[PATCH v2 0/6] iommu/arm-smmu-v3: Finish PASID support and command queue batching

[PATCH v2 0/6] iommu/arm-smmu-v3: Finish PASID support and command queue batching

[Jean-Philippe Brucker]

Finish off PASID support for SMMUv3, and batch command queue.

Since v1 [1]:
* Added patch 4 to factor command queue batching
* Included patch 6 from Rob [2]

[1] https://lore.kernel.org/linux-iommu/20200213101435.229932-1-jean-philippe@linaro.org/
[2] https://lore.kernel.org/linux-iommu/20200213205600.19690-1-robh@kernel.org/

Jean-Philippe Brucker (5):
  PCI/ATS: Export symbols of PASID functions
  iommu/arm-smmu-v3: Add support for PCI PASID
  iommu/arm-smmu-v3: Write level-1 descriptors atomically
  iommu/arm-smmu-v3: Add command queue batching helpers
  iommu/arm-smmu-v3: Batch context descriptor invalidation

Rob Herring (1):
  iommu/arm-smmu-v3: Batch ATC invalidation commands

 drivers/iommu/arm-smmu-v3.c | 139 ++++++++++++++++++++++++++++--------
 drivers/pci/ats.c           |   4 ++
 2 files changed, 115 insertions(+), 28 deletions(-)

-- 
2.25.0

[PATCH v2 1/6] PCI/ATS: Export symbols of PASID functions

[Jean-Philippe Brucker]

The Arm SMMUv3 driver uses pci_{enable,disable}_pasid() and related
functions.  Export them to allow the driver to be built as a module.

Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
---
 drivers/pci/ats.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c
index 3ef0bb281e7c..390e92f2d8d1 100644
--- a/drivers/pci/ats.c
+++ b/drivers/pci/ats.c
@@ -366,6 +366,7 @@ int pci_enable_pasid(struct pci_dev *pdev, int features)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(pci_enable_pasid);
 
 /**
  * pci_disable_pasid - Disable the PASID capability
@@ -390,6 +391,7 @@ void pci_disable_pasid(struct pci_dev *pdev)
 
 	pdev->pasid_enabled = 0;
 }
+EXPORT_SYMBOL_GPL(pci_disable_pasid);
 
 /**
  * pci_restore_pasid_state - Restore PASID capabilities
@@ -441,6 +443,7 @@ int pci_pasid_features(struct pci_dev *pdev)
 
 	return supported;
 }
+EXPORT_SYMBOL_GPL(pci_pasid_features);
 
 #define PASID_NUMBER_SHIFT	8
 #define PASID_NUMBER_MASK	(0x1f << PASID_NUMBER_SHIFT)
@@ -469,4 +472,5 @@ int pci_max_pasids(struct pci_dev *pdev)
 
 	return (1 << supported);
 }
+EXPORT_SYMBOL_GPL(pci_max_pasids);
 #endif /* CONFIG_PCI_PASID */
-- 
2.25.0

Re: [PATCH v2 1/6] PCI/ATS: Export symbols of PASID functions

[Bjorn Helgaas]

On Mon, Feb 24, 2020 at 05:58:41PM +0100, Jean-Philippe Brucker wrote:
> The Arm SMMUv3 driver uses pci_{enable,disable}_pasid() and related
> functions.  Export them to allow the driver to be built as a module.
> 
> Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>

Acked-by: Bjorn Helgaas <bhelgaas@google.com>

> ---
>  drivers/pci/ats.c | 4 ++++
>  1 file changed, 4 insertions(+)
> 
> diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c
> index 3ef0bb281e7c..390e92f2d8d1 100644
> --- a/drivers/pci/ats.c
> +++ b/drivers/pci/ats.c
> @@ -366,6 +366,7 @@ int pci_enable_pasid(struct pci_dev *pdev, int features)
>  
>  	return 0;
>  }
> +EXPORT_SYMBOL_GPL(pci_enable_pasid);
>  
>  /**
>   * pci_disable_pasid - Disable the PASID capability
> @@ -390,6 +391,7 @@ void pci_disable_pasid(struct pci_dev *pdev)
>  
>  	pdev->pasid_enabled = 0;
>  }
> +EXPORT_SYMBOL_GPL(pci_disable_pasid);
>  
>  /**
>   * pci_restore_pasid_state - Restore PASID capabilities
> @@ -441,6 +443,7 @@ int pci_pasid_features(struct pci_dev *pdev)
>  
>  	return supported;
>  }
> +EXPORT_SYMBOL_GPL(pci_pasid_features);
>  
>  #define PASID_NUMBER_SHIFT	8
>  #define PASID_NUMBER_MASK	(0x1f << PASID_NUMBER_SHIFT)
> @@ -469,4 +472,5 @@ int pci_max_pasids(struct pci_dev *pdev)
>  
>  	return (1 << supported);
>  }
> +EXPORT_SYMBOL_GPL(pci_max_pasids);
>  #endif /* CONFIG_PCI_PASID */
> -- 
> 2.25.0
> 

Re: [PATCH v2 1/6] PCI/ATS: Export symbols of PASID functions

[Will Deacon]

On Wed, Mar 18, 2020 at 01:36:06PM -0500, Bjorn Helgaas wrote:
> On Mon, Feb 24, 2020 at 05:58:41PM +0100, Jean-Philippe Brucker wrote:
> > The Arm SMMUv3 driver uses pci_{enable,disable}_pasid() and related
> > functions.  Export them to allow the driver to be built as a module.
> > 
> > Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
> 
> Acked-by: Bjorn Helgaas <bhelgaas@google.com>

Cheers, Bjorn. I'll queue this series in the Arm SMMU tree.

Will

[PATCH v2 2/6] iommu/arm-smmu-v3: Add support for PCI PASID

[Jean-Philippe Brucker]

Enable PASID for PCI devices that support it. Initialize PASID early in
add_device() because it must be enabled before ATS.

Tested-by: Zhangfei Gao <zhangfei.gao@linaro.org>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
---
 drivers/iommu/arm-smmu-v3.c | 62 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 61 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index aa3ac2a03807..6b76df37025e 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -2628,6 +2628,53 @@ static void arm_smmu_disable_ats(struct arm_smmu_master *master)
 	atomic_dec(&smmu_domain->nr_ats_masters);
 }
 
+static int arm_smmu_enable_pasid(struct arm_smmu_master *master)
+{
+	int ret;
+	int features;
+	int num_pasids;
+	struct pci_dev *pdev;
+
+	if (!dev_is_pci(master->dev))
+		return -ENODEV;
+
+	pdev = to_pci_dev(master->dev);
+
+	features = pci_pasid_features(pdev);
+	if (features < 0)
+		return features;
+
+	num_pasids = pci_max_pasids(pdev);
+	if (num_pasids <= 0)
+		return num_pasids;
+
+	ret = pci_enable_pasid(pdev, features);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to enable PASID\n");
+		return ret;
+	}
+
+	master->ssid_bits = min_t(u8, ilog2(num_pasids),
+				  master->smmu->ssid_bits);
+	return 0;
+}
+
+static void arm_smmu_disable_pasid(struct arm_smmu_master *master)
+{
+	struct pci_dev *pdev;
+
+	if (!dev_is_pci(master->dev))
+		return;
+
+	pdev = to_pci_dev(master->dev);
+
+	if (!pdev->pasid_enabled)
+		return;
+
+	master->ssid_bits = 0;
+	pci_disable_pasid(pdev);
+}
+
 static void arm_smmu_detach_dev(struct arm_smmu_master *master)
 {
 	unsigned long flags;
@@ -2831,13 +2878,23 @@ static int arm_smmu_add_device(struct device *dev)
 
 	master->ssid_bits = min(smmu->ssid_bits, fwspec->num_pasid_bits);
 
+	/*
+	 * Note that PASID must be enabled before, and disabled after ATS:
+	 * PCI Express Base 4.0r1.0 - 10.5.1.3 ATS Control Register
+	 *
+	 *   Behavior is undefined if this bit is Set and the value of the PASID
+	 *   Enable, Execute Requested Enable, or Privileged Mode Requested bits
+	 *   are changed.
+	 */
+	arm_smmu_enable_pasid(master);
+
 	if (!(smmu->features & ARM_SMMU_FEAT_2_LVL_CDTAB))
 		master->ssid_bits = min_t(u8, master->ssid_bits,
 					  CTXDESC_LINEAR_CDMAX);
 
 	ret = iommu_device_link(&smmu->iommu, dev);
 	if (ret)
-		goto err_free_master;
+		goto err_disable_pasid;
 
 	group = iommu_group_get_for_dev(dev);
 	if (IS_ERR(group)) {
@@ -2850,6 +2907,8 @@ static int arm_smmu_add_device(struct device *dev)
 
 err_unlink:
 	iommu_device_unlink(&smmu->iommu, dev);
+err_disable_pasid:
+	arm_smmu_disable_pasid(master);
 err_free_master:
 	kfree(master);
 	fwspec->iommu_priv = NULL;
@@ -2870,6 +2929,7 @@ static void arm_smmu_remove_device(struct device *dev)
 	arm_smmu_detach_dev(master);
 	iommu_group_remove_device(dev);
 	iommu_device_unlink(&smmu->iommu, dev);
+	arm_smmu_disable_pasid(master);
 	kfree(master);
 	iommu_fwspec_free(dev);
 }
-- 
2.25.0

[PATCH v2 3/6] iommu/arm-smmu-v3: Write level-1 descriptors atomically

[Jean-Philippe Brucker]

Use WRITE_ONCE() to make sure that the SMMU doesn't read incomplete
stream table descriptors. Refer to the comment about 64-bit accesses,
and add the comment to the equivalent context descriptor code.

Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
---
 drivers/iommu/arm-smmu-v3.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index 6b76df37025e..068a16d0eabe 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -1531,6 +1531,7 @@ static void arm_smmu_write_cd_l1_desc(__le64 *dst,
 	u64 val = (l1_desc->l2ptr_dma & CTXDESC_L1_DESC_L2PTR_MASK) |
 		  CTXDESC_L1_DESC_V;
 
+	/* See comment in arm_smmu_write_ctx_desc() */
 	WRITE_ONCE(*dst, cpu_to_le64(val));
 }
 
@@ -1726,7 +1727,8 @@ arm_smmu_write_strtab_l1_desc(__le64 *dst, struct arm_smmu_strtab_l1_desc *desc)
 	val |= FIELD_PREP(STRTAB_L1_DESC_SPAN, desc->span);
 	val |= desc->l2ptr_dma & STRTAB_L1_DESC_L2PTR_MASK;
 
-	*dst = cpu_to_le64(val);
+	/* See comment in arm_smmu_write_ctx_desc() */
+	WRITE_ONCE(*dst, cpu_to_le64(val));
 }
 
 static void arm_smmu_sync_ste_for_sid(struct arm_smmu_device *smmu, u32 sid)
-- 
2.25.0

[PATCH v2 4/6] iommu/arm-smmu-v3: Add command queue batching helpers

[Jean-Philippe Brucker]

As more functions will implement command queue batching, add two helpers
to simplify building a command list.

Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
---
 drivers/iommu/arm-smmu-v3.c | 37 ++++++++++++++++++++++++++-----------
 1 file changed, 26 insertions(+), 11 deletions(-)

diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index 068a16d0eabe..beeec366bc41 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -548,6 +548,11 @@ struct arm_smmu_cmdq {
 	atomic_t			lock;
 };
 
+struct arm_smmu_cmdq_batch {
+	u64				cmds[CMDQ_BATCH_ENTRIES * CMDQ_ENT_DWORDS];
+	int				num;
+};
+
 struct arm_smmu_evtq {
 	struct arm_smmu_queue		q;
 	u32				max_stalls;
@@ -1482,6 +1487,24 @@ static int arm_smmu_cmdq_issue_sync(struct arm_smmu_device *smmu)
 	return arm_smmu_cmdq_issue_cmdlist(smmu, NULL, 0, true);
 }
 
+static void arm_smmu_cmdq_batch_add(struct arm_smmu_device *smmu,
+				    struct arm_smmu_cmdq_batch *cmds,
+				    struct arm_smmu_cmdq_ent *cmd)
+{
+	if (cmds->num == CMDQ_BATCH_ENTRIES) {
+		arm_smmu_cmdq_issue_cmdlist(smmu, cmds->cmds, cmds->num, false);
+		cmds->num = 0;
+	}
+	arm_smmu_cmdq_build_cmd(&cmds->cmds[cmds->num * CMDQ_ENT_DWORDS], cmd);
+	cmds->num++;
+}
+
+static int arm_smmu_cmdq_batch_submit(struct arm_smmu_device *smmu,
+				      struct arm_smmu_cmdq_batch *cmds)
+{
+	return arm_smmu_cmdq_issue_cmdlist(smmu, cmds->cmds, cmds->num, true);
+}
+
 /* Context descriptor manipulation functions */
 static void arm_smmu_sync_cd(struct arm_smmu_domain *smmu_domain,
 			     int ssid, bool leaf)
@@ -2220,10 +2243,9 @@ static void arm_smmu_tlb_inv_range(unsigned long iova, size_t size,
 				   size_t granule, bool leaf,
 				   struct arm_smmu_domain *smmu_domain)
 {
-	u64 cmds[CMDQ_BATCH_ENTRIES * CMDQ_ENT_DWORDS];
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 	unsigned long start = iova, end = iova + size;
-	int i = 0;
+	struct arm_smmu_cmdq_batch cmds = {};
 	struct arm_smmu_cmdq_ent cmd = {
 		.tlbi = {
 			.leaf	= leaf,
@@ -2242,18 +2264,11 @@ static void arm_smmu_tlb_inv_range(unsigned long iova, size_t size,
 	}
 
 	while (iova < end) {
-		if (i == CMDQ_BATCH_ENTRIES) {
-			arm_smmu_cmdq_issue_cmdlist(smmu, cmds, i, false);
-			i = 0;
-		}
-
 		cmd.tlbi.addr = iova;
-		arm_smmu_cmdq_build_cmd(&cmds[i * CMDQ_ENT_DWORDS], &cmd);
+		arm_smmu_cmdq_batch_add(smmu, &cmds, &cmd);
 		iova += granule;
-		i++;
 	}
-
-	arm_smmu_cmdq_issue_cmdlist(smmu, cmds, i, true);
+	arm_smmu_cmdq_batch_submit(smmu, &cmds);
 
 	/*
 	 * Unfortunately, this can't be leaf-only since we may have
-- 
2.25.0

[PATCH v2 5/6] iommu/arm-smmu-v3: Batch context descriptor invalidation

[Jean-Philippe Brucker]

Rather than publishing one command at a time when invalidating a context
descriptor, batch the commands for all SIDs in the domain.

Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
---
 drivers/iommu/arm-smmu-v3.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index beeec366bc41..12b2a0fa747e 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -1512,6 +1512,7 @@ static void arm_smmu_sync_cd(struct arm_smmu_domain *smmu_domain,
 	size_t i;
 	unsigned long flags;
 	struct arm_smmu_master *master;
+	struct arm_smmu_cmdq_batch cmds = {};
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 	struct arm_smmu_cmdq_ent cmd = {
 		.opcode	= CMDQ_OP_CFGI_CD,
@@ -1525,12 +1526,12 @@ static void arm_smmu_sync_cd(struct arm_smmu_domain *smmu_domain,
 	list_for_each_entry(master, &smmu_domain->devices, domain_head) {
 		for (i = 0; i < master->num_sids; i++) {
 			cmd.cfgi.sid = master->sids[i];
-			arm_smmu_cmdq_issue_cmd(smmu, &cmd);
+			arm_smmu_cmdq_batch_add(smmu, &cmds, &cmd);
 		}
 	}
 	spin_unlock_irqrestore(&smmu_domain->devices_lock, flags);
 
-	arm_smmu_cmdq_issue_sync(smmu);
+	arm_smmu_cmdq_batch_submit(smmu, &cmds);
 }
 
 static int arm_smmu_alloc_cd_leaf_table(struct arm_smmu_device *smmu,
-- 
2.25.0

[PATCH v2 6/6] iommu/arm-smmu-v3: Batch ATC invalidation commands

[Jean-Philippe Brucker]

From: Rob Herring <robh@kernel.org>

Similar to commit 2af2e72b18b4 ("iommu/arm-smmu-v3: Defer TLB
invalidation until ->iotlb_sync()"), build up a list of ATC invalidation
commands and submit them all at once to the command queue instead of
one-by-one.

As there is only one caller of arm_smmu_atc_inv_master() left, we can
simplify it and avoid passing in struct arm_smmu_cmdq_ent.

Cc: Jean-Philippe Brucker <jean-philippe@linaro.org>
Cc: Will Deacon <will@kernel.org>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: Joerg Roedel <joro@8bytes.org>
Signed-off-by: Rob Herring <robh@kernel.org>
Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
---
 drivers/iommu/arm-smmu-v3.c | 31 ++++++++++++++++++-------------
 1 file changed, 18 insertions(+), 13 deletions(-)

diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index 12b2a0fa747e..4f0a38dae6db 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -2158,17 +2158,16 @@ arm_smmu_atc_inv_to_cmd(int ssid, unsigned long iova, size_t size,
 	cmd->atc.size	= log2_span;
 }
 
-static int arm_smmu_atc_inv_master(struct arm_smmu_master *master,
-				   struct arm_smmu_cmdq_ent *cmd)
+static int arm_smmu_atc_inv_master(struct arm_smmu_master *master)
 {
 	int i;
+	struct arm_smmu_cmdq_ent cmd;
 
-	if (!master->ats_enabled)
-		return 0;
+	arm_smmu_atc_inv_to_cmd(0, 0, 0, &cmd);
 
 	for (i = 0; i < master->num_sids; i++) {
-		cmd->atc.sid = master->sids[i];
-		arm_smmu_cmdq_issue_cmd(master->smmu, cmd);
+		cmd.atc.sid = master->sids[i];
+		arm_smmu_cmdq_issue_cmd(master->smmu, &cmd);
 	}
 
 	return arm_smmu_cmdq_issue_sync(master->smmu);
@@ -2177,10 +2176,11 @@ static int arm_smmu_atc_inv_master(struct arm_smmu_master *master,
 static int arm_smmu_atc_inv_domain(struct arm_smmu_domain *smmu_domain,
 				   int ssid, unsigned long iova, size_t size)
 {
-	int ret = 0;
+	int i;
 	unsigned long flags;
 	struct arm_smmu_cmdq_ent cmd;
 	struct arm_smmu_master *master;
+	struct arm_smmu_cmdq_batch cmds = {};
 
 	if (!(smmu_domain->smmu->features & ARM_SMMU_FEAT_ATS))
 		return 0;
@@ -2205,11 +2205,18 @@ static int arm_smmu_atc_inv_domain(struct arm_smmu_domain *smmu_domain,
 	arm_smmu_atc_inv_to_cmd(ssid, iova, size, &cmd);
 
 	spin_lock_irqsave(&smmu_domain->devices_lock, flags);
-	list_for_each_entry(master, &smmu_domain->devices, domain_head)
-		ret |= arm_smmu_atc_inv_master(master, &cmd);
+	list_for_each_entry(master, &smmu_domain->devices, domain_head) {
+		if (!master->ats_enabled)
+			continue;
+
+		for (i = 0; i < master->num_sids; i++) {
+			cmd.atc.sid = master->sids[i];
+			arm_smmu_cmdq_batch_add(smmu_domain->smmu, &cmds, &cmd);
+		}
+	}
 	spin_unlock_irqrestore(&smmu_domain->devices_lock, flags);
 
-	return ret ? -ETIMEDOUT : 0;
+	return arm_smmu_cmdq_batch_submit(smmu_domain->smmu, &cmds);
 }
 
 /* IO_PGTABLE API */
@@ -2629,7 +2636,6 @@ static void arm_smmu_enable_ats(struct arm_smmu_master *master)
 
 static void arm_smmu_disable_ats(struct arm_smmu_master *master)
 {
-	struct arm_smmu_cmdq_ent cmd;
 	struct arm_smmu_domain *smmu_domain = master->domain;
 
 	if (!master->ats_enabled)
@@ -2641,8 +2647,7 @@ static void arm_smmu_disable_ats(struct arm_smmu_master *master)
 	 * ATC invalidation via the SMMU.
 	 */
 	wmb();
-	arm_smmu_atc_inv_to_cmd(0, 0, 0, &cmd);
-	arm_smmu_atc_inv_master(master, &cmd);
+	arm_smmu_atc_inv_master(master);
 	atomic_dec(&smmu_domain->nr_ats_masters);
 }
 
-- 
2.25.0