Changes since v18:
- Addressing Stephen's comment [5]:
Replaced the entire clock bulk data filling and handling with
devm_clk_bulk_get_all().
Changes since v17:
- Addressing Will's comment to embed Thor's change [2] for pulling
clocks information from device tree. This is done by squashing
Thor's change [2] in v17's 1/5 patch [3].
- Another minor change is addition of runtime pm hooks to
arm_smmu_iova_to_phys_hard().
Previous version of this patch series is @ [1].
Also refer to [4] for change logs for previous versions.
[1] https://lore.kernel.org/patchwork/cover/1017699/
[2] https://lore.kernel.org/patchwork/patch/996143/
[3] https://lore.kernel.org/patchwork/patch/1013167/
[4] https://lore.kernel.org/patchwork/cover/979429/
[5] https://lore.kernel.org/patchwork/patch/1017700/
Sricharan R (3):
iommu/arm-smmu: Add pm_runtime/sleep ops
iommu/arm-smmu: Invoke pm_runtime during probe, add/remove device
iommu/arm-smmu: Add the device_link between masters and smmu
Vivek Gautam (2):
dt-bindings: arm-smmu: Add bindings for qcom,smmu-v2
iommu/arm-smmu: Add support for qcom,smmu-v2 variant
.../devicetree/bindings/iommu/arm,smmu.txt | 39 +++++
drivers/iommu/arm-smmu.c | 170 +++++++++++++++++++--
2 files changed, 197 insertions(+), 12 deletions(-)
--
QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a member
of Code Aurora Forum, hosted by The Linux Foundation
From: Sricharan R <[email protected]>
The smmu needs to be functional only when the respective
master's using it are active. The device_link feature
helps to track such functional dependencies, so that the
iommu gets powered when the master device enables itself
using pm_runtime. So by adapting the smmu driver for
runtime pm, above said dependency can be addressed.
This patch adds the pm runtime/sleep callbacks to the
driver and the corresponding bulk clock handling for all
the clocks needed by smmu.
Also, while we enable the runtime pm, add a pm sleep suspend
callback that pushes devices to low power state by turning
the clocks off in a system sleep.
Add corresponding clock enable path in resume callback as well.
Signed-off-by: Sricharan R <[email protected]>
Signed-off-by: Archit Taneja <[email protected]>
[Thor: Rework to get clocks from device tree]
Signed-off-by: Thor Thayer <[email protected]>
[vivek: rework for clock and pm ops]
Signed-off-by: Vivek Gautam <[email protected]>
Reviewed-by: Tomasz Figa <[email protected]>
Tested-by: Srinivas Kandagatla <[email protected]>
Reviewed-by: Robin Murphy <[email protected]>
Tested-by: Thor Thayer <[email protected]>
---
Changes since v18:
- Replaced the entire clock bulk data filling and handling with
devm_clk_bulk_get_all().
drivers/iommu/arm-smmu.c | 58 +++++++++++++++++++++++++++++++++++++++++++++---
1 file changed, 55 insertions(+), 3 deletions(-)
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 5a28ae892504..602b67d4f2d6 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -48,6 +48,7 @@
#include <linux/of_iommu.h>
#include <linux/pci.h>
#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
@@ -206,6 +207,8 @@ struct arm_smmu_device {
u32 num_global_irqs;
u32 num_context_irqs;
unsigned int *irqs;
+ struct clk_bulk_data *clks;
+ int num_clks;
u32 cavium_id_base; /* Specific to Cavium */
@@ -1947,7 +1950,7 @@ struct arm_smmu_match_data {
};
#define ARM_SMMU_MATCH_DATA(name, ver, imp) \
-static struct arm_smmu_match_data name = { .version = ver, .model = imp }
+static const struct arm_smmu_match_data name = { .version = ver, .model = imp }
ARM_SMMU_MATCH_DATA(smmu_generic_v1, ARM_SMMU_V1, GENERIC_SMMU);
ARM_SMMU_MATCH_DATA(smmu_generic_v2, ARM_SMMU_V2, GENERIC_SMMU);
@@ -2150,6 +2153,17 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
smmu->irqs[i] = irq;
}
+ err = devm_clk_bulk_get_all(dev, &smmu->clks);
+ if (err < 0) {
+ dev_err(dev, "failed to get clocks %d\n", err);
+ return err;
+ }
+ smmu->num_clks = err;
+
+ err = clk_bulk_prepare_enable(smmu->num_clks, smmu->clks);
+ if (err)
+ return err;
+
err = arm_smmu_device_cfg_probe(smmu);
if (err)
return err;
@@ -2236,6 +2250,9 @@ static int arm_smmu_device_remove(struct platform_device *pdev)
/* Turn the thing off */
writel(sCR0_CLIENTPD, ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sCR0);
+
+ clk_bulk_disable_unprepare(smmu->num_clks, smmu->clks);
+
return 0;
}
@@ -2244,15 +2261,50 @@ static void arm_smmu_device_shutdown(struct platform_device *pdev)
arm_smmu_device_remove(pdev);
}
-static int __maybe_unused arm_smmu_pm_resume(struct device *dev)
+static int __maybe_unused arm_smmu_runtime_resume(struct device *dev)
{
struct arm_smmu_device *smmu = dev_get_drvdata(dev);
+ int ret;
+
+ ret = clk_bulk_enable(smmu->num_clks, smmu->clks);
+ if (ret)
+ return ret;
arm_smmu_device_reset(smmu);
+
return 0;
}
-static SIMPLE_DEV_PM_OPS(arm_smmu_pm_ops, NULL, arm_smmu_pm_resume);
+static int __maybe_unused arm_smmu_runtime_suspend(struct device *dev)
+{
+ struct arm_smmu_device *smmu = dev_get_drvdata(dev);
+
+ clk_bulk_disable(smmu->num_clks, smmu->clks);
+
+ return 0;
+}
+
+static int __maybe_unused arm_smmu_pm_resume(struct device *dev)
+{
+ if (pm_runtime_suspended(dev))
+ return 0;
+
+ return arm_smmu_runtime_resume(dev);
+}
+
+static int __maybe_unused arm_smmu_pm_suspend(struct device *dev)
+{
+ if (pm_runtime_suspended(dev))
+ return 0;
+
+ return arm_smmu_runtime_suspend(dev);
+}
+
+static const struct dev_pm_ops arm_smmu_pm_ops = {
+ SET_SYSTEM_SLEEP_PM_OPS(arm_smmu_pm_suspend, arm_smmu_pm_resume)
+ SET_RUNTIME_PM_OPS(arm_smmu_runtime_suspend,
+ arm_smmu_runtime_resume, NULL)
+};
static struct platform_driver arm_smmu_driver = {
.driver = {
--
QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a member
of Code Aurora Forum, hosted by The Linux Foundation
From: Sricharan R <[email protected]>
Enable pm-runtime on devices that implement a pm domain. Then,
add pm runtime hooks to several iommu_ops to power cycle the
smmu device for explicit TLB invalidation requests, and
register space accesses, etc.
We need these hooks when the smmu, linked to its master through
device links, has to be powered-up without the master device
being in context.
Signed-off-by: Sricharan R <[email protected]>
[vivek: Cleanup pm runtime calls]
Signed-off-by: Vivek Gautam <[email protected]>
Reviewed-by: Tomasz Figa <[email protected]>
Tested-by: Srinivas Kandagatla <[email protected]>
Reviewed-by: Robin Murphy <[email protected]>
---
Changes since v18:
None.
drivers/iommu/arm-smmu.c | 108 ++++++++++++++++++++++++++++++++++++++++++-----
1 file changed, 98 insertions(+), 10 deletions(-)
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 602b67d4f2d6..1917d214c4d9 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -270,6 +270,20 @@ static struct arm_smmu_option_prop arm_smmu_options[] = {
{ 0, NULL},
};
+static inline int arm_smmu_rpm_get(struct arm_smmu_device *smmu)
+{
+ if (pm_runtime_enabled(smmu->dev))
+ return pm_runtime_get_sync(smmu->dev);
+
+ return 0;
+}
+
+static inline void arm_smmu_rpm_put(struct arm_smmu_device *smmu)
+{
+ if (pm_runtime_enabled(smmu->dev))
+ pm_runtime_put(smmu->dev);
+}
+
static struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom)
{
return container_of(dom, struct arm_smmu_domain, domain);
@@ -929,11 +943,15 @@ static void arm_smmu_destroy_domain_context(struct iommu_domain *domain)
struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
struct arm_smmu_device *smmu = smmu_domain->smmu;
struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
- int irq;
+ int ret, irq;
if (!smmu || domain->type == IOMMU_DOMAIN_IDENTITY)
return;
+ ret = arm_smmu_rpm_get(smmu);
+ if (ret < 0)
+ return;
+
/*
* Disable the context bank and free the page tables before freeing
* it.
@@ -948,6 +966,8 @@ static void arm_smmu_destroy_domain_context(struct iommu_domain *domain)
free_io_pgtable_ops(smmu_domain->pgtbl_ops);
__arm_smmu_free_bitmap(smmu->context_map, cfg->cbndx);
+
+ arm_smmu_rpm_put(smmu);
}
static struct iommu_domain *arm_smmu_domain_alloc(unsigned type)
@@ -1229,10 +1249,15 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
return -ENODEV;
smmu = fwspec_smmu(fwspec);
+
+ ret = arm_smmu_rpm_get(smmu);
+ if (ret < 0)
+ return ret;
+
/* Ensure that the domain is finalised */
ret = arm_smmu_init_domain_context(domain, smmu);
if (ret < 0)
- return ret;
+ goto rpm_put;
/*
* Sanity check the domain. We don't support domains across
@@ -1242,49 +1267,74 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
dev_err(dev,
"cannot attach to SMMU %s whilst already attached to domain on SMMU %s\n",
dev_name(smmu_domain->smmu->dev), dev_name(smmu->dev));
- return -EINVAL;
+ ret = -EINVAL;
+ goto rpm_put;
}
/* Looks ok, so add the device to the domain */
- return arm_smmu_domain_add_master(smmu_domain, fwspec);
+ ret = arm_smmu_domain_add_master(smmu_domain, fwspec);
+
+rpm_put:
+ arm_smmu_rpm_put(smmu);
+ return ret;
}
static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova,
phys_addr_t paddr, size_t size, int prot)
{
struct io_pgtable_ops *ops = to_smmu_domain(domain)->pgtbl_ops;
+ struct arm_smmu_device *smmu = to_smmu_domain(domain)->smmu;
+ int ret;
if (!ops)
return -ENODEV;
- return ops->map(ops, iova, paddr, size, prot);
+ arm_smmu_rpm_get(smmu);
+ ret = ops->map(ops, iova, paddr, size, prot);
+ arm_smmu_rpm_put(smmu);
+
+ return ret;
}
static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
size_t size)
{
struct io_pgtable_ops *ops = to_smmu_domain(domain)->pgtbl_ops;
+ struct arm_smmu_device *smmu = to_smmu_domain(domain)->smmu;
+ size_t ret;
if (!ops)
return 0;
- return ops->unmap(ops, iova, size);
+ arm_smmu_rpm_get(smmu);
+ ret = ops->unmap(ops, iova, size);
+ arm_smmu_rpm_put(smmu);
+
+ return ret;
}
static void arm_smmu_flush_iotlb_all(struct iommu_domain *domain)
{
struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+ struct arm_smmu_device *smmu = smmu_domain->smmu;
- if (smmu_domain->tlb_ops)
+ if (smmu_domain->tlb_ops) {
+ arm_smmu_rpm_get(smmu);
smmu_domain->tlb_ops->tlb_flush_all(smmu_domain);
+ arm_smmu_rpm_put(smmu);
+ }
}
static void arm_smmu_iotlb_sync(struct iommu_domain *domain)
{
struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+ struct arm_smmu_device *smmu = smmu_domain->smmu;
- if (smmu_domain->tlb_ops)
+ if (smmu_domain->tlb_ops) {
+ arm_smmu_rpm_get(smmu);
smmu_domain->tlb_ops->tlb_sync(smmu_domain);
+ arm_smmu_rpm_put(smmu);
+ }
}
static phys_addr_t arm_smmu_iova_to_phys_hard(struct iommu_domain *domain,
@@ -1299,6 +1349,11 @@ static phys_addr_t arm_smmu_iova_to_phys_hard(struct iommu_domain *domain,
u32 tmp;
u64 phys;
unsigned long va, flags;
+ int ret;
+
+ ret = arm_smmu_rpm_get(smmu);
+ if (ret < 0)
+ return 0;
cb_base = ARM_SMMU_CB(smmu, cfg->cbndx);
@@ -1327,6 +1382,8 @@ static phys_addr_t arm_smmu_iova_to_phys_hard(struct iommu_domain *domain,
return 0;
}
+ arm_smmu_rpm_put(smmu);
+
return (phys & GENMASK_ULL(39, 12)) | (iova & 0xfff);
}
@@ -1431,7 +1488,13 @@ static int arm_smmu_add_device(struct device *dev)
while (i--)
cfg->smendx[i] = INVALID_SMENDX;
+ ret = arm_smmu_rpm_get(smmu);
+ if (ret < 0)
+ goto out_cfg_free;
+
ret = arm_smmu_master_alloc_smes(dev);
+ arm_smmu_rpm_put(smmu);
+
if (ret)
goto out_cfg_free;
@@ -1451,7 +1514,7 @@ static void arm_smmu_remove_device(struct device *dev)
struct iommu_fwspec *fwspec = dev->iommu_fwspec;
struct arm_smmu_master_cfg *cfg;
struct arm_smmu_device *smmu;
-
+ int ret;
if (!fwspec || fwspec->ops != &arm_smmu_ops)
return;
@@ -1459,8 +1522,15 @@ static void arm_smmu_remove_device(struct device *dev)
cfg = fwspec->iommu_priv;
smmu = cfg->smmu;
+ ret = arm_smmu_rpm_get(smmu);
+ if (ret < 0)
+ return;
+
iommu_device_unlink(&smmu->iommu, dev);
arm_smmu_master_free_smes(fwspec);
+
+ arm_smmu_rpm_put(smmu);
+
iommu_group_remove_device(dev);
kfree(fwspec->iommu_priv);
iommu_fwspec_free(dev);
@@ -2213,6 +2283,17 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
arm_smmu_device_reset(smmu);
arm_smmu_test_smr_masks(smmu);
+ /*
+ * We want to avoid touching dev->power.lock in fastpaths unless
+ * it's really going to do something useful - pm_runtime_enabled()
+ * can serve as an ideal proxy for that decision. So, conditionally
+ * enable pm_runtime.
+ */
+ if (dev->pm_domain) {
+ pm_runtime_set_active(dev);
+ pm_runtime_enable(dev);
+ }
+
/*
* For ACPI and generic DT bindings, an SMMU will be probed before
* any device which might need it, so we want the bus ops in place
@@ -2248,10 +2329,17 @@ static int arm_smmu_device_remove(struct platform_device *pdev)
if (!bitmap_empty(smmu->context_map, ARM_SMMU_MAX_CBS))
dev_err(&pdev->dev, "removing device with active domains!\n");
+ arm_smmu_rpm_get(smmu);
/* Turn the thing off */
writel(sCR0_CLIENTPD, ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sCR0);
+ arm_smmu_rpm_put(smmu);
+
+ if (pm_runtime_enabled(smmu->dev))
+ pm_runtime_force_suspend(smmu->dev);
+ else
+ clk_bulk_disable(smmu->num_clks, smmu->clks);
- clk_bulk_disable_unprepare(smmu->num_clks, smmu->clks);
+ clk_bulk_unprepare(smmu->num_clks, smmu->clks);
return 0;
}
--
QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a member
of Code Aurora Forum, hosted by The Linux Foundation
From: Sricharan R <[email protected]>
Finally add the device link between the master device and
smmu, so that the smmu gets runtime enabled/disabled only when the
master needs it. This is done from add_device callback which gets
called once when the master is added to the smmu.
Signed-off-by: Sricharan R <[email protected]>
Signed-off-by: Vivek Gautam <[email protected]>
Reviewed-by: Tomasz Figa <[email protected]>
Tested-by: Srinivas Kandagatla <[email protected]>
Reviewed-by: Robin Murphy <[email protected]>
---
Changes since v18:
None.
drivers/iommu/arm-smmu.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 1917d214c4d9..b6b11642b3a9 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -1500,6 +1500,9 @@ static int arm_smmu_add_device(struct device *dev)
iommu_device_link(&smmu->iommu, dev);
+ device_link_add(dev, smmu->dev,
+ DL_FLAG_PM_RUNTIME | DL_FLAG_AUTOREMOVE_SUPPLIER);
+
return 0;
out_cfg_free:
--
QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a member
of Code Aurora Forum, hosted by The Linux Foundation
qcom,smmu-v2 is an arm,smmu-v2 implementation with specific
clock and power requirements.
On msm8996, multiple cores, viz. mdss, video, etc. use this
smmu. On sdm845, this smmu is used with gpu.
Add bindings for the same.
Signed-off-by: Vivek Gautam <[email protected]>
Reviewed-by: Rob Herring <[email protected]>
Reviewed-by: Tomasz Figa <[email protected]>
Tested-by: Srinivas Kandagatla <[email protected]>
Reviewed-by: Robin Murphy <[email protected]>
---
Changes since v18:
None.
drivers/iommu/arm-smmu.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index b6b11642b3a9..ba18d89d4732 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -120,6 +120,7 @@ enum arm_smmu_implementation {
GENERIC_SMMU,
ARM_MMU500,
CAVIUM_SMMUV2,
+ QCOM_SMMUV2,
};
struct arm_smmu_s2cr {
@@ -2030,6 +2031,7 @@ ARM_SMMU_MATCH_DATA(smmu_generic_v2, ARM_SMMU_V2, GENERIC_SMMU);
ARM_SMMU_MATCH_DATA(arm_mmu401, ARM_SMMU_V1_64K, GENERIC_SMMU);
ARM_SMMU_MATCH_DATA(arm_mmu500, ARM_SMMU_V2, ARM_MMU500);
ARM_SMMU_MATCH_DATA(cavium_smmuv2, ARM_SMMU_V2, CAVIUM_SMMUV2);
+ARM_SMMU_MATCH_DATA(qcom_smmuv2, ARM_SMMU_V2, QCOM_SMMUV2);
static const struct of_device_id arm_smmu_of_match[] = {
{ .compatible = "arm,smmu-v1", .data = &smmu_generic_v1 },
@@ -2038,6 +2040,7 @@ static const struct of_device_id arm_smmu_of_match[] = {
{ .compatible = "arm,mmu-401", .data = &arm_mmu401 },
{ .compatible = "arm,mmu-500", .data = &arm_mmu500 },
{ .compatible = "cavium,smmu-v2", .data = &cavium_smmuv2 },
+ { .compatible = "qcom,smmu-v2", .data = &qcom_smmuv2 },
{ },
};
MODULE_DEVICE_TABLE(of, arm_smmu_of_match);
--
QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a member
of Code Aurora Forum, hosted by The Linux Foundation
Add bindings doc for Qcom's smmu-v2 implementation.
Signed-off-by: Vivek Gautam <[email protected]>
Reviewed-by: Tomasz Figa <[email protected]>
Tested-by: Srinivas Kandagatla <[email protected]>
Reviewed-by: Rob Herring <[email protected]>
Reviewed-by: Robin Murphy <[email protected]>
---
Changes since v18:
None.
.../devicetree/bindings/iommu/arm,smmu.txt | 39 ++++++++++++++++++++++
1 file changed, 39 insertions(+)
diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu.txt b/Documentation/devicetree/bindings/iommu/arm,smmu.txt
index 8a6ffce12af5..a6504b37cc21 100644
--- a/Documentation/devicetree/bindings/iommu/arm,smmu.txt
+++ b/Documentation/devicetree/bindings/iommu/arm,smmu.txt
@@ -17,10 +17,16 @@ conditions.
"arm,mmu-401"
"arm,mmu-500"
"cavium,smmu-v2"
+ "qcom,smmu-v2"
depending on the particular implementation and/or the
version of the architecture implemented.
+ Qcom SoCs must contain, as below, SoC-specific compatibles
+ along with "qcom,smmu-v2":
+ "qcom,msm8996-smmu-v2", "qcom,smmu-v2",
+ "qcom,sdm845-smmu-v2", "qcom,smmu-v2".
+
- reg : Base address and size of the SMMU.
- #global-interrupts : The number of global interrupts exposed by the
@@ -71,6 +77,22 @@ conditions.
or using stream matching with #iommu-cells = <2>, and
may be ignored if present in such cases.
+- clock-names: List of the names of clocks input to the device. The
+ required list depends on particular implementation and
+ is as follows:
+ - for "qcom,smmu-v2":
+ - "bus": clock required for downstream bus access and
+ for the smmu ptw,
+ - "iface": clock required to access smmu's registers
+ through the TCU's programming interface.
+ - unspecified for other implementations.
+
+- clocks: Specifiers for all clocks listed in the clock-names property,
+ as per generic clock bindings.
+
+- power-domains: Specifiers for power domains required to be powered on for
+ the SMMU to operate, as per generic power domain bindings.
+
** Deprecated properties:
- mmu-masters (deprecated in favour of the generic "iommus" binding) :
@@ -137,3 +159,20 @@ conditions.
iommu-map = <0 &smmu3 0 0x400>;
...
};
+
+ /* Qcom's arm,smmu-v2 implementation */
+ smmu4: iommu@d00000 {
+ compatible = "qcom,msm8996-smmu-v2", "qcom,smmu-v2";
+ reg = <0xd00000 0x10000>;
+
+ #global-interrupts = <1>;
+ interrupts = <GIC_SPI 73 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 320 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 321 IRQ_TYPE_LEVEL_HIGH>;
+ #iommu-cells = <1>;
+ power-domains = <&mmcc MDSS_GDSC>;
+
+ clocks = <&mmcc SMMU_MDP_AXI_CLK>,
+ <&mmcc SMMU_MDP_AHB_CLK>;
+ clock-names = "bus", "iface";
+ };
--
QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a member
of Code Aurora Forum, hosted by The Linux Foundation