diff mbox series

[v14,07/10] iommu/arm-smmu-v3: Maintain a SID->device structure

Message ID 20210401154718.307519-8-jean-philippe@linaro.org (mailing list archive)
State New, archived
Headers show
Series iommu: I/O page faults for SMMUv3 | expand

Commit Message

Jean-Philippe Brucker April 1, 2021, 3:47 p.m. UTC
When handling faults from the event or PRI queue, we need to find the
struct device associated with a SID. Add a rb_tree to keep track of
SIDs.

Acked-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Keqian Zhu <zhukeqian1@huawei.com>
Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h |  13 +-
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 158 ++++++++++++++++----
 2 files changed, 141 insertions(+), 30 deletions(-)

Comments

Will Deacon April 1, 2021, 5:07 p.m. UTC | #1
On Thu, Apr 01, 2021 at 05:47:16PM +0200, Jean-Philippe Brucker wrote:
> When handling faults from the event or PRI queue, we need to find the
> struct device associated with a SID. Add a rb_tree to keep track of
> SIDs.
> 
> Acked-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
> Reviewed-by: Eric Auger <eric.auger@redhat.com>
> Reviewed-by: Keqian Zhu <zhukeqian1@huawei.com>
> Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>

Acked-by: Will Deacon <will@kernel.org>

Will
niliqiang Aug. 1, 2024, 3:29 p.m. UTC | #2
> +static int arm_smmu_insert_master(struct arm_smmu_device *smmu,
> +				  struct arm_smmu_master *master)
> +{
> +	int i;
> +	int ret = 0;
> +	struct arm_smmu_stream *new_stream, *cur_stream;
> +	struct rb_node **new_node, *parent_node = NULL;
> +	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(master->dev);
> +
> +	master->streams = kcalloc(fwspec->num_ids, sizeof(*master->streams),
> +				  GFP_KERNEL);
> +	if (!master->streams)
> +		return -ENOMEM;
> +	master->num_streams = fwspec->num_ids;
> +
> +	mutex_lock(&smmu->streams_mutex);
> +	for (i = 0; i < fwspec->num_ids; i++) {

Hi all experts,

Recently, I have been debugging the smmuv3 code in the Linux kernel,
and I have some questions regarding the `mutex_lock(&smmu->streams_mutex)`
statement in the `arm_smmu_insert_master` function. 
I would like to understand why streams_mutex is being locked here. 
Is it to handle different types of PF under a single EP, each with its own device ID?

Thanks.
Robin Murphy Aug. 2, 2024, 12:01 p.m. UTC | #3
On 01/08/2024 4:29 pm, niliqiang wrote:
>> +static int arm_smmu_insert_master(struct arm_smmu_device *smmu,
>> +				  struct arm_smmu_master *master)
>> +{
>> +	int i;
>> +	int ret = 0;
>> +	struct arm_smmu_stream *new_stream, *cur_stream;
>> +	struct rb_node **new_node, *parent_node = NULL;
>> +	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(master->dev);
>> +
>> +	master->streams = kcalloc(fwspec->num_ids, sizeof(*master->streams),
>> +				  GFP_KERNEL);
>> +	if (!master->streams)
>> +		return -ENOMEM;
>> +	master->num_streams = fwspec->num_ids;
>> +
>> +	mutex_lock(&smmu->streams_mutex);
>> +	for (i = 0; i < fwspec->num_ids; i++) {
> 
> Hi all experts,
> 
> Recently, I have been debugging the smmuv3 code in the Linux kernel,
> and I have some questions regarding the `mutex_lock(&smmu->streams_mutex)`
> statement in the `arm_smmu_insert_master` function.
> I would like to understand why streams_mutex is being locked here.

Because the "streams" rbtree is being modified, so it would be pretty 
bad if another thread tried to walk or modify it concurrently. I'd hope 
that was obvious from the code everywhere "streams" and "streams_mutex" 
are referenced.

> Is it to handle different types of PF under a single EP, each with its own device ID?

It is expected that a single SMMU instance is highly likely to have more 
than one device behind it, and therefore more than one StreamID to keep 
track of.

Thanks,
Robin.
niliqiang Aug. 6, 2024, 3:31 p.m. UTC | #4
> It is expected that a single SMMU instance is highly likely to have more 
> than one device behind it, and therefore more than one StreamID to keep 
> track of.

Thanks for your explanation. I now understand the role of the `mutex_lock` statement.
However, I have a new question that I hope you can help me with: I noticed that the
function `arm_smmu_insert_master`, which includes the `mutex_lock` statement, was
introduced in Linux version 5.13. For kernel code before version 5.13, how do we
ensure that there's no resource contention when multiple devices are loaded
behind a single SMMU instance?

Currently, we're indeed encountering resource contention issues when loading
multiple device drivers on the 5.10 kernel. Do you have any suggestions on
how to resolve this issue?

Thanks.
diff mbox series

Patch

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
index 230b6f6b3901..1b463e27bca1 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -639,6 +639,15 @@  struct arm_smmu_device {
 
 	/* IOMMU core code handle */
 	struct iommu_device		iommu;
+
+	struct rb_root			streams;
+	struct mutex			streams_mutex;
+};
+
+struct arm_smmu_stream {
+	u32				id;
+	struct arm_smmu_master		*master;
+	struct rb_node			node;
 };
 
 /* SMMU private data for each master */
@@ -647,8 +656,8 @@  struct arm_smmu_master {
 	struct device			*dev;
 	struct arm_smmu_domain		*domain;
 	struct list_head		domain_head;
-	u32				*sids;
-	unsigned int			num_sids;
+	struct arm_smmu_stream		*streams;
+	unsigned int			num_streams;
 	bool				ats_enabled;
 	bool				sva_enabled;
 	struct list_head		bonds;
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index bd77495023c8..8279291660b2 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -909,8 +909,8 @@  static void arm_smmu_sync_cd(struct arm_smmu_domain *smmu_domain,
 
 	spin_lock_irqsave(&smmu_domain->devices_lock, flags);
 	list_for_each_entry(master, &smmu_domain->devices, domain_head) {
-		for (i = 0; i < master->num_sids; i++) {
-			cmd.cfgi.sid = master->sids[i];
+		for (i = 0; i < master->num_streams; i++) {
+			cmd.cfgi.sid = master->streams[i].id;
 			arm_smmu_cmdq_batch_add(smmu, &cmds, &cmd);
 		}
 	}
@@ -1355,6 +1355,29 @@  static int arm_smmu_init_l2_strtab(struct arm_smmu_device *smmu, u32 sid)
 	return 0;
 }
 
+__maybe_unused
+static struct arm_smmu_master *
+arm_smmu_find_master(struct arm_smmu_device *smmu, u32 sid)
+{
+	struct rb_node *node;
+	struct arm_smmu_stream *stream;
+
+	lockdep_assert_held(&smmu->streams_mutex);
+
+	node = smmu->streams.rb_node;
+	while (node) {
+		stream = rb_entry(node, struct arm_smmu_stream, node);
+		if (stream->id < sid)
+			node = node->rb_right;
+		else if (stream->id > sid)
+			node = node->rb_left;
+		else
+			return stream->master;
+	}
+
+	return NULL;
+}
+
 /* IRQ and event handlers */
 static irqreturn_t arm_smmu_evtq_thread(int irq, void *dev)
 {
@@ -1588,8 +1611,8 @@  static int arm_smmu_atc_inv_master(struct arm_smmu_master *master)
 
 	arm_smmu_atc_inv_to_cmd(0, 0, 0, &cmd);
 
-	for (i = 0; i < master->num_sids; i++) {
-		cmd.atc.sid = master->sids[i];
+	for (i = 0; i < master->num_streams; i++) {
+		cmd.atc.sid = master->streams[i].id;
 		arm_smmu_cmdq_issue_cmd(master->smmu, &cmd);
 	}
 
@@ -1632,8 +1655,8 @@  int arm_smmu_atc_inv_domain(struct arm_smmu_domain *smmu_domain, int ssid,
 		if (!master->ats_enabled)
 			continue;
 
-		for (i = 0; i < master->num_sids; i++) {
-			cmd.atc.sid = master->sids[i];
+		for (i = 0; i < master->num_streams; i++) {
+			cmd.atc.sid = master->streams[i].id;
 			arm_smmu_cmdq_batch_add(smmu_domain->smmu, &cmds, &cmd);
 		}
 	}
@@ -2065,13 +2088,13 @@  static void arm_smmu_install_ste_for_dev(struct arm_smmu_master *master)
 	int i, j;
 	struct arm_smmu_device *smmu = master->smmu;
 
-	for (i = 0; i < master->num_sids; ++i) {
-		u32 sid = master->sids[i];
+	for (i = 0; i < master->num_streams; ++i) {
+		u32 sid = master->streams[i].id;
 		__le64 *step = arm_smmu_get_step_for_sid(smmu, sid);
 
 		/* Bridged PCI devices may end up with duplicated IDs */
 		for (j = 0; j < i; j++)
-			if (master->sids[j] == sid)
+			if (master->streams[j].id == sid)
 				break;
 		if (j < i)
 			continue;
@@ -2348,11 +2371,101 @@  static bool arm_smmu_sid_in_range(struct arm_smmu_device *smmu, u32 sid)
 	return sid < limit;
 }
 
+static int arm_smmu_insert_master(struct arm_smmu_device *smmu,
+				  struct arm_smmu_master *master)
+{
+	int i;
+	int ret = 0;
+	struct arm_smmu_stream *new_stream, *cur_stream;
+	struct rb_node **new_node, *parent_node = NULL;
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(master->dev);
+
+	master->streams = kcalloc(fwspec->num_ids, sizeof(*master->streams),
+				  GFP_KERNEL);
+	if (!master->streams)
+		return -ENOMEM;
+	master->num_streams = fwspec->num_ids;
+
+	mutex_lock(&smmu->streams_mutex);
+	for (i = 0; i < fwspec->num_ids; i++) {
+		u32 sid = fwspec->ids[i];
+
+		new_stream = &master->streams[i];
+		new_stream->id = sid;
+		new_stream->master = master;
+
+		/*
+		 * Check the SIDs are in range of the SMMU and our stream table
+		 */
+		if (!arm_smmu_sid_in_range(smmu, sid)) {
+			ret = -ERANGE;
+			break;
+		}
+
+		/* Ensure l2 strtab is initialised */
+		if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB) {
+			ret = arm_smmu_init_l2_strtab(smmu, sid);
+			if (ret)
+				break;
+		}
+
+		/* Insert into SID tree */
+		new_node = &(smmu->streams.rb_node);
+		while (*new_node) {
+			cur_stream = rb_entry(*new_node, struct arm_smmu_stream,
+					      node);
+			parent_node = *new_node;
+			if (cur_stream->id > new_stream->id) {
+				new_node = &((*new_node)->rb_left);
+			} else if (cur_stream->id < new_stream->id) {
+				new_node = &((*new_node)->rb_right);
+			} else {
+				dev_warn(master->dev,
+					 "stream %u already in tree\n",
+					 cur_stream->id);
+				ret = -EINVAL;
+				break;
+			}
+		}
+		if (ret)
+			break;
+
+		rb_link_node(&new_stream->node, parent_node, new_node);
+		rb_insert_color(&new_stream->node, &smmu->streams);
+	}
+
+	if (ret) {
+		for (i--; i >= 0; i--)
+			rb_erase(&master->streams[i].node, &smmu->streams);
+		kfree(master->streams);
+	}
+	mutex_unlock(&smmu->streams_mutex);
+
+	return ret;
+}
+
+static void arm_smmu_remove_master(struct arm_smmu_master *master)
+{
+	int i;
+	struct arm_smmu_device *smmu = master->smmu;
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(master->dev);
+
+	if (!smmu || !master->streams)
+		return;
+
+	mutex_lock(&smmu->streams_mutex);
+	for (i = 0; i < fwspec->num_ids; i++)
+		rb_erase(&master->streams[i].node, &smmu->streams);
+	mutex_unlock(&smmu->streams_mutex);
+
+	kfree(master->streams);
+}
+
 static struct iommu_ops arm_smmu_ops;
 
 static struct iommu_device *arm_smmu_probe_device(struct device *dev)
 {
-	int i, ret;
+	int ret;
 	struct arm_smmu_device *smmu;
 	struct arm_smmu_master *master;
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
@@ -2373,27 +2486,12 @@  static struct iommu_device *arm_smmu_probe_device(struct device *dev)
 
 	master->dev = dev;
 	master->smmu = smmu;
-	master->sids = fwspec->ids;
-	master->num_sids = fwspec->num_ids;
 	INIT_LIST_HEAD(&master->bonds);
 	dev_iommu_priv_set(dev, master);
 
-	/* Check the SIDs are in range of the SMMU and our stream table */
-	for (i = 0; i < master->num_sids; i++) {
-		u32 sid = master->sids[i];
-
-		if (!arm_smmu_sid_in_range(smmu, sid)) {
-			ret = -ERANGE;
-			goto err_free_master;
-		}
-
-		/* Ensure l2 strtab is initialised */
-		if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB) {
-			ret = arm_smmu_init_l2_strtab(smmu, sid);
-			if (ret)
-				goto err_free_master;
-		}
-	}
+	ret = arm_smmu_insert_master(smmu, master);
+	if (ret)
+		goto err_free_master;
 
 	device_property_read_u32(dev, "pasid-num-bits", &master->ssid_bits);
 	master->ssid_bits = min(smmu->ssid_bits, master->ssid_bits);
@@ -2432,6 +2530,7 @@  static void arm_smmu_release_device(struct device *dev)
 	WARN_ON(arm_smmu_master_sva_enabled(master));
 	arm_smmu_detach_dev(master);
 	arm_smmu_disable_pasid(master);
+	arm_smmu_remove_master(master);
 	kfree(master);
 	iommu_fwspec_free(dev);
 }
@@ -2855,6 +2954,9 @@  static int arm_smmu_init_structures(struct arm_smmu_device *smmu)
 {
 	int ret;
 
+	mutex_init(&smmu->streams_mutex);
+	smmu->streams = RB_ROOT;
+
 	ret = arm_smmu_init_queues(smmu);
 	if (ret)
 		return ret;