &dev_info_signed->public_data, sizeof(info->public_data));
+	memcpy(&info->certificate, &dev_info_signed->certificate, sizeof(info->certificate));
+	memcpy(&info->dev_info, &dev_info_signed->info, info->dev_info_len);
+
+	rc = copy_to_user(out, info, min_t(size_t, max_size, sizeof(*info))) ? -EFAULT : 0;
+
+free_info:
+	kfree(info);
+free_dev_info_signed:
+	kfree(dev_info_signed);
+
+	return rc;
+}
+
+
 static int eventfd_register(struct hl_fpriv *hpriv, struct hl_info_args *args)
 {
 	int rc;
@@ -1089,6 +1139,9 @@ static int _hl_info_ioctl(struct hl_fpriv *hpriv, void *data,
 	case HL_INFO_FW_GENERIC_REQ:
 		return send_fw_generic_request(hdev, args);
 
+	case HL_INFO_DEV_SIGNED:
+		return dev_info_signed(hpriv, args);
+
 	default:
 		dev_err(dev, "Invalid request %d\n", args->op);
 		rc = -EINVAL;
-- 
cgit 


From d980e1ced9899451d2d2a84030ce9f2a04eae7e8 Mon Sep 17 00:00:00 2001
From: Ariel Suller <asuller@habana.ai>
Date: Thu, 23 Nov 2023 16:27:07 +0200
Subject: accel/habanalabs: report 3 instances of Infineon second stage

Infineon controller second stage has 3 instances that their version
need to be reported by driver.

Signed-off-by: Ariel Suller <asuller@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
 drivers/accel/habanalabs/common/sysfs.c | 20 ++++++++++++++++++--
 1 file changed, 18 insertions(+), 2 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/habanalabs/common/sysfs.c b/drivers/accel/habanalabs/common/sysfs.c
index 8d2164691d81..c940c5f1d109 100644
--- a/drivers/accel/habanalabs/common/sysfs.c
+++ b/drivers/accel/habanalabs/common/sysfs.c
@@ -8,6 +8,7 @@
 #include "habanalabs.h"
 
 #include <linux/pci.h>
+#include <linux/types.h>
 
 static ssize_t clk_max_freq_mhz_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
@@ -80,12 +81,27 @@ static ssize_t vrm_ver_show(struct device *dev, struct device_attribute *attr, c
 {
 	struct hl_device *hdev = dev_get_drvdata(dev);
 	struct cpucp_info *cpucp_info;
+	u32 infineon_second_stage_version;
+	u32 infineon_second_stage_first_instance;
+	u32 infineon_second_stage_second_instance;
+	u32 infineon_second_stage_third_instance;
+	u32 mask = 0xff;
 
 	cpucp_info = &hdev->asic_prop.cpucp_info;
 
+	infineon_second_stage_version = le32_to_cpu(cpucp_info->infineon_second_stage_version);
+	infineon_second_stage_first_instance = infineon_second_stage_version & mask;
+	infineon_second_stage_second_instance =
+					(infineon_second_stage_version >> 8) & mask;
+	infineon_second_stage_third_instance =
+					(infineon_second_stage_version >> 16) & mask;
+
 	if (cpucp_info->infineon_second_stage_version)
-		return sprintf(buf, "%#04x %#04x\n", le32_to_cpu(cpucp_info->infineon_version),
-				le32_to_cpu(cpucp_info->infineon_second_stage_version));
+		return sprintf(buf, "%#04x %#04x:%#04x:%#04x\n",
+				le32_to_cpu(cpucp_info->infineon_version),
+				infineon_second_stage_first_instance,
+				infineon_second_stage_second_instance,
+				infineon_second_stage_third_instance);
 	else
 		return sprintf(buf, "%#04x\n", le32_to_cpu(cpucp_info->infineon_version));
 }
-- 
cgit 


From 565ee78840906da33f124c143e0c788e42f824e8 Mon Sep 17 00:00:00 2001
From: Tomer Tayar <ttayar@habana.ai>
Date: Thu, 23 Nov 2023 09:49:36 +0200
Subject: accel/habanalabs/gaudi2: add zero padding when printing QM CP
 instruction

QM instructions are in multiples of 64 bits and the command type is in
the upper bits of first QWORD.
To make it clearer that an undefined command is due to a type of 0x0,
always print all 64 bits and add a zero padding if needed.

Signed-off-by: Tomer Tayar <ttayar@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
 drivers/accel/habanalabs/gaudi2/gaudi2.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/habanalabs/gaudi2/gaudi2.c b/drivers/accel/habanalabs/gaudi2/gaudi2.c
index bf537c2082cd..f81b57649b00 100644
--- a/drivers/accel/habanalabs/gaudi2/gaudi2.c
+++ b/drivers/accel/habanalabs/gaudi2/gaudi2.c
@@ -7884,7 +7884,7 @@ static void handle_lower_qman_data_on_err(struct hl_device *hdev, u64 qman_base,
 	cp_current_inst = ((u64) hi) << 32 | lo;
 
 	dev_info(hdev->dev,
-		"LowerQM. %sCQ: {ptr %#llx, size %u}, CP: {instruction %#llx}\n",
+		"LowerQM. %sCQ: {ptr %#llx, size %u}, CP: {instruction %#018llx}\n",
 		is_arc_cq ? "ARC_" : "", cq_ptr, cq_ptr_size, cp_current_inst);
 
 	if (event_mask & HL_NOTIFIER_EVENT_UNDEFINED_OPCODE) {
-- 
cgit 


From aa5cea38ce687021bf97f9f4cdb18b26db290964 Mon Sep 17 00:00:00 2001
From: Tomer Tayar <ttayar@habana.ai>
Date: Wed, 3 May 2023 13:19:17 +0300
Subject: accel/habanalabs: add parent_device sysfs attribute

The device debugfs directory was modified to be named as the
device-name.
This name is the parent device name, i.e. either the PCI address in case
of an ASIC, or the simulator device name in case of a simulator.

This change makes it more difficult for a user to access the debugfs
directory for a specific accel device, because he can't just use the
accel minor id, but he needs to do more device-dependent operations to
get the device name.

To make it easier to get this name, add a 'parent_device' sysfs
attribute that the user can read using the minor id before accessing
debugfs.

Signed-off-by: Tomer Tayar <ttayar@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
 drivers/accel/habanalabs/common/habanalabs.h | 3 +++
 drivers/accel/habanalabs/common/sysfs.c      | 9 +++++++++
 2 files changed, 12 insertions(+)

(limited to 'drivers/accel')

diff --git a/drivers/accel/habanalabs/common/habanalabs.h b/drivers/accel/habanalabs/common/habanalabs.h
index dd3fe3ddc00a..2a900c9941fe 100644
--- a/drivers/accel/habanalabs/common/habanalabs.h
+++ b/drivers/accel/habanalabs/common/habanalabs.h
@@ -3521,6 +3521,9 @@ struct hl_device {
 	u8				heartbeat;
 };
 
+/* Retrieve PCI device name in case of a PCI device or dev name in simulator */
+#define HL_DEV_NAME(hdev)	\
+		((hdev)->pdev ? dev_name(&(hdev)->pdev->dev) : "NA-DEVICE")
 
 /**
  * struct hl_cs_encaps_sig_handle - encapsulated signals handle structure
diff --git a/drivers/accel/habanalabs/common/sysfs.c b/drivers/accel/habanalabs/common/sysfs.c
index c940c5f1d109..8a9f98832157 100644
--- a/drivers/accel/habanalabs/common/sysfs.c
+++ b/drivers/accel/habanalabs/common/sysfs.c
@@ -410,6 +410,13 @@ static ssize_t module_id_show(struct device *dev,
 	return sprintf(buf, "%u\n", le32_to_cpu(hdev->asic_prop.cpucp_info.card_location));
 }
 
+static ssize_t parent_device_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct hl_device *hdev = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%s\n", HL_DEV_NAME(hdev));
+}
+
 static DEVICE_ATTR_RO(armcp_kernel_ver);
 static DEVICE_ATTR_RO(armcp_ver);
 static DEVICE_ATTR_RO(cpld_ver);
@@ -430,6 +437,7 @@ static DEVICE_ATTR_RO(uboot_ver);
 static DEVICE_ATTR_RO(fw_os_ver);
 static DEVICE_ATTR_RO(security_enabled);
 static DEVICE_ATTR_RO(module_id);
+static DEVICE_ATTR_RO(parent_device);
 
 static struct bin_attribute bin_attr_eeprom = {
 	.attr = {.name = "eeprom", .mode = (0444)},
@@ -456,6 +464,7 @@ static struct attribute *hl_dev_attrs[] = {
 	&dev_attr_fw_os_ver.attr,
 	&dev_attr_security_enabled.attr,
 	&dev_attr_module_id.attr,
+	&dev_attr_parent_device.attr,
 	NULL,
 };
 
-- 
cgit 


From bc5f15abcf95ce7e4c2e33daddcb5850ee5e671d Mon Sep 17 00:00:00 2001
From: Tomer Tayar <ttayar@habana.ai>
Date: Wed, 29 Nov 2023 16:20:31 +0200
Subject: accel/habanalabs/gaudi2: avoid overriding existing undefined opcode
 data

Part of the undefined opcode data is updated in
gaudi2_handle_qman_err_generic() and some in
handle_lower_qman_data_on_err().
However, the 'write_enable' flag is checked only in
gaudi2_handle_qman_err_generic(), and information of more than a single
error can be mixed there.

Moreover, handle_lower_qman_data_on_err() is called only for the lower
QMAN, so for an error in the upper QMAN there is only a partial info.

Move all the data update to be done in a single place, protected by the
'write_enable' flag.
As mainly the lower QMAN's info is interesting, avoid saving the partial
info for the upper QMAN.

Signed-off-by: Tomer Tayar <ttayar@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
 drivers/accel/habanalabs/gaudi2/gaudi2.c | 40 +++++++++++++++-----------------
 1 file changed, 19 insertions(+), 21 deletions(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/habanalabs/gaudi2/gaudi2.c b/drivers/accel/habanalabs/gaudi2/gaudi2.c
index f81b57649b00..e0e5615ef9b0 100644
--- a/drivers/accel/habanalabs/gaudi2/gaudi2.c
+++ b/drivers/accel/habanalabs/gaudi2/gaudi2.c
@@ -7858,10 +7858,11 @@ static bool gaudi2_handle_ecc_event(struct hl_device *hdev, u16 event_type,
 	return !!ecc_data->is_critical;
 }
 
-static void handle_lower_qman_data_on_err(struct hl_device *hdev, u64 qman_base, u64 event_mask)
+static void handle_lower_qman_data_on_err(struct hl_device *hdev, u64 qman_base, u32 engine_id)
 {
-	u32 lo, hi, cq_ptr_size, cp_sts;
+	struct undefined_opcode_info *undef_opcode = &hdev->captured_err_info.undef_opcode;
 	u64 cq_ptr, cp_current_inst;
+	u32 lo, hi, cq_size, cp_sts;
 	bool is_arc_cq;
 
 	cp_sts = RREG32(qman_base + QM_CP_STS_4_OFFSET);
@@ -7871,12 +7872,12 @@ static void handle_lower_qman_data_on_err(struct hl_device *hdev, u64 qman_base,
 		lo = RREG32(qman_base + QM_ARC_CQ_PTR_LO_STS_OFFSET);
 		hi = RREG32(qman_base + QM_ARC_CQ_PTR_HI_STS_OFFSET);
 		cq_ptr = ((u64) hi) << 32 | lo;
-		cq_ptr_size = RREG32(qman_base + QM_ARC_CQ_TSIZE_STS_OFFSET);
+		cq_size = RREG32(qman_base + QM_ARC_CQ_TSIZE_STS_OFFSET);
 	} else {
 		lo = RREG32(qman_base + QM_CQ_PTR_LO_STS_4_OFFSET);
 		hi = RREG32(qman_base + QM_CQ_PTR_HI_STS_4_OFFSET);
 		cq_ptr = ((u64) hi) << 32 | lo;
-		cq_ptr_size = RREG32(qman_base + QM_CQ_TSIZE_STS_4_OFFSET);
+		cq_size = RREG32(qman_base + QM_CQ_TSIZE_STS_4_OFFSET);
 	}
 
 	lo = RREG32(qman_base + QM_CP_CURRENT_INST_LO_4_OFFSET);
@@ -7885,12 +7886,16 @@ static void handle_lower_qman_data_on_err(struct hl_device *hdev, u64 qman_base,
 
 	dev_info(hdev->dev,
 		"LowerQM. %sCQ: {ptr %#llx, size %u}, CP: {instruction %#018llx}\n",
-		is_arc_cq ? "ARC_" : "", cq_ptr, cq_ptr_size, cp_current_inst);
+		is_arc_cq ? "ARC_" : "", cq_ptr, cq_size, cp_current_inst);
 
-	if (event_mask & HL_NOTIFIER_EVENT_UNDEFINED_OPCODE) {
-		hdev->captured_err_info.undef_opcode.cq_addr = cq_ptr;
-		hdev->captured_err_info.undef_opcode.cq_size = cq_ptr_size;
-		hdev->captured_err_info.undef_opcode.stream_id = QMAN_STREAMS;
+	if (undef_opcode->write_enable) {
+		memset(undef_opcode, 0, sizeof(*undef_opcode));
+		undef_opcode->timestamp = ktime_get();
+		undef_opcode->cq_addr = cq_ptr;
+		undef_opcode->cq_size = cq_size;
+		undef_opcode->engine_id = engine_id;
+		undef_opcode->stream_id = QMAN_STREAMS;
+		undef_opcode->write_enable = 0;
 	}
 }
 
@@ -7929,19 +7934,12 @@ static int gaudi2_handle_qman_err_generic(struct hl_device *hdev, u16 event_type
 				error_count++;
 			}
 
-		/* check for undefined opcode */
-		if (glbl_sts_val & PDMA0_QM_GLBL_ERR_STS_CP_UNDEF_CMD_ERR_MASK) {
+		/* Check for undefined opcode error in lower QM */
+		if ((i == QMAN_STREAMS) &&
+				(glbl_sts_val & PDMA0_QM_GLBL_ERR_STS_CP_UNDEF_CMD_ERR_MASK)) {
+			handle_lower_qman_data_on_err(hdev, qman_base,
+							gaudi2_queue_id_to_engine_id[qid_base]);
 			*event_mask |= HL_NOTIFIER_EVENT_UNDEFINED_OPCODE;
-			if (hdev->captured_err_info.undef_opcode.write_enable) {
-				memset(&hdev->captured_err_info.undef_opcode, 0,
-						sizeof(hdev->captured_err_info.undef_opcode));
-				hdev->captured_err_info.undef_opcode.timestamp = ktime_get();
-				hdev->captured_err_info.undef_opcode.engine_id =
-							gaudi2_queue_id_to_engine_id[qid_base];
-			}
-
-			if (i == QMAN_STREAMS)
-				handle_lower_qman_data_on_err(hdev, qman_base, *event_mask);
 		}
 	}
 
-- 
cgit 


From a9f07790a4b2250f0140e9a61c7f842fd9b618c7 Mon Sep 17 00:00:00 2001
From: Xingyuan Mo <hdthky0@gmail.com>
Date: Fri, 8 Dec 2023 21:00:59 +0800
Subject: accel/habanalabs: fix information leak in sec_attest_info()

This function may copy the pad0 field of struct hl_info_sec_attest to user
mode which has not been initialized, resulting in leakage of kernel heap
data to user mode. To prevent this, use kzalloc() to allocate and zero out
the buffer, which can also eliminate other uninitialized holes, if any.

Fixes: 0c88760f8f5e ("habanalabs/gaudi2: add secured attestation info uapi")
Signed-off-by: Xingyuan Mo <hdthky0@gmail.com>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
 drivers/accel/habanalabs/common/habanalabs_ioctl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/accel')

diff --git a/drivers/accel/habanalabs/common/habanalabs_ioctl.c b/drivers/accel/habanalabs/common/habanalabs_ioctl.c
index a92713e0e580..1dd6e23172ca 100644
--- a/drivers/accel/habanalabs/common/habanalabs_ioctl.c
+++ b/drivers/accel/habanalabs/common/habanalabs_ioctl.c
@@ -688,7 +688,7 @@ static int sec_attest_info(struct hl_fpriv *hpriv, struct hl_info_args *args)
 	if (!sec_attest_info)
 		return -ENOMEM;
 
-	info = kmalloc(sizeof(*info), GFP_KERNEL);
+	info = kzalloc(sizeof(*info), GFP_KERNEL);
 	if (!info) {
 		rc = -ENOMEM;
 		goto free_sec_attest_info;
-- 
cgit