Re: [PATCH 5/9] iommu/arm-smmu: tegra: Detect number of instances at runtime
On 2021-03-25 13:03, Thierry Reding wrote:
From: Thierry Reding
Parse the reg property in device tree and detect the number of instances
represented by a device tree node. This is subsequently needed in order
to support single-instance SMMUs with the Tegra implementation because
additional programming is needed to properly configure the SID override
registers in the memory controller.
Signed-off-by: Thierry Reding
---
drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c | 49 ++--
1 file changed, 34 insertions(+), 15 deletions(-)
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c
b/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c
index 29117444e5a0..5b1170b028f0 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c
@@ -20,13 +20,19 @@
* The third instance usage is through standard arm-smmu driver itself and
* is out of scope of this implementation.
*/
-#define NUM_SMMU_INSTANCES 2
+#define MAX_SMMU_INSTANCES 2
struct nvidia_smmu {
- struct arm_smmu_device smmu;
- void __iomem*bases[NUM_SMMU_INSTANCES];
+ struct arm_smmu_device smmu;
+ void __iomem *bases[MAX_SMMU_INSTANCES];
+ unsigned int num_instances;
Surely it would make more sense to just add a second set of
implementation ops without all the overrides that aren't needed for a
single instance?
Also note that the binding currently requires the Tegra-specific
compatible to have exactly two regions.
Robin.
};
+static inline struct nvidia_smmu *to_nvidia_smmu(struct arm_smmu_device *smmu)
+{
+ return container_of(smmu, struct nvidia_smmu, smmu);
+}
+
static inline void __iomem *nvidia_smmu_page(struct arm_smmu_device *smmu,
unsigned int inst, int page)
{
@@ -47,9 +53,10 @@ static u32 nvidia_smmu_read_reg(struct arm_smmu_device *smmu,
static void nvidia_smmu_write_reg(struct arm_smmu_device *smmu,
int page, int offset, u32 val)
{
+ struct nvidia_smmu *nvidia = to_nvidia_smmu(smmu);
unsigned int i;
- for (i = 0; i < NUM_SMMU_INSTANCES; i++) {
+ for (i = 0; i < nvidia->num_instances; i++) {
void __iomem *reg = nvidia_smmu_page(smmu, i, page) + offset;
writel_relaxed(val, reg);
@@ -67,9 +74,10 @@ static u64 nvidia_smmu_read_reg64(struct arm_smmu_device
*smmu,
static void nvidia_smmu_write_reg64(struct arm_smmu_device *smmu,
int page, int offset, u64 val)
{
+ struct nvidia_smmu *nvidia = to_nvidia_smmu(smmu);
unsigned int i;
- for (i = 0; i < NUM_SMMU_INSTANCES; i++) {
+ for (i = 0; i < nvidia->num_instances; i++) {
void __iomem *reg = nvidia_smmu_page(smmu, i, page) + offset;
writeq_relaxed(val, reg);
@@ -79,6 +87,7 @@ static void nvidia_smmu_write_reg64(struct arm_smmu_device
*smmu,
static void nvidia_smmu_tlb_sync(struct arm_smmu_device *smmu, int page,
int sync, int status)
{
+ struct nvidia_smmu *nvidia = to_nvidia_smmu(smmu);
unsigned int delay;
arm_smmu_writel(smmu, page, sync, 0);
@@ -90,7 +99,7 @@ static void nvidia_smmu_tlb_sync(struct arm_smmu_device
*smmu, int page,
u32 val = 0;
unsigned int i;
- for (i = 0; i < NUM_SMMU_INSTANCES; i++) {
+ for (i = 0; i < nvidia->num_instances; i++) {
void __iomem *reg;
reg = nvidia_smmu_page(smmu, i, page) + status;
@@ -112,9 +121,10 @@ static void nvidia_smmu_tlb_sync(struct arm_smmu_device
*smmu, int page,
static int nvidia_smmu_reset(struct arm_smmu_device *smmu)
{
+ struct nvidia_smmu *nvidia = to_nvidia_smmu(smmu);
unsigned int i;
- for (i = 0; i < NUM_SMMU_INSTANCES; i++) {
+ for (i = 0; i < nvidia->num_instances; i++) {
u32 val;
void __iomem *reg = nvidia_smmu_page(smmu, i, ARM_SMMU_GR0) +
ARM_SMMU_GR0_sGFSR;
@@ -157,8 +167,9 @@ static irqreturn_t nvidia_smmu_global_fault(int irq, void
*dev)
unsigned int inst;
irqreturn_t ret = IRQ_NONE;
struct arm_smmu_device *smmu = dev;
+ struct nvidia_smmu *nvidia = to_nvidia_smmu(smmu);
- for (inst = 0; inst < NUM_SMMU_INSTANCES; inst++) {
+ for (inst = 0; inst < nvidia->num_instances; inst++) {
irqreturn_t irq_ret;
irq_ret = nvidia_smmu_global_fault_inst(irq, smmu, inst);
@@ -202,11 +213,13 @@ static irqreturn_t nvidia_smmu_context_fault(int irq,
void *dev)
struct arm_smmu_device *smmu;
struct iommu_domain *domain = dev;
struct arm_smmu_domain *smmu_domain;
+ struct nvidia_smmu *nvidia;
smmu_domain = container_of(domain, struct arm_smmu_domain, domain);
smmu = smmu_domain->smmu;
+ nvidia =
[PATCH 5/9] iommu/arm-smmu: tegra: Detect number of instances at runtime
From: Thierry Reding
Parse the reg property in device tree and detect the number of instances
represented by a device tree node. This is subsequently needed in order
to support single-instance SMMUs with the Tegra implementation because
additional programming is needed to properly configure the SID override
registers in the memory controller.
Signed-off-by: Thierry Reding
---
drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c | 49 ++--
1 file changed, 34 insertions(+), 15 deletions(-)
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c
b/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c
index 29117444e5a0..5b1170b028f0 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-nvidia.c
@@ -20,13 +20,19 @@
* The third instance usage is through standard arm-smmu driver itself and
* is out of scope of this implementation.
*/
-#define NUM_SMMU_INSTANCES 2
+#define MAX_SMMU_INSTANCES 2
struct nvidia_smmu {
- struct arm_smmu_device smmu;
- void __iomem*bases[NUM_SMMU_INSTANCES];
+ struct arm_smmu_device smmu;
+ void __iomem *bases[MAX_SMMU_INSTANCES];
+ unsigned int num_instances;
};
+static inline struct nvidia_smmu *to_nvidia_smmu(struct arm_smmu_device *smmu)
+{
+ return container_of(smmu, struct nvidia_smmu, smmu);
+}
+
static inline void __iomem *nvidia_smmu_page(struct arm_smmu_device *smmu,
unsigned int inst, int page)
{
@@ -47,9 +53,10 @@ static u32 nvidia_smmu_read_reg(struct arm_smmu_device *smmu,
static void nvidia_smmu_write_reg(struct arm_smmu_device *smmu,
int page, int offset, u32 val)
{
+ struct nvidia_smmu *nvidia = to_nvidia_smmu(smmu);
unsigned int i;
- for (i = 0; i < NUM_SMMU_INSTANCES; i++) {
+ for (i = 0; i < nvidia->num_instances; i++) {
void __iomem *reg = nvidia_smmu_page(smmu, i, page) + offset;
writel_relaxed(val, reg);
@@ -67,9 +74,10 @@ static u64 nvidia_smmu_read_reg64(struct arm_smmu_device
*smmu,
static void nvidia_smmu_write_reg64(struct arm_smmu_device *smmu,
int page, int offset, u64 val)
{
+ struct nvidia_smmu *nvidia = to_nvidia_smmu(smmu);
unsigned int i;
- for (i = 0; i < NUM_SMMU_INSTANCES; i++) {
+ for (i = 0; i < nvidia->num_instances; i++) {
void __iomem *reg = nvidia_smmu_page(smmu, i, page) + offset;
writeq_relaxed(val, reg);
@@ -79,6 +87,7 @@ static void nvidia_smmu_write_reg64(struct arm_smmu_device
*smmu,
static void nvidia_smmu_tlb_sync(struct arm_smmu_device *smmu, int page,
int sync, int status)
{
+ struct nvidia_smmu *nvidia = to_nvidia_smmu(smmu);
unsigned int delay;
arm_smmu_writel(smmu, page, sync, 0);
@@ -90,7 +99,7 @@ static void nvidia_smmu_tlb_sync(struct arm_smmu_device
*smmu, int page,
u32 val = 0;
unsigned int i;
- for (i = 0; i < NUM_SMMU_INSTANCES; i++) {
+ for (i = 0; i < nvidia->num_instances; i++) {
void __iomem *reg;
reg = nvidia_smmu_page(smmu, i, page) + status;
@@ -112,9 +121,10 @@ static void nvidia_smmu_tlb_sync(struct arm_smmu_device
*smmu, int page,
static int nvidia_smmu_reset(struct arm_smmu_device *smmu)
{
+ struct nvidia_smmu *nvidia = to_nvidia_smmu(smmu);
unsigned int i;
- for (i = 0; i < NUM_SMMU_INSTANCES; i++) {
+ for (i = 0; i < nvidia->num_instances; i++) {
u32 val;
void __iomem *reg = nvidia_smmu_page(smmu, i, ARM_SMMU_GR0) +
ARM_SMMU_GR0_sGFSR;
@@ -157,8 +167,9 @@ static irqreturn_t nvidia_smmu_global_fault(int irq, void
*dev)
unsigned int inst;
irqreturn_t ret = IRQ_NONE;
struct arm_smmu_device *smmu = dev;
+ struct nvidia_smmu *nvidia = to_nvidia_smmu(smmu);
- for (inst = 0; inst < NUM_SMMU_INSTANCES; inst++) {
+ for (inst = 0; inst < nvidia->num_instances; inst++) {
irqreturn_t irq_ret;
irq_ret = nvidia_smmu_global_fault_inst(irq, smmu, inst);
@@ -202,11 +213,13 @@ static irqreturn_t nvidia_smmu_context_fault(int irq,
void *dev)
struct arm_smmu_device *smmu;
struct iommu_domain *domain = dev;
struct arm_smmu_domain *smmu_domain;
+ struct nvidia_smmu *nvidia;
smmu_domain = container_of(domain, struct arm_smmu_domain, domain);
smmu = smmu_domain->smmu;
+ nvidia = to_nvidia_smmu(smmu);
- for (inst = 0; inst < NUM_SMMU_INSTANCES; inst++) {
+ for (inst = 0; inst < nvidia->num_instances; inst++) {
irqreturn_t irq_ret;
/*
@@ -241,6 +254,7 @@ struct arm_smmu_device
