dmaengine: idxd: Add shared workqueue support

Add shared workqueue support that includes the support of Shared Virtual
memory (SVM) or in similar terms On Demand Paging (ODP). The shared
workqueue uses the enqcmds command in kernel and will respond with retry if
the workqueue is full. Shared workqueue only works when there is PASID
support from the IOMMU.

Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Link: https://lore.kernel.org/r/160382007499.3911367.26043087963708134.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>

1 files changed, 127 insertions, 0 deletions

diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c
index 07a5db06a29a..6d292eb79bf3 100644
--- a/drivers/dma/idxd/sysfs.c
+++ b/drivers/dma/idxd/sysfs.c
@@ -175,6 +175,30 @@ static int idxd_config_bus_probe(struct device *dev)
 			return -EINVAL;
 		}
 
+		/* Shared WQ checks */
+		if (wq_shared(wq)) {
+			if (!device_swq_supported(idxd)) {
+				dev_warn(dev,
+					 "PASID not enabled and shared WQ.\n");
+				mutex_unlock(&wq->wq_lock);
+				return -ENXIO;
+			}
+			/*
+			 * Shared wq with the threshold set to 0 means the user
+			 * did not set the threshold or transitioned from a
+			 * dedicated wq but did not set threshold. A value
+			 * of 0 would effectively disable the shared wq. The
+			 * driver does not allow a value of 0 to be set for
+			 * threshold via sysfs.
+			 */
+			if (wq->threshold == 0) {
+				dev_warn(dev,
+					 "Shared WQ and threshold 0.\n");
+				mutex_unlock(&wq->wq_lock);
+				return -EINVAL;
+			}
+		}
+
 		rc = idxd_wq_alloc_resources(wq);
 		if (rc < 0) {
 			mutex_unlock(&wq->wq_lock);
@@ -875,6 +899,8 @@ static ssize_t wq_mode_store(struct device *dev,
 	if (sysfs_streq(buf, "dedicated")) {
 		set_bit(WQ_FLAG_DEDICATED, &wq->flags);
 		wq->threshold = 0;
+	} else if (sysfs_streq(buf, "shared") && device_swq_supported(idxd)) {
+		clear_bit(WQ_FLAG_DEDICATED, &wq->flags);
 	} else {
 		return -EINVAL;
 	}
@@ -973,6 +999,87 @@ static ssize_t wq_priority_store(struct device *dev,
 static struct device_attribute dev_attr_wq_priority =
 		__ATTR(priority, 0644, wq_priority_show, wq_priority_store);
 
+static ssize_t wq_block_on_fault_show(struct device *dev,
+				      struct device_attribute *attr, char *buf)
+{
+	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
+
+	return sprintf(buf, "%u\n",
+		       test_bit(WQ_FLAG_BLOCK_ON_FAULT, &wq->flags));
+}
+
+static ssize_t wq_block_on_fault_store(struct device *dev,
+				       struct device_attribute *attr,
+				       const char *buf, size_t count)
+{
+	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
+	struct idxd_device *idxd = wq->idxd;
+	bool bof;
+	int rc;
+
+	if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
+		return -EPERM;
+
+	if (wq->state != IDXD_WQ_DISABLED)
+		return -ENXIO;
+
+	rc = kstrtobool(buf, &bof);
+	if (rc < 0)
+		return rc;
+
+	if (bof)
+		set_bit(WQ_FLAG_BLOCK_ON_FAULT, &wq->flags);
+	else
+		clear_bit(WQ_FLAG_BLOCK_ON_FAULT, &wq->flags);
+
+	return count;
+}
+
+static struct device_attribute dev_attr_wq_block_on_fault =
+		__ATTR(block_on_fault, 0644, wq_block_on_fault_show,
+		       wq_block_on_fault_store);
+
+static ssize_t wq_threshold_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
+
+	return sprintf(buf, "%u\n", wq->threshold);
+}
+
+static ssize_t wq_threshold_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t count)
+{
+	struct idxd_wq *wq = container_of(dev, struct idxd_wq, conf_dev);
+	struct idxd_device *idxd = wq->idxd;
+	unsigned int val;
+	int rc;
+
+	rc = kstrtouint(buf, 0, &val);
+	if (rc < 0)
+		return -EINVAL;
+
+	if (val > wq->size || val <= 0)
+		return -EINVAL;
+
+	if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
+		return -EPERM;
+
+	if (wq->state != IDXD_WQ_DISABLED)
+		return -ENXIO;
+
+	if (test_bit(WQ_FLAG_DEDICATED, &wq->flags))
+		return -EINVAL;
+
+	wq->threshold = val;
+
+	return count;
+}
+
+static struct device_attribute dev_attr_wq_threshold =
+		__ATTR(threshold, 0644, wq_threshold_show, wq_threshold_store);
+
 static ssize_t wq_type_show(struct device *dev,
 			    struct device_attribute *attr, char *buf)
 {
@@ -1044,6 +1151,13 @@ static ssize_t wq_name_store(struct device *dev,
 	if (strlen(buf) > WQ_NAME_SIZE || strlen(buf) == 0)
 		return -EINVAL;
 
+	/*
+	 * This is temporarily placed here until we have SVM support for
+	 * dmaengine.
+	 */
+	if (wq->type == IDXD_WQT_KERNEL && device_pasid_enabled(wq->idxd))
+		return -EOPNOTSUPP;
+
 	memset(wq->name, 0, WQ_NAME_SIZE + 1);
 	strncpy(wq->name, buf, WQ_NAME_SIZE);
 	strreplace(wq->name, '\n', '\0');
@@ -1154,6 +1268,8 @@ static struct attribute *idxd_wq_attributes[] = {
 	&dev_attr_wq_mode.attr,
 	&dev_attr_wq_size.attr,
 	&dev_attr_wq_priority.attr,
+	&dev_attr_wq_block_on_fault.attr,
+	&dev_attr_wq_threshold.attr,
 	&dev_attr_wq_type.attr,
 	&dev_attr_wq_name.attr,
 	&dev_attr_wq_cdev_minor.attr,
@@ -1305,6 +1421,16 @@ static ssize_t clients_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(clients);
 
+static ssize_t pasid_enabled_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
+{
+	struct idxd_device *idxd =
+		container_of(dev, struct idxd_device, conf_dev);
+
+	return sprintf(buf, "%u\n", device_pasid_enabled(idxd));
+}
+static DEVICE_ATTR_RO(pasid_enabled);
+
 static ssize_t state_show(struct device *dev,
 			  struct device_attribute *attr, char *buf)
 {
@@ -1424,6 +1550,7 @@ static struct attribute *idxd_device_attributes[] = {
 	&dev_attr_gen_cap.attr,
 	&dev_attr_configurable.attr,
 	&dev_attr_clients.attr,
+	&dev_attr_pasid_enabled.attr,
 	&dev_attr_state.attr,
 	&dev_attr_errors.attr,
 	&dev_attr_max_tokens.attr,